2021 |
Purkayastha, Saptarshi; Goyal, Shreya; Oluwalade, Bolu; Phillips, Tyler; Wu, Huanmei; Zou, Xukai Usability and Security of Different Authentication Methods for an Electronic Health Records System Conference Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (HEALTHINF), 2021. @conference{purkayastha2021usability, title = {Usability and Security of Different Authentication Methods for an Electronic Health Records System}, author = {Saptarshi Purkayastha and Shreya Goyal and Bolu Oluwalade and Tyler Phillips and Huanmei Wu and Xukai Zou}, year = {2021}, date = {2021-03-13}, booktitle = {Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (HEALTHINF)}, abstract = {We conducted a survey of 67 graduate students enrolled in the Privacy and Security in Healthcare course at Indiana University Purdue University Indianapolis. This was done to measure user preference and their understanding of usability and security of three different Electronic Health Records authentication methods: single authentication method (username and password), Single sign-on with Central Authentication Service (CAS) authentication method, and a bio-capsule facial authentication method. This research aims to explore the relationship between security and usability, and measure the effect of perceived security on usability in these three aforementioned authentication methods. We developed a formative-formative Partial Least Square Structural Equation Modeling (PLS-SEM) model to measure the relationship between the latent variables of Usability, and Security. The measurement model was developed using five observed variables (measures).-Efficiency and Effectiveness, Satisfaction, Preference, Concerns, and Confidence. The results obtained highlight the importance and impact of these measures on the latent variables and the relationship among the latent variables. From the PLS-SEM analysis, it was found that security has a positive impact on usability for Single sign-on and bio-capsule facial authentication methods. We conclude that the facial authentication method was the most secure and usable among the three authentication methods. Further, descriptive analysis was done to draw out the interesting findings from the survey regarding the observed variables.}, keywords = {}, pubstate = {published}, tppubtype = {conference} } We conducted a survey of 67 graduate students enrolled in the Privacy and Security in Healthcare course at Indiana University Purdue University Indianapolis. This was done to measure user preference and their understanding of usability and security of three different Electronic Health Records authentication methods: single authentication method (username and password), Single sign-on with Central Authentication Service (CAS) authentication method, and a bio-capsule facial authentication method. This research aims to explore the relationship between security and usability, and measure the effect of perceived security on usability in these three aforementioned authentication methods. We developed a formative-formative Partial Least Square Structural Equation Modeling (PLS-SEM) model to measure the relationship between the latent variables of Usability, and Security. The measurement model was developed using five observed variables (measures).-Efficiency and Effectiveness, Satisfaction, Preference, Concerns, and Confidence. The results obtained highlight the importance and impact of these measures on the latent variables and the relationship among the latent variables. From the PLS-SEM analysis, it was found that security has a positive impact on usability for Single sign-on and bio-capsule facial authentication methods. We conclude that the facial authentication method was the most secure and usable among the three authentication methods. Further, descriptive analysis was done to draw out the interesting findings from the survey regarding the observed variables. |
Purkayastha, Saptarshi; Trivedi, Hari; Gichoya, Judy Wawira Failures hiding in success for artificial intelligence in radiology Journal Article Journal of the American College of Radiology, 18 (3), pp. 517-519, 2021. @article{purkayastha2021failures, title = {Failures hiding in success for artificial intelligence in radiology}, author = {Saptarshi Purkayastha and Hari Trivedi and Judy Wawira Gichoya}, doi = {10.1016/j.jacr.2020.11.008}, year = {2021}, date = {2021-03-01}, journal = {Journal of the American College of Radiology}, volume = {18}, number = {3}, pages = {517-519}, abstract = {Reports of computer algorithms outperforming radiologists have persisted over the last 15 years, starting with the 2005 publication by Rubin et al on detecting pulmonary nodules from CT scans. Back then, these technologies were referred to as computer-aided diagnosis, which could be considered as a precursor, of sorts, to what is now referred to broadly as artificial intelligence (AI). Technology gains in hardware over the past 5 years have facilitated the training of deep neural networks with millions of parameters, exponentially accelerating the pace of AI publications. However, like every other scientific field, the successes of AI in radiology are published and publicized with much fanfare, and failures are not discussed or made public. In fact, most AI failures are discovered anecdotally from personal experience or when shared in social media as tweets or blog posts. In this article, we discuss some pitfalls frequently encountered in reporting the success of AI in radiology, which might be considered failures when considered differently. }, keywords = {}, pubstate = {published}, tppubtype = {article} } Reports of computer algorithms outperforming radiologists have persisted over the last 15 years, starting with the 2005 publication by Rubin et al on detecting pulmonary nodules from CT scans. Back then, these technologies were referred to as computer-aided diagnosis, which could be considered as a precursor, of sorts, to what is now referred to broadly as artificial intelligence (AI). Technology gains in hardware over the past 5 years have facilitated the training of deep neural networks with millions of parameters, exponentially accelerating the pace of AI publications. However, like every other scientific field, the successes of AI in radiology are published and publicized with much fanfare, and failures are not discussed or made public. In fact, most AI failures are discovered anecdotally from personal experience or when shared in social media as tweets or blog posts. In this article, we discuss some pitfalls frequently encountered in reporting the success of AI in radiology, which might be considered failures when considered differently. |
Oluwalade, Bolu; Neela, Sunil; Wawira, Judy; Adejumo, Tobiloba; Purkayastha, Saptarshi Human Activity Recognition using Deep Learning Models on Smartphones and Smartwatches Sensor Data Conference Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021), 5 , Science and Technology Publications, 2021, ISBN: 978-989-758-490-9. @conference{oluwalade2021human, title = {Human Activity Recognition using Deep Learning Models on Smartphones and Smartwatches Sensor Data}, author = {Bolu Oluwalade and Sunil Neela and Judy Wawira and Tobiloba Adejumo and Saptarshi Purkayastha}, doi = {10.5220/0010325906450650}, isbn = {978-989-758-490-9}, year = {2021}, date = {2021-02-11}, booktitle = {Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021)}, volume = {5}, pages = {645-650}, publisher = {Science and Technology Publications}, abstract = {In recent years, human activity recognition has garnered considerable attention both in industrial and academic research because of the wide deployment of sensors, such as accelerometers and gyroscopes, in products such as smartphones and smartwatches. Activity recognition is currently applied in various fields where valuable information about an individual’s functional ability and lifestyle is needed. In this study, we used the popular WISDM dataset for activity recognition. Using multivariate analysis of covariance (MANCOVA), we established a statistically significant difference (p< 0.05) between the data generated from the sensors embedded in smartphones and smartwatches. By doing this, we show that smartphones and smartwatches don’t capture data in the same way due to the location where they are worn. We deployed several neural network architectures to classify 15 different hand and non-hand-oriented activities. These models include Long short-term memory (LSTM), Bi-directional Long short-term memory (BiLSTM), Convolutional Neural Network (CNN), and Convolutional LSTM (ConvLSTM). The developed models performed best with watch accelerometer data. Also, we saw that the classification precision obtained with the convolutional input classifiers (CNN and ConvLSTM) was higher than the end-to-end LSTM classifier in 12 of the 15 activities. Additionally, the CNN model for the watch accelerometer was better able to classify non-hand oriented activities when compared to hand-oriented activities.}, keywords = {}, pubstate = {published}, tppubtype = {conference} } In recent years, human activity recognition has garnered considerable attention both in industrial and academic research because of the wide deployment of sensors, such as accelerometers and gyroscopes, in products such as smartphones and smartwatches. Activity recognition is currently applied in various fields where valuable information about an individual’s functional ability and lifestyle is needed. In this study, we used the popular WISDM dataset for activity recognition. Using multivariate analysis of covariance (MANCOVA), we established a statistically significant difference (p< 0.05) between the data generated from the sensors embedded in smartphones and smartwatches. By doing this, we show that smartphones and smartwatches don’t capture data in the same way due to the location where they are worn. We deployed several neural network architectures to classify 15 different hand and non-hand-oriented activities. These models include Long short-term memory (LSTM), Bi-directional Long short-term memory (BiLSTM), Convolutional Neural Network (CNN), and Convolutional LSTM (ConvLSTM). The developed models performed best with watch accelerometer data. Also, we saw that the classification precision obtained with the convolutional input classifiers (CNN and ConvLSTM) was higher than the end-to-end LSTM classifier in 12 of the 15 activities. Additionally, the CNN model for the watch accelerometer was better able to classify non-hand oriented activities when compared to hand-oriented activities. |
2020 |
Tariq, Amara; Purkayastha, Saptarshi; Padmanaban, Geetha Priya; Krupinski, Elizabeth; Trivedi, Hari; Banerjee, Imon; Gichoya, Judy Wawira Current clinical applications of artificial intelligence in radiology and their best supporting evidence Journal Article Journal of the American College of Radiology, 17 (11), pp. 1371-1381, 2020. @article{tariq2020current, title = {Current clinical applications of artificial intelligence in radiology and their best supporting evidence}, author = {Amara Tariq and Saptarshi Purkayastha and Geetha Priya Padmanaban and Elizabeth Krupinski and Hari Trivedi and Imon Banerjee and Judy Wawira Gichoya}, doi = {10.1016/j.jacr.2020.08.018}, year = {2020}, date = {2020-11-02}, journal = {Journal of the American College of Radiology}, volume = {17}, number = {11}, pages = {1371-1381}, publisher = {Elsevier}, abstract = {Purpose Despite tremendous gains from deep learning and the promise of artificial intelligence (AI) in medicine to improve diagnosis and save costs, there exists a large translational gap to implement and use AI products in real-world clinical situations. Adoption of standards such as Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis, Consolidated Standards of Reporting Trials, and the Checklist for Artificial Intelligence in Medical Imaging is increasing to improve the peer-review process and reporting of AI tools. However, no such standards exist for product-level review. Methods A review of clinical trials showed a paucity of evidence for radiology AI products; thus, the authors developed a 10-question assessment tool for reviewing AI products with an emphasis on their validation and result dissemination. The assessment tool was applied to commercial and open-source algorithms used for diagnosis to extract evidence on the clinical utility of the tools. Results There is limited technical information on methodologies for FDA-approved algorithms compared with open-source products, likely because of intellectual property concerns. Furthermore, FDA-approved products use much smaller data sets compared with open-source AI tools, because the terms of use of public data sets are limited to academic and noncommercial entities, which precludes their use in commercial products. Conclusions Overall, this study reveals a broad spectrum of maturity and clinical use of AI products, but a large gap exists in exploring the actual performance of AI tools in clinical practice.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Purpose Despite tremendous gains from deep learning and the promise of artificial intelligence (AI) in medicine to improve diagnosis and save costs, there exists a large translational gap to implement and use AI products in real-world clinical situations. Adoption of standards such as Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis, Consolidated Standards of Reporting Trials, and the Checklist for Artificial Intelligence in Medical Imaging is increasing to improve the peer-review process and reporting of AI tools. However, no such standards exist for product-level review. Methods A review of clinical trials showed a paucity of evidence for radiology AI products; thus, the authors developed a 10-question assessment tool for reviewing AI products with an emphasis on their validation and result dissemination. The assessment tool was applied to commercial and open-source algorithms used for diagnosis to extract evidence on the clinical utility of the tools. Results There is limited technical information on methodologies for FDA-approved algorithms compared with open-source products, likely because of intellectual property concerns. Furthermore, FDA-approved products use much smaller data sets compared with open-source AI tools, because the terms of use of public data sets are limited to academic and noncommercial entities, which precludes their use in commercial products. Conclusions Overall, this study reveals a broad spectrum of maturity and clinical use of AI products, but a large gap exists in exploring the actual performance of AI tools in clinical practice. |
Bucher, Sherri; Hoilett, Orlando; Bluhm, Nicholas; Walters, Benjamin; Pickering, Alyson; Purkayastha, Saptarshi; Linnes, Jacqueline C; Esamai, Fabian; Ummel, Jason; Ekhaguere, Osayame Wireless vital signs monitoring of opioid-exposed newborns during skin-to-skin care: Biomedical device innovation Presentation 28.10.2020. @misc{bucher2020wireless, title = {Wireless vital signs monitoring of opioid-exposed newborns during skin-to-skin care: Biomedical device innovation}, author = {Sherri Bucher and Orlando Hoilett and Nicholas Bluhm and Benjamin Walters and Alyson Pickering and Saptarshi Purkayastha and Jacqueline C Linnes and Fabian Esamai and Jason Ummel and Osayame Ekhaguere}, url = {https://apha.confex.com/apha/2020/meetingapp.cgi/Paper/477733}, year = {2020}, date = {2020-10-28}, booktitle = {APHA's 2020 VIRTUAL Annual Meeting and Expo (Oct. 24-28)}, publisher = {American Public Health Association}, abstract = {Background/Significance: Indiana has one of the highest rates of infant mortality in the United States. Premature birth, low birthweight, and in utero exposure to drugs of abuse are leading causes of neonatal complications. In 2016, 22% of umbilical cord blood samples from Indiana newborns tested positive for exposure to opiates. Health care providers are increasingly utilizing non-pharmacological strategies to manage the symptoms of opioid-exposed babies with neonatal abstinence syndrome (NAS). NAS babies require frequent vital signs monitoring, which can be a barrier to prolonged skin-to-skin care (STS). Methods: Our multidisciplinary, cross-institutional team utilized human-centered and participatory design, agile development, qualitative (focus group discussions; key informant interviews), and quantitative assessments to design, develop, build, and evaluate an integrated biomedical device/digital health solution. Results: Our 3-part, bundled innovation includes: (1) Built prototype of a wearable biomedical device with two integrated components: a carrier (worn by an adult caregiver) and a “pouch” (worn by the infant); (2) Wireless sensor technology which automatically, continuously, and accurately monitors key infant vital signs including body temperature, breathing, and heart rate, across three device use modes, including during STS care among adult caregiver-newborn dyads; (3) Android app which collects and displays device and infant vital signs monitoring information, and provides a platform for digitized educational resources. Feasibility assessments indicate broad acceptability of the device and app among health care providers, parents, and family stakeholders. Engineering verification has confirmed that our wireless sensor technology for measuring temperature, heart and respiratory rate during STS compares to the gold standard (impedance pneumography). Conclusion: To facilitate non-pharmacological management of opioid-exposed babies, we have developed a prototype of a wearable biomedical device with built-in sensor technology for continuous wireless vital signs monitoring. Infant vital signs information is collected, and displayed, on an Android app. This innovative device potentially equips health care providers with additional tools to support non-pharmacological management of opioid-exposed babies.}, keywords = {}, pubstate = {published}, tppubtype = {presentation} } Background/Significance: Indiana has one of the highest rates of infant mortality in the United States. Premature birth, low birthweight, and in utero exposure to drugs of abuse are leading causes of neonatal complications. In 2016, 22% of umbilical cord blood samples from Indiana newborns tested positive for exposure to opiates. Health care providers are increasingly utilizing non-pharmacological strategies to manage the symptoms of opioid-exposed babies with neonatal abstinence syndrome (NAS). NAS babies require frequent vital signs monitoring, which can be a barrier to prolonged skin-to-skin care (STS). Methods: Our multidisciplinary, cross-institutional team utilized human-centered and participatory design, agile development, qualitative (focus group discussions; key informant interviews), and quantitative assessments to design, develop, build, and evaluate an integrated biomedical device/digital health solution. Results: Our 3-part, bundled innovation includes: (1) Built prototype of a wearable biomedical device with two integrated components: a carrier (worn by an adult caregiver) and a “pouch” (worn by the infant); (2) Wireless sensor technology which automatically, continuously, and accurately monitors key infant vital signs including body temperature, breathing, and heart rate, across three device use modes, including during STS care among adult caregiver-newborn dyads; (3) Android app which collects and displays device and infant vital signs monitoring information, and provides a platform for digitized educational resources. Feasibility assessments indicate broad acceptability of the device and app among health care providers, parents, and family stakeholders. Engineering verification has confirmed that our wireless sensor technology for measuring temperature, heart and respiratory rate during STS compares to the gold standard (impedance pneumography). Conclusion: To facilitate non-pharmacological management of opioid-exposed babies, we have developed a prototype of a wearable biomedical device with built-in sensor technology for continuous wireless vital signs monitoring. Infant vital signs information is collected, and displayed, on an Android app. This innovative device potentially equips health care providers with additional tools to support non-pharmacological management of opioid-exposed babies. |
Goyal, Shreya; Purkayastha, Saptarshi; Phillips, Tyler; Quick, Rob; Britt, Alexis Enabling Secure and Effective Biomedical Data Sharing through Cyberinfrastructure Gateways Conference Gateways 2020, 2020. @conference{goyal2020enabling, title = {Enabling Secure and Effective Biomedical Data Sharing through Cyberinfrastructure Gateways}, author = {Shreya Goyal and Saptarshi Purkayastha and Tyler Phillips and Rob Quick and Alexis Britt}, doi = {10.17605/OSF.IO/6Y8WG}, year = {2020}, date = {2020-10-19}, booktitle = {Gateways 2020}, journal = {arXiv preprint arXiv:2012.12835}, abstract = {Dynaswap project reports on developing a coherently integrated and trustworthy holistic secure workflow protection architecture for cyberinfrastructures which can be used on virtual machines deployed through cyberinfrastructure (CI) services such as JetStream. This service creates a user-friendly cloud environment designed to give researchers access to interactive computing and data analysis resources on demand. The Dynaswap cybersecurity architecture supports roles, role hierarchies, and data hierarchies, as well as dynamic changes of roles and hierarchical relations within the scientific infrastructure. Dynaswap combines existing cutting-edge security frameworks (including an Authentication Authorization-Accounting framework, Multi-Factor Authentication, Secure Digital Provenance, and Blockchain) with advanced security tools (e.g., Biometric-Capsule, Cryptography-based Hierarchical Access Control, and Dual-level Key Management). The CI is being validated in life-science research environments and in the education settings of Health Informatics. }, keywords = {}, pubstate = {published}, tppubtype = {conference} } Dynaswap project reports on developing a coherently integrated and trustworthy holistic secure workflow protection architecture for cyberinfrastructures which can be used on virtual machines deployed through cyberinfrastructure (CI) services such as JetStream. This service creates a user-friendly cloud environment designed to give researchers access to interactive computing and data analysis resources on demand. The Dynaswap cybersecurity architecture supports roles, role hierarchies, and data hierarchies, as well as dynamic changes of roles and hierarchical relations within the scientific infrastructure. Dynaswap combines existing cutting-edge security frameworks (including an Authentication Authorization-Accounting framework, Multi-Factor Authentication, Secure Digital Provenance, and Blockchain) with advanced security tools (e.g., Biometric-Capsule, Cryptography-based Hierarchical Access Control, and Dual-level Key Management). The CI is being validated in life-science research environments and in the education settings of Health Informatics. |
Bucher, Sherri L; Cardellichio, Peter; Muinga, Naomi; Patterson, Jackie K; Thukral, Anu; Deorari, Ashok K; Data, Santorino; Umoren, Rachel; Purkayastha, Saptarshi Digital health innovations, tools, and resources to support Helping Babies Survive programs Journal Article Pediatrics, 146 (Supplement 2), pp. S165-S182, 2020, ISSN: 0031-4005. @article{bucher2020digital, title = {Digital health innovations, tools, and resources to support Helping Babies Survive programs}, author = {Sherri L. Bucher and Peter Cardellichio and Naomi Muinga and Jackie K. Patterson and Anu Thukral and Ashok K. Deorari and Santorino Data and Rachel Umoren and Saptarshi Purkayastha}, url = {https://pediatrics.aappublications.org/content/146/Supplement_2/S165}, doi = {10.1542/peds.2020-016915I}, issn = {0031-4005}, year = {2020}, date = {2020-10-01}, journal = {Pediatrics}, volume = {146}, number = {Supplement 2}, pages = {S165-S182}, abstract = {The Helping Babies Survive (HBS) initiative features a suite of evidence-based curricula and simulation-based training programs designed to provide health workers in low- and middle-income countries (LMICs) with the knowledge, skills, and competencies to prevent, recognize, and manage leading causes of newborn morbidity and mortality. Global scale-up of HBS initiatives has been rapid. As HBS initiatives rolled out across LMIC settings, numerous bottlenecks, gaps, and barriers to the effective, consistent dissemination and implementation of the programs, across both the pre- and in-service continuums, emerged. Within the first decade of expansive scale-up of HBS programs, mobile phone ownership and access to cellular networks have also concomitantly surged in LMICs. In this article, we describe a number of HBS digital health innovations and resources that have been developed from 2010 to 2020 to support education and training, data collection for monitoring and evaluation, clinical decision support, and quality improvement. Helping Babies Survive partners and stakeholders can potentially integrate the described digital tools with HBS dissemination and implementation efforts in a myriad of ways to support low-dose high-frequency skills practice, in-person refresher courses, continuing medical and nursing education, on-the-job training, or peer-to-peer learning, and strengthen data collection for key newborn care and quality improvement indicators and outcomes. Thoughtful integration of purpose-built digital health tools, innovations, and resources may assist HBS practitioners to more effectively disseminate and implement newborn care programs in LMICs, and facilitate progress toward the achievement of Sustainable Development Goal health goals, targets, and objectives.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The Helping Babies Survive (HBS) initiative features a suite of evidence-based curricula and simulation-based training programs designed to provide health workers in low- and middle-income countries (LMICs) with the knowledge, skills, and competencies to prevent, recognize, and manage leading causes of newborn morbidity and mortality. Global scale-up of HBS initiatives has been rapid. As HBS initiatives rolled out across LMIC settings, numerous bottlenecks, gaps, and barriers to the effective, consistent dissemination and implementation of the programs, across both the pre- and in-service continuums, emerged. Within the first decade of expansive scale-up of HBS programs, mobile phone ownership and access to cellular networks have also concomitantly surged in LMICs. In this article, we describe a number of HBS digital health innovations and resources that have been developed from 2010 to 2020 to support education and training, data collection for monitoring and evaluation, clinical decision support, and quality improvement. Helping Babies Survive partners and stakeholders can potentially integrate the described digital tools with HBS dissemination and implementation efforts in a myriad of ways to support low-dose high-frequency skills practice, in-person refresher courses, continuing medical and nursing education, on-the-job training, or peer-to-peer learning, and strengthen data collection for key newborn care and quality improvement indicators and outcomes. Thoughtful integration of purpose-built digital health tools, innovations, and resources may assist HBS practitioners to more effectively disseminate and implement newborn care programs in LMICs, and facilitate progress toward the achievement of Sustainable Development Goal health goals, targets, and objectives. |
Bhimireddy, Ananth; Sinha, Priyanshu; Oluwalade, Bolu; Gichoya, Judy Wawira; Purkayastha, Saptarshi Blood Glucose Level Prediction as Time-Series Modeling using Sequence-to-Sequence Neural Networks Inproceedings Bach, Kerstin; Bunescu, Razvan; Marling, Cindy; Wiratunga, Nirmalie (Ed.): Proceedings of the 5th International Workshop on Knowledge Discovery in Healthcare Data co-located with 24th European Conference on Artificial Intelligence (ECAI 2020), pp. 125-130, CEUR-WS Workshop Proceedings, 2020. @inproceedings{bhimireddy2020blood, title = {Blood Glucose Level Prediction as Time-Series Modeling using Sequence-to-Sequence Neural Networks}, author = {Ananth Bhimireddy and Priyanshu Sinha and Bolu Oluwalade and Judy Wawira Gichoya and Saptarshi Purkayastha}, editor = {Kerstin Bach and Razvan Bunescu and Cindy Marling and Nirmalie Wiratunga}, url = {http://ceur-ws.org/Vol-2675/paper22.pdf}, year = {2020}, date = {2020-09-17}, booktitle = {Proceedings of the 5th International Workshop on Knowledge Discovery in Healthcare Data co-located with 24th European Conference on Artificial Intelligence (ECAI 2020)}, volume = {Vol-2675}, pages = {125-130}, publisher = {CEUR-WS Workshop Proceedings}, abstract = {The management of blood glucose levels is critical in the care of Type 1 diabetes subjects. In extremes, high or low levels of blood glucose are fatal. To avoid such adverse events, there is the development and adoption of wearable technologies that continuously monitor blood glucose and administer insulin. This technology allows subjects to easily track their blood glucose levels with early intervention, preventing the need for hospital visits. The data collected from these sensors is an excellent candidate for the application of machine learning algorithms to learn patterns and predict future values of blood glucose levels. In this study, we developed artificial neural network algorithms based on the OhioT1DM training dataset that contains data on 12 subjects. The dataset contains features such as subject identifiers, continuous glucose monitoring data obtained in 5 minutes intervals, insulin infusion rate, etc. We developed individual models, including LSTM, BiLSTM, Convolutional LSTMs, TCN, and sequence-to-sequence models. We also developed transfer learning models based on the most important features of the data, as identified by a gradient boosting algorithm. These models were evaluated on the OhioT1DM test dataset that contains 6 unique subjects data. The model with the lowest RMSE values for the 30- and 60-minutes was selected as the best performing model. Our result shows that sequence-to-sequence BiLSTM performed better than the other models. This work demonstrates the potential of artificial neural networks algorithms in the management of Type 1 diabetes.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The management of blood glucose levels is critical in the care of Type 1 diabetes subjects. In extremes, high or low levels of blood glucose are fatal. To avoid such adverse events, there is the development and adoption of wearable technologies that continuously monitor blood glucose and administer insulin. This technology allows subjects to easily track their blood glucose levels with early intervention, preventing the need for hospital visits. The data collected from these sensors is an excellent candidate for the application of machine learning algorithms to learn patterns and predict future values of blood glucose levels. In this study, we developed artificial neural network algorithms based on the OhioT1DM training dataset that contains data on 12 subjects. The dataset contains features such as subject identifiers, continuous glucose monitoring data obtained in 5 minutes intervals, insulin infusion rate, etc. We developed individual models, including LSTM, BiLSTM, Convolutional LSTMs, TCN, and sequence-to-sequence models. We also developed transfer learning models based on the most important features of the data, as identified by a gradient boosting algorithm. These models were evaluated on the OhioT1DM test dataset that contains 6 unique subjects data. The model with the lowest RMSE values for the 30- and 60-minutes was selected as the best performing model. Our result shows that sequence-to-sequence BiLSTM performed better than the other models. This work demonstrates the potential of artificial neural networks algorithms in the management of Type 1 diabetes. |
Rajapuri, Anushri S; Ravindran, Radhika; Horan, Kevin; Bucher, Sherri; Purkayastha, Saptarshi Essential Care for Every Baby: Neonatal Clinical Decision Support Tool Conference International Conference on Applied Human Factors and Ergonomics, 1205 , 2020, ISBN: 978-3-030-50837-1. @conference{rajapuri2020essential, title = {Essential Care for Every Baby: Neonatal Clinical Decision Support Tool}, author = {Anushri S Rajapuri and Radhika Ravindran and Kevin Horan and Sherri Bucher and Saptarshi Purkayastha}, editor = {Kalra J., Lightner N}, doi = {https://doi.org/10.1007/978-3-030-50838-8_26}, isbn = {978-3-030-50837-1}, year = {2020}, date = {2020-07-16}, booktitle = {International Conference on Applied Human Factors and Ergonomics}, volume = {1205}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
Balthazar, Patricia; Tajmir, Shahein H; Ortiz, Daniel A; Herse, Catherine C; Shea, Lindsey AG; Seals, Kevin F; Cohen-Addad, Dan; Purkayastha, Saptarshi; Gichoya, Judy W The Artificial Intelligence Journal Club (# RADAIJC): A Multi-Institutional Resident-Driven Web-Based Educational Initiative Journal Article Academic radiology, 27 (1), pp. 136–139, 2020. @article{balthazar2020artificial, title = {The Artificial Intelligence Journal Club (# RADAIJC): A Multi-Institutional Resident-Driven Web-Based Educational Initiative}, author = {Patricia Balthazar and Shahein H Tajmir and Daniel A Ortiz and Catherine C Herse and Lindsey AG Shea and Kevin F Seals and Dan Cohen-Addad and Saptarshi Purkayastha and Judy W Gichoya}, year = {2020}, date = {2020-01-01}, journal = {Academic radiology}, volume = {27}, number = {1}, pages = {136--139}, publisher = {Elsevier}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Phillips, Tyler; Yu, Xiaoyuan; Haakenson, Brandon; Goyal, Shreya; Zou, Xukai; Purkayastha, Saptarshi; Wu, Huanmei AuthN-AuthZ: Integrated, User-Friendly and Privacy-Preserving Authentication and Authorization Inproceedings 2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), pp. 189–198, IEEE 2020. @inproceedings{phillips2020authn, title = {AuthN-AuthZ: Integrated, User-Friendly and Privacy-Preserving Authentication and Authorization}, author = {Tyler Phillips and Xiaoyuan Yu and Brandon Haakenson and Shreya Goyal and Xukai Zou and Saptarshi Purkayastha and Huanmei Wu}, year = {2020}, date = {2020-01-01}, booktitle = {2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)}, pages = {189--198}, organization = {IEEE}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Purkayastha, Saptarshi; Addepally, Siva Abhishek; Bucher, Sherri Engagement and Usability of a Cognitive Behavioral Therapy Mobile App Compared With Web-Based Cognitive Behavioral Therapy Among College Students: Randomized Heuristic Trial Journal Article JMIR Human Factors, 7 (1), pp. e14146, 2020. @article{purkayastha2020engagement, title = {Engagement and Usability of a Cognitive Behavioral Therapy Mobile App Compared With Web-Based Cognitive Behavioral Therapy Among College Students: Randomized Heuristic Trial}, author = {Saptarshi Purkayastha and Siva Abhishek Addepally and Sherri Bucher}, year = {2020}, date = {2020-01-01}, journal = {JMIR Human Factors}, volume = {7}, number = {1}, pages = {e14146}, publisher = {JMIR Publications Inc., Toronto, Canada}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Singh, AK; Guntu, Mounika; Bhimireddy, Ananth Reddy; Gichoya, Judy W; Purkayastha, Saptarshi Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes Journal Article arXiv preprint arXiv:2003.07507, 2020. @article{singh2020multi, title = {Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes}, author = {AK Singh and Mounika Guntu and Ananth Reddy Bhimireddy and Judy W Gichoya and Saptarshi Purkayastha}, year = {2020}, date = {2020-01-01}, journal = {arXiv preprint arXiv:2003.07507}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Kathiravelu, Pradeeban; Sharma, Ashish; Purkayastha, Saptarshi; Sinha, Priyanshu; Cadrin-Chenevert, Alexandre; Banerjee, Imon; Gichoya, Judy Wawira Developing and Deploying Machine Learning Pipelines against Real-Time Image Streams from the PACS Journal Article arXiv preprint arXiv:2004.07965, 2020. @article{kathiravelu2020developing, title = {Developing and Deploying Machine Learning Pipelines against Real-Time Image Streams from the PACS}, author = {Pradeeban Kathiravelu and Ashish Sharma and Saptarshi Purkayastha and Priyanshu Sinha and Alexandre Cadrin-Chenevert and Imon Banerjee and Judy Wawira Gichoya}, year = {2020}, date = {2020-01-01}, journal = {arXiv preprint arXiv:2004.07965}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Mathur, Varoon; Purkayashtha, Saptarshi; Gichoya, Judy Wawira Artificial Intelligence for Global Health: Learning From a Decade of Digital Transformation in Health Care Journal Article arXiv preprint arXiv:2005.12378, 2020. @article{mathur2020artificial, title = {Artificial Intelligence for Global Health: Learning From a Decade of Digital Transformation in Health Care}, author = {Varoon Mathur and Saptarshi Purkayashtha and Judy Wawira Gichoya}, year = {2020}, date = {2020-01-01}, journal = {arXiv preprint arXiv:2005.12378}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Umoren, Rachel A; Bucher, Sherri; Purkayastha, Saptarshi; Ezeaka, Chinyere; Esamai, Fabian; Mairami, Amsa; Asangansi, Ime; Bresnahan, Brian; Paton, Chris eHBB/mHBS-DHIS2: Mobile Virtual Reality Provider Training in Helping Babies Breathetextregistered Miscellaneous 2020. @misc{umoren2020ehbb, title = {eHBB/mHBS-DHIS2: Mobile Virtual Reality Provider Training in Helping Babies Breathetextregistered}, author = {Rachel A Umoren and Sherri Bucher and Saptarshi Purkayastha and Chinyere Ezeaka and Fabian Esamai and Amsa Mairami and Ime Asangansi and Brian Bresnahan and Chris Paton}, year = {2020}, date = {2020-01-01}, publisher = {American Academy of Pediatrics}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
Umoren, Rachel A; Ezeaka, Chinyere; Esamai, Fabian; Kshatriya, Bhavani Agnikula; Avanigadda, Prem; Clopp, Bailey; Ezenwa, Beatrice; Fajolu, Iretiola; Feltner, John; Makokha, Felicitas; others, Pre-Training Cognitive and Psychomotor Gaps in Healthcare Worker Neonatal Resuscitation Skills for Helping Babies Breathe--A Report from the eHBB/mHBS Study Miscellaneous 2020. @misc{umoren2020pre, title = {Pre-Training Cognitive and Psychomotor Gaps in Healthcare Worker Neonatal Resuscitation Skills for Helping Babies Breathe--A Report from the eHBB/mHBS Study}, author = {Rachel A Umoren and Chinyere Ezeaka and Fabian Esamai and Bhavani Agnikula Kshatriya and Prem Avanigadda and Bailey Clopp and Beatrice Ezenwa and Iretiola Fajolu and John Feltner and Felicitas Makokha and others}, year = {2020}, date = {2020-01-01}, publisher = {American Academy of Pediatrics}, keywords = {}, pubstate = {published}, tppubtype = {misc} } |
Banerjee, Imon; Sinha, Priyanshu; Purkayastha, Saptarshi; Mashhaditafreshi, Nazanin; Tariq, Amara; Jeong, Jiwoong; Trivedi, Hari; Gichoya, Judy W Was there COVID-19 back in 2012? Challenge for AI in Diagnosis with Similar Indications Journal Article arXiv preprint arXiv:2006.13262, 2020. @article{banerjee2020there, title = {Was there COVID-19 back in 2012? Challenge for AI in Diagnosis with Similar Indications}, author = {Imon Banerjee and Priyanshu Sinha and Saptarshi Purkayastha and Nazanin Mashhaditafreshi and Amara Tariq and Jiwoong Jeong and Hari Trivedi and Judy W Gichoya}, year = {2020}, date = {2020-01-01}, journal = {arXiv preprint arXiv:2006.13262}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2019 |
Nuthakki, Siddhartha; Bucher, Sherri; Purkayastha, Saptarshi The Development and Usability Testing of a Decision Support Mobile App for the Essential Care for Every Baby (ECEB) Program Conference International Conference on Human-Computer Interaction Springer, Cham, 2019. @conference{Nuthakki2019, title = {The Development and Usability Testing of a Decision Support Mobile App for the Essential Care for Every Baby (ECEB) Program}, author = {Siddhartha Nuthakki and Sherri Bucher and Saptarshi Purkayastha}, year = {2019}, date = {2019-07-26}, pages = {259-263}, publisher = {Springer, Cham}, organization = {International Conference on Human-Computer Interaction}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
Purkayastha, Saptarshi; Buddi, Surendra Babu; Nuthakki, Siddhartha; Yadav, Bhawana; Gichoya, Judy W Evaluating the Implementation of Deep Learning in LibreHealth Radiology on Chest X-Rays Conference Computer Vision Conference, Springer, Cham, 2019. @conference{Purkayastha2019, title = {Evaluating the Implementation of Deep Learning in LibreHealth Radiology on Chest X-Rays}, author = {Saptarshi Purkayastha and Surendra Babu Buddi and Siddhartha Nuthakki and Bhawana Yadav and Judy W Gichoya}, url = {https://scholarworks.iupui.edu/bitstream/handle/1805/18297/paper_258.pdf}, year = {2019}, date = {2019-04-25}, booktitle = {Computer Vision Conference}, pages = {648-657}, publisher = {Springer, Cham}, abstract = {Respiratory diseases are the dominant cause of deaths worldwide. In the US, the number of deaths due to chronic lung infections (mostly pneumonia and tuberculosis), lung cancer and chronic obstructive pulmonary disease has increased. The timely and accurate diagnosis of the disease is highly imperative to diminish the deaths. A chest X-ray is a vital diagnostic tool used for diagnosing lung diseases. Delay in X-Ray diagnosis is run-of-the-mill milieu and the reasons for the impediment are mostly because the X-ray reports are arduous to interpret, due to the complex visual contents of radiographs containing superimposed anatomical structures. A shortage of trained radiologists is another cause of increased workload and thus delay. We integrated CheXNet, a neural network algorithm into the LibreHealth Radiology Information System, which allows physicians to upload Chest X-rays and identify diagnosis probabilities. The uploaded images are evaluated from labels for 14 thoracic diseases. The turnaround time for each evaluation is about 30 seconds, which does not affect clinical workflow. A Python Flask application hosted web service is used to upload radiographs into a GPU server containing the algorithm. Thus, the use of this system is not limited to clients having their GPU server, but instead, we provide a web service. To evaluate the model, we randomly split the dataset into training (70%), validation (10%) and test (20%) sets. With over 86% accuracy and turnaround time under 30 seconds, the application demonstrates the feasibility of a web service for machine learning-based diagnosis of 14-lung pathologies from Chest X-rays.}, keywords = {}, pubstate = {published}, tppubtype = {conference} } Respiratory diseases are the dominant cause of deaths worldwide. In the US, the number of deaths due to chronic lung infections (mostly pneumonia and tuberculosis), lung cancer and chronic obstructive pulmonary disease has increased. The timely and accurate diagnosis of the disease is highly imperative to diminish the deaths. A chest X-ray is a vital diagnostic tool used for diagnosing lung diseases. Delay in X-Ray diagnosis is run-of-the-mill milieu and the reasons for the impediment are mostly because the X-ray reports are arduous to interpret, due to the complex visual contents of radiographs containing superimposed anatomical structures. A shortage of trained radiologists is another cause of increased workload and thus delay. We integrated CheXNet, a neural network algorithm into the LibreHealth Radiology Information System, which allows physicians to upload Chest X-rays and identify diagnosis probabilities. The uploaded images are evaluated from labels for 14 thoracic diseases. The turnaround time for each evaluation is about 30 seconds, which does not affect clinical workflow. A Python Flask application hosted web service is used to upload radiographs into a GPU server containing the algorithm. Thus, the use of this system is not limited to clients having their GPU server, but instead, we provide a web service. To evaluate the model, we randomly split the dataset into training (70%), validation (10%) and test (20%) sets. With over 86% accuracy and turnaround time under 30 seconds, the application demonstrates the feasibility of a web service for machine learning-based diagnosis of 14-lung pathologies from Chest X-rays. |
Purkayastha, Saptarshi; Allam, Roshini; Maity, Pallavi; Gichoya, Judy W Comparison of Open-Source Electronic Health Record Systems Based on Functional and User Performance Criteria Journal Article Healthcare informatics research, 25 (2), pp. 89-98, 2019. @article{Purkayastha2019b, title = {Comparison of Open-Source Electronic Health Record Systems Based on Functional and User Performance Criteria}, author = {Saptarshi Purkayastha and Roshini Allam and Pallavi Maity and Judy W Gichoya}, url = {https://synapse.koreamed.org/DOIx.php?id=10.4258/hir.2019.25.2.89}, doi = {doi.org/10.4258/hir.2019.25.2.89}, year = {2019}, date = {2019-04-01}, journal = {Healthcare informatics research}, volume = {25}, number = {2}, pages = {89-98}, abstract = {Objectives: Open-source Electronic Health Record (EHR) systems have gained importance. The main aim of our research is to guide organizational choice by comparing the features, functionality, and user-facing system performance of the five most popular open-source EHR systems. Methods: We performed a qualitative content analysis with a directed approach on recently published literature (2012–2017) to develop an integrated set of criteria to compare the EHR systems. The functional criteria are an integration of the literature, meaningful use criteria, and the Institute of Medicine's functional requirements of EHR, whereas the user-facing system performance is based on the time required to perform basic tasks within the EHR system. Results: Based on the Alexa web ranking and Google Trends, the five most popular EHR systems at the time of our study were OSHERA VistA, GNU Health, the Open Medical Record System (OpenMRS), Open Electronic Medical Record (OpenEMR), and OpenEHR. We also found the trends in popularity of the EHR systems and the locations where they were more popular than others. OpenEMR met all the 32 functional criteria, OSHERA VistA met 28, OpenMRS met 12 fully and 11 partially, OpenEHR-based EHR met 10 fully and 3 partially, and GNU Health met the least with only 10 criteria fully and 2 partially. Conclusions: Based on our functional criteria, OpenEMR is the most promising EHR system, closely followed by VistA. With regard to user-facing system performance, OpenMRS has superior performance in comparison to OpenEMR.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Objectives: Open-source Electronic Health Record (EHR) systems have gained importance. The main aim of our research is to guide organizational choice by comparing the features, functionality, and user-facing system performance of the five most popular open-source EHR systems. Methods: We performed a qualitative content analysis with a directed approach on recently published literature (2012–2017) to develop an integrated set of criteria to compare the EHR systems. The functional criteria are an integration of the literature, meaningful use criteria, and the Institute of Medicine's functional requirements of EHR, whereas the user-facing system performance is based on the time required to perform basic tasks within the EHR system. Results: Based on the Alexa web ranking and Google Trends, the five most popular EHR systems at the time of our study were OSHERA VistA, GNU Health, the Open Medical Record System (OpenMRS), Open Electronic Medical Record (OpenEMR), and OpenEHR. We also found the trends in popularity of the EHR systems and the locations where they were more popular than others. OpenEMR met all the 32 functional criteria, OSHERA VistA met 28, OpenMRS met 12 fully and 11 partially, OpenEHR-based EHR met 10 fully and 3 partially, and GNU Health met the least with only 10 criteria fully and 2 partially. Conclusions: Based on our functional criteria, OpenEMR is the most promising EHR system, closely followed by VistA. With regard to user-facing system performance, OpenMRS has superior performance in comparison to OpenEMR. |
Kasthurirathne, Suranga N; Biondich, Paul G; Grannis, Shaun J; Purkayastha, Saptarshi; Vest, Joshua R; Jones, Josette F Journal of medical Internet research, 21 (7), pp. e13809, 2019. @article{Kasthurirathne2019, title = {Identification of Patients in Need of Advanced Care for Depression Using Data Extracted From a Statewide Health Information Exchange: A Machine Learning Approach}, author = {Suranga N Kasthurirathne and Paul G Biondich and Shaun J Grannis and Saptarshi Purkayastha and Joshua R Vest and Josette F Jones}, url = {https://www.jmir.org/2019/7/e13809/}, doi = {doi:10.2196/13809}, year = {2019}, date = {2019-01-02}, journal = {Journal of medical Internet research}, volume = {21}, number = {7}, pages = {e13809}, publisher = {JMIR Publications Inc., Toronto, Canada}, abstract = {Background: As the most commonly occurring form of mental illness worldwide, depression poses significant health and economic burdens to both the individual and community. Different types of depression pose different levels of risk. Individuals who suffer from mild forms of depression may recover without any assistance or be effectively managed by primary care or family practitioners. However, other forms of depression are far more severe and require advanced care by certified mental health providers. However, identifying cases of depression that require advanced care may be challenging to primary care providers and health care team members whose skill sets run broad rather than deep. Objective: This study aimed to leverage a comprehensive range of patient-level diagnostic, behavioral, and demographic data, as well as past visit history data from a statewide health information exchange to build decision models capable of predicting the need of advanced care for depression across patients presenting at Eskenazi Health, the public safety net health system for Marion County, Indianapolis, Indiana. Methods: Patient-level diagnostic, behavioral, demographic, and past visit history data extracted from structured datasets were merged with outcome variables extracted from unstructured free-text datasets and were used to train random forest decision models that predicted the need of advanced care for depression across (1) the overall patient population and (2) various subsets of patients at higher risk for depression-related adverse events; patients with a past diagnosis of depression; patients with a Charlson comorbidity index of ≥1; patients with a Charlson comorbidity index of ≥2; and all unique patients identified across the 3 above-mentioned high-risk groups. Results: The overall patient population consisted of 84,317 adult (aged ≥18 years) patients. A total of 6992 (8.29%) of these patients were in need of advanced care for depression. Decision models for high-risk patient groups yielded area under the curve (AUC) scores between 86.31% and 94.43%. The decision model for the overall patient population yielded a comparatively lower AUC score of 78.87%. The variance of optimal sensitivity and specificity for all decision models, as identified using Youden J Index, is as follows: sensitivity=68.79% to 83.91% and specificity=76.03% to 92.18%. Conclusions: This study demonstrates the ability to automate screening for patients in need of advanced care for depression across (1) an overall patient population or (2) various high-risk patient groups using structured datasets covering acute and chronic conditions, patient demographics, behaviors, and past visit history. Furthermore, these results show considerable potential to enable preventative care and can be easily integrated into existing clinical workflows to improve access to wraparound health care services.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: As the most commonly occurring form of mental illness worldwide, depression poses significant health and economic burdens to both the individual and community. Different types of depression pose different levels of risk. Individuals who suffer from mild forms of depression may recover without any assistance or be effectively managed by primary care or family practitioners. However, other forms of depression are far more severe and require advanced care by certified mental health providers. However, identifying cases of depression that require advanced care may be challenging to primary care providers and health care team members whose skill sets run broad rather than deep. Objective: This study aimed to leverage a comprehensive range of patient-level diagnostic, behavioral, and demographic data, as well as past visit history data from a statewide health information exchange to build decision models capable of predicting the need of advanced care for depression across patients presenting at Eskenazi Health, the public safety net health system for Marion County, Indianapolis, Indiana. Methods: Patient-level diagnostic, behavioral, demographic, and past visit history data extracted from structured datasets were merged with outcome variables extracted from unstructured free-text datasets and were used to train random forest decision models that predicted the need of advanced care for depression across (1) the overall patient population and (2) various subsets of patients at higher risk for depression-related adverse events; patients with a past diagnosis of depression; patients with a Charlson comorbidity index of ≥1; patients with a Charlson comorbidity index of ≥2; and all unique patients identified across the 3 above-mentioned high-risk groups. Results: The overall patient population consisted of 84,317 adult (aged ≥18 years) patients. A total of 6992 (8.29%) of these patients were in need of advanced care for depression. Decision models for high-risk patient groups yielded area under the curve (AUC) scores between 86.31% and 94.43%. The decision model for the overall patient population yielded a comparatively lower AUC score of 78.87%. The variance of optimal sensitivity and specificity for all decision models, as identified using Youden J Index, is as follows: sensitivity=68.79% to 83.91% and specificity=76.03% to 92.18%. Conclusions: This study demonstrates the ability to automate screening for patients in need of advanced care for depression across (1) an overall patient population or (2) various high-risk patient groups using structured datasets covering acute and chronic conditions, patient demographics, behaviors, and past visit history. Furthermore, these results show considerable potential to enable preventative care and can be easily integrated into existing clinical workflows to improve access to wraparound health care services. |
Yandrapalli, Bhanu Teja; Jones, Josette; Purkayastha, Saptarshi Development and Implementation of a Dashboard for Diabetes Care Management in OpenMRS Journal Article arXiv preprint arXiv:1910.11437, 2019. @article{teja2019development, title = {Development and Implementation of a Dashboard for Diabetes Care Management in OpenMRS}, author = {Bhanu Teja Yandrapalli and Josette Jones and Saptarshi Purkayastha}, year = {2019}, date = {2019-01-01}, journal = {arXiv preprint arXiv:1910.11437}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Purkayastha, Saptarshi; Guntu, Mounika; Ravindran, Radhika; Surapaneni, Asha Kiranmayee Learning Gains of Process Oriented Guided Inquiry Learning in an Online Course Setting Inproceedings European Conference on e-Learning, pp. 495–XII, Academic Conferences International Limited 2019. @inproceedings{purkayastha2019learning, title = {Learning Gains of Process Oriented Guided Inquiry Learning in an Online Course Setting}, author = {Saptarshi Purkayastha and Mounika Guntu and Radhika Ravindran and Asha Kiranmayee Surapaneni}, year = {2019}, date = {2019-01-01}, booktitle = {European Conference on e-Learning}, pages = {495--XII}, organization = {Academic Conferences International Limited}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Nuthakki, Siddhartha; Neela, Sunil; Gichoya, Judy W; Purkayastha, Saptarshi Natural language processing of MIMIC-III clinical notes for identifying diagnosis and procedures with neural networks Journal Article arXiv preprint arXiv:1912.12397, 2019. @article{nuthakki2019natural, title = {Natural language processing of MIMIC-III clinical notes for identifying diagnosis and procedures with neural networks}, author = {Siddhartha Nuthakki and Sunil Neela and Judy W Gichoya and Saptarshi Purkayastha}, year = {2019}, date = {2019-01-01}, journal = {arXiv preprint arXiv:1912.12397}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Obidi, Joyce; Villa, Carlos Hipolito; Storch, Emily; Whitaker, Barbee I; Chada, Kinnera; Williams, Alan; Fowler, Stephanie; Schilling, Lisa; Kahn, Michael G; Edlavitch, Stanley A; others, Trends in RED Blood CELL Transfusions within the Biologics Effectiveness and Safety (BEST) Initiative Network, 2012-2018 Inproceedings 2019 Annual Meeting, AABB 2019. @inproceedings{obidi2019trends, title = {Trends in RED Blood CELL Transfusions within the Biologics Effectiveness and Safety (BEST) Initiative Network, 2012-2018}, author = {Joyce Obidi and Carlos Hipolito Villa and Emily Storch and Barbee I Whitaker and Kinnera Chada and Alan Williams and Stephanie Fowler and Lisa Schilling and Michael G Kahn and Stanley A Edlavitch and others}, year = {2019}, date = {2019-01-01}, booktitle = {2019 Annual Meeting}, organization = {AABB}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Purkayastha, Saptarshi; Surapaneni, Asha K; Maity, Pallavi; Rajapuri, Anushri S; Gichoya, Judy W Critical Components of Formative Assessment in Process-Oriented Guided Inquiry Learning for Online Labs Journal Article Electronic Journal of e-Learning, 17 (2), 2019. @article{Purkayastha2019c, title = {Critical Components of Formative Assessment in Process-Oriented Guided Inquiry Learning for Online Labs}, author = {Saptarshi Purkayastha and Asha K Surapaneni and Pallavi Maity and Anushri S Rajapuri and Judy W Gichoya}, url = {https://files.eric.ed.gov/fulltext/EJ1220140.pdf}, doi = {DOI: 10.34190/JEL.17.2.02}, year = {2019}, date = {2019-00-00}, journal = {Electronic Journal of e-Learning}, volume = {17}, number = {2}, abstract = {In the traditional lab setting, it is reasonably straightforward to monitor student learning and provide ongoing feedback. Such formative assessments can help students identify their strengths and weaknesses, and assist faculty to recognize where students are struggling and address problems immediately. But in an online virtual lab setting, formative assessment has challenges that go beyond space-time synchrony of online classroom. As we see increased enrollment in online courses, learning science needs to address the problem of formative assessment in online laboratory sessions. We developed a student team learning monitor (STLM module) in an electronic health record system to measure student engagement and actualize the social constructivist approach of Process Oriented Guided Inquiry Learning (POGIL). Using iterative Plan-Do-Study-Act cycles in two undergraduate courses over a period of two years, we identified critical components that are required for the online implementation of POGIL. We reviewed published research on POGIL classroom implementations for the last ten years and identified some common elements that affect learning gains. We present the critical components that are necessary for implementing POGIL in online lab settings, and refer to this as Cyber POGIL. Incorporating these critical components are required to determine when, how and the circumstances under which Cyber POGIL may be successfully implemented. We recommend that more online tools be developed for POGIL classrooms, which evolve from just providing synchronous communication to improved task monitoring and assistive feedback.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In the traditional lab setting, it is reasonably straightforward to monitor student learning and provide ongoing feedback. Such formative assessments can help students identify their strengths and weaknesses, and assist faculty to recognize where students are struggling and address problems immediately. But in an online virtual lab setting, formative assessment has challenges that go beyond space-time synchrony of online classroom. As we see increased enrollment in online courses, learning science needs to address the problem of formative assessment in online laboratory sessions. We developed a student team learning monitor (STLM module) in an electronic health record system to measure student engagement and actualize the social constructivist approach of Process Oriented Guided Inquiry Learning (POGIL). Using iterative Plan-Do-Study-Act cycles in two undergraduate courses over a period of two years, we identified critical components that are required for the online implementation of POGIL. We reviewed published research on POGIL classroom implementations for the last ten years and identified some common elements that affect learning gains. We present the critical components that are necessary for implementing POGIL in online lab settings, and refer to this as Cyber POGIL. Incorporating these critical components are required to determine when, how and the circumstances under which Cyber POGIL may be successfully implemented. We recommend that more online tools be developed for POGIL classrooms, which evolve from just providing synchronous communication to improved task monitoring and assistive feedback. |
Sinha, Priyanshu; Gichoya, Judy W; Purkayastha, Saptarshi Full training versus fine tuning for radiology images concept detection task for the Image Conference 2019, ISSN: 1613-0073. @conference{Sinha2019, title = {Full training versus fine tuning for radiology images concept detection task for the Image}, author = {Priyanshu Sinha and Judy W Gichoya and Saptarshi Purkayastha }, issn = {1613-0073}, year = {2019}, date = {2019-00-00}, journal = {CEUR Workshop Proceedings,(CEUR-WS. org)}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
2018 |
Saptarshi Purkayastha Asha Kiranmayee Surapaneni, Pallavi Maity Implementing Guided Inquiry Learning and Measuring Engagement Using an Electronic Health Record System in an Online Setting Conference European Conference on e-Learning, Academic Conferences International Limited, 2018. @conference{Purkayastha2018b, title = {Implementing Guided Inquiry Learning and Measuring Engagement Using an Electronic Health Record System in an Online Setting}, author = {Saptarshi Purkayastha, Asha Kiranmayee Surapaneni, Pallavi Maity}, year = {2018}, date = {2018-11-01}, booktitle = {European Conference on e-Learning}, pages = {481-488}, publisher = {Academic Conferences International Limited}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
Saptarshi Purkayastha Parvati Ravindranathan Menon Naliyatthaliyazchayil, Asha Kiranmayee Surapaneni Ashwini Kowkutla Pallavi Maity Improving "Desktop medicine" efficiency using Guided Inquiry Learning in an Electronic Health Records System Conference Communications in Computer and Information Science, vol 852, Springer, Cham, 2018. @conference{Purkayastha2018, title = {Improving "Desktop medicine" efficiency using Guided Inquiry Learning in an Electronic Health Records System}, author = {Saptarshi Purkayastha, Parvati Ravindranathan Menon Naliyatthaliyazchayil, Asha Kiranmayee Surapaneni, Ashwini Kowkutla, Pallavi Maity}, editor = {Stephanidis C. HCI International 2018 – Posters' Extended Abstracts. HCI 2018}, year = {2018}, date = {2018-07-18}, booktitle = {Communications in Computer and Information Science, vol 852}, journal = {Communications in Computer and Information Science, vol 852.}, publisher = {Springer, Cham}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
Gichoya, Judy W; Kohli, Marc; Ivange, Larry; Schmidt, Teri S; Purkayastha, Saptarshi A Platform for Innovation and Standards Evaluation: a Case Study from the OpenMRS Open-Source Radiology Information System Journal Article Journal of digital imaging, pp. 1–10, 2018. @article{gichoya2018platform, title = {A Platform for Innovation and Standards Evaluation: a Case Study from the OpenMRS Open-Source Radiology Information System}, author = {Judy W Gichoya and Marc Kohli and Larry Ivange and Teri S Schmidt and Saptarshi Purkayastha}, year = {2018}, date = {2018-01-01}, journal = {Journal of digital imaging}, pages = {1--10}, publisher = {Springer International Publishing}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Gichoya, Judy W; Nuthakki, Siddhartha; Maity, Pallavi G; Purkayastha, Saptarshi Phronesis of AI in radiology: Superhuman meets natural stupidity Journal Article arXiv preprint arXiv:1803.11244, 2018. @article{gichoya2018phronesis, title = {Phronesis of AI in radiology: Superhuman meets natural stupidity}, author = {Judy W Gichoya and Siddhartha Nuthakki and Pallavi G Maity and Saptarshi Purkayastha}, year = {2018}, date = {2018-01-01}, journal = {arXiv preprint arXiv:1803.11244}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2017 |
Holden, Richard J; Kulanthaivel, Anand; Purkayastha, Saptarshi; Goggins, Kathryn M; Kripalani, Sunil Know thy eHealth user: Development of biopsychosocial personas from a study of older adults with heart failure Journal Article International Journal of Medical Informatics, 108 , pp. 158-167, 2017, ISSN: 1386-5056. @article{holden2017know, title = {Know thy eHealth user: Development of biopsychosocial personas from a study of older adults with heart failure}, author = { Richard J Holden and Anand Kulanthaivel and Saptarshi Purkayastha and Kathryn M Goggins and Sunil Kripalani}, doi = {10.1016/j.ijmedinf.2017.10.006}, issn = {1386-5056}, year = {2017}, date = {2017-12-01}, journal = {International Journal of Medical Informatics}, volume = {108}, pages = {158-167}, publisher = {Elsevier}, abstract = {Background Personas are a canonical user-centered design method increasingly used in health informatics research. Personas—empirically-derived user archetypes—can be used by eHealth designers to gain a robust understanding of their target end users such as patients. Objective To develop biopsychosocial personas of older patients with heart failure using quantitative analysis of survey data. Method Data were collected using standardized surveys and medical record abstraction from 32 older adults with heart failure recently hospitalized for acute heart failure exacerbation. Hierarchical cluster analysis was performed on a final dataset of n = 30. Nonparametric analyses were used to identify differences between clusters on 30 clustering variables and seven outcome variables. Results Six clusters were produced, ranging in size from two to eight patients per cluster. Clusters differed significantly on these biopsychosocial domains and subdomains: demographics (age, sex); medical status (comorbid diabetes); functional status (exhaustion, household work ability, hygiene care ability, physical ability); psychological status (depression, health literacy, numeracy); technology (Internet availability); healthcare system (visit by home healthcare, trust in providers); social context (informal caregiver support, cohabitation, marital status); and economic context (employment status). Tabular and narrative persona descriptions provide an easy reference guide for informatics designers. Discussion Personas development using approaches such as clustering of structured survey data is an important tool for health informatics professionals. We describe insights from our study of patients with heart failure, then recommend a generic ten-step personas development process. Methods strengths and limitations of the study and of personas development generally are discussed.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background Personas are a canonical user-centered design method increasingly used in health informatics research. Personas—empirically-derived user archetypes—can be used by eHealth designers to gain a robust understanding of their target end users such as patients. Objective To develop biopsychosocial personas of older patients with heart failure using quantitative analysis of survey data. Method Data were collected using standardized surveys and medical record abstraction from 32 older adults with heart failure recently hospitalized for acute heart failure exacerbation. Hierarchical cluster analysis was performed on a final dataset of n = 30. Nonparametric analyses were used to identify differences between clusters on 30 clustering variables and seven outcome variables. Results Six clusters were produced, ranging in size from two to eight patients per cluster. Clusters differed significantly on these biopsychosocial domains and subdomains: demographics (age, sex); medical status (comorbid diabetes); functional status (exhaustion, household work ability, hygiene care ability, physical ability); psychological status (depression, health literacy, numeracy); technology (Internet availability); healthcare system (visit by home healthcare, trust in providers); social context (informal caregiver support, cohabitation, marital status); and economic context (employment status). Tabular and narrative persona descriptions provide an easy reference guide for informatics designers. Discussion Personas development using approaches such as clustering of structured survey data is an important tool for health informatics professionals. We describe insights from our study of patients with heart failure, then recommend a generic ten-step personas development process. Methods strengths and limitations of the study and of personas development generally are discussed. |
Kasiiti, N; Wawira, J; Purkayastha, S; Were, MC Comparative Performance Analysis of Different Fingerprint Biometric Scanners for Patient Matching. Conference MedInfo 2017, 245 , 2017. @conference{kasiiti2017comparative, title = {Comparative Performance Analysis of Different Fingerprint Biometric Scanners for Patient Matching.}, author = {N Kasiiti and J Wawira and S Purkayastha and MC Were}, year = {2017}, date = {2017-11-01}, booktitle = {MedInfo 2017}, journal = {Studies in health technology and informatics}, volume = {245}, pages = {1053--1057}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
Gichoya, Judy Wawira; Alarifi, Mohammad; Bhaduri, Ria; Tahir, Bilal; Purkayastha, Saptarshi Using cognitive fit theory to evaluate patient understanding of medical images Inproceedings Engineering in Medicine and Biology Society (EMBC), 2017 39th Annual International Conference of the IEEE, pp. 2430-2433, IEEE 2017. @inproceedings{gichoya2017using, title = {Using cognitive fit theory to evaluate patient understanding of medical images}, author = { Judy Wawira Gichoya and Mohammad Alarifi and Ria Bhaduri and Bilal Tahir and Saptarshi Purkayastha}, doi = {10.1109/EMBC.2017.8037347}, year = {2017}, date = {2017-07-11}, booktitle = {Engineering in Medicine and Biology Society (EMBC), 2017 39th Annual International Conference of the IEEE}, pages = {2430-2433}, organization = {IEEE}, abstract = {Patients are increasingly presented with their health data through patient portals in an attempt to engage patients in their own care. Due to the large amounts of data generated during a patient visit, the medical information when shared with patients can be overwhelming and cause anxiety due to lack of understanding. Health care organizations are attempting to improve transparency by providing patients with access to visit information. In this paper, we present our findings from a research study to evaluate patient understanding of medical images. We used cognitive fit theory to evaluate existing tools and images that are shared with patients and analyzed the relevance of such sharing. We discover that medical images need a lot of customization before they can be shared with patients. We suggest that new tools for medical imaging should be developed to fit the cognitive abilities of patients.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Patients are increasingly presented with their health data through patient portals in an attempt to engage patients in their own care. Due to the large amounts of data generated during a patient visit, the medical information when shared with patients can be overwhelming and cause anxiety due to lack of understanding. Health care organizations are attempting to improve transparency by providing patients with access to visit information. In this paper, we present our findings from a research study to evaluate patient understanding of medical images. We used cognitive fit theory to evaluate existing tools and images that are shared with patients and analyzed the relevance of such sharing. We discover that medical images need a lot of customization before they can be shared with patients. We suggest that new tools for medical imaging should be developed to fit the cognitive abilities of patients. |
Addepally, Siva Abhishek; Purkayastha, Saptarshi Mobile-Application Based Cognitive Behavior Therapy (CBT) for Identifying and Managing Depression and Anxiety Inproceedings V., Duffy (Ed.): International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management, pp. 3–12, Springer, Cham, 2017, ISBN: 978-3-319-58466-9. @inproceedings{addepally2017mobile, title = {Mobile-Application Based Cognitive Behavior Therapy (CBT) for Identifying and Managing Depression and Anxiety}, author = { Siva Abhishek Addepally and Saptarshi Purkayastha}, editor = {Duffy V.}, doi = {10.1007/978-3-319-58466-9_1}, isbn = {978-3-319-58466-9}, year = {2017}, date = {2017-05-14}, booktitle = {International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management}, pages = {3--12}, publisher = {Springer, Cham}, abstract = {Mobile technology is a cost effective and scalable platform for developing a therapeutic intervention. This paper discusses the development of a mobile application for people suffering with depression and anxiety. The application which we have developed is similar to a Cognitive Behavior Therapy (CBT) website, which is freely available on the internet. Past research has shown that CBT delivered over the internet is effective in alleviating the depressive symptoms in users. But, this delivery method is associated with some innate drawbacks, which caused user dropout and reduced adherence to the therapy. To overcome these shortfalls, from web based CBT delivery, a mobile application called MoodTrainer was developed. The application is equipped with mobile specific interventions and CBT modules which aim at delivering a dynamic supportive psychotherapy to the user. The mobile specific interventions using this application ensures that the user is constantly engaged with the application and focused to change the negative thought process. We present MoodTrainer as a self-efficacy tool and virtual CBT that is not meant to replace a clinical caregiver. Rather, it is a supportive tool that can be used to self-monitor, as well as a monitoring aid for clinicians.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Mobile technology is a cost effective and scalable platform for developing a therapeutic intervention. This paper discusses the development of a mobile application for people suffering with depression and anxiety. The application which we have developed is similar to a Cognitive Behavior Therapy (CBT) website, which is freely available on the internet. Past research has shown that CBT delivered over the internet is effective in alleviating the depressive symptoms in users. But, this delivery method is associated with some innate drawbacks, which caused user dropout and reduced adherence to the therapy. To overcome these shortfalls, from web based CBT delivery, a mobile application called MoodTrainer was developed. The application is equipped with mobile specific interventions and CBT modules which aim at delivering a dynamic supportive psychotherapy to the user. The mobile specific interventions using this application ensures that the user is constantly engaged with the application and focused to change the negative thought process. We present MoodTrainer as a self-efficacy tool and virtual CBT that is not meant to replace a clinical caregiver. Rather, it is a supportive tool that can be used to self-monitor, as well as a monitoring aid for clinicians. |
Oladiran, Olakunle; Gichoya, Judy; Purkayastha, Saptarshi Conversion of JPG Image into DICOM Image Format with One Click Tagging Inproceedings International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management, pp. 61-70, Springer, Cham 2017, ISBN: 978-3-319-58466-9. @inproceedings{oladiran2017conversion, title = {Conversion of JPG Image into DICOM Image Format with One Click Tagging}, author = { Olakunle Oladiran and Judy Gichoya and Saptarshi Purkayastha}, doi = {10.1007/978-3-319-58466-9_6}, isbn = {978-3-319-58466-9}, year = {2017}, date = {2017-05-14}, booktitle = {International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management}, pages = {61-70}, organization = {Springer, Cham}, abstract = {DICOM images are the centerpiece of radiological imaging. They contain a lot of metadata information about the patient, procedure, sequence of images, device and location. To modify, annotate or simply anonymize images for distribution, we often need to convert DICOM images to another format like jpeg since there are a number of image manipulation tools available for jpeg images compared to DICOM. As part of a research at our institution to customize radiology images to assess cognitive ability of multiple user groups, we created an open-source tool called Jpg2DicomTags, which is able to extract DICOM metadata tags, convert images to lossless jpg that can be manipulated and subsequently reconvert jpg images to DICOM by adding back the metadata tags. This tool provides a simple, easy to use user-interface for a tedious manual task that providers, researchers and patients might often need to do.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } DICOM images are the centerpiece of radiological imaging. They contain a lot of metadata information about the patient, procedure, sequence of images, device and location. To modify, annotate or simply anonymize images for distribution, we often need to convert DICOM images to another format like jpeg since there are a number of image manipulation tools available for jpeg images compared to DICOM. As part of a research at our institution to customize radiology images to assess cognitive ability of multiple user groups, we created an open-source tool called Jpg2DicomTags, which is able to extract DICOM metadata tags, convert images to lossless jpg that can be manipulated and subsequently reconvert jpg images to DICOM by adding back the metadata tags. This tool provides a simple, easy to use user-interface for a tedious manual task that providers, researchers and patients might often need to do. |
Walker, Marisa; Ge, Weiwei; Gichoya, Judy W; Purkayastha, Saptarshi Implementing clinical practice guidelines for chronic obstructive pulmonary disease in an EHR system Inproceedings Healthcare Innovations and Point of Care Technologies (HI-POCT), 2017 IEEE, pp. 148–151, IEEE 2017. @inproceedings{walker2017implementing, title = {Implementing clinical practice guidelines for chronic obstructive pulmonary disease in an EHR system}, author = {Marisa Walker and Weiwei Ge and Judy W Gichoya and Saptarshi Purkayastha}, year = {2017}, date = {2017-01-01}, booktitle = {Healthcare Innovations and Point of Care Technologies (HI-POCT), 2017 IEEE}, pages = {148--151}, organization = {IEEE}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Gichoya, J; Haste, P; Mills, A; Kohli, M; Johnson, M Creating an interventional oncology translational database: early experience at Indiana University Presentation 01.01.2017. @misc{Gichoya2017c, title = {Creating an interventional oncology translational database: early experience at Indiana University }, author = { J Gichoya and P Haste and A Mills and M Kohli and M Johnson}, doi = {10.1016/j.jvir.2016.12.996}, year = {2017}, date = {2017-01-01}, journal = {Journal of Vascular and Interventional Radiology}, volume = {28}, number = {2 Supplement}, pages = {S162}, keywords = {}, pubstate = {published}, tppubtype = {presentation} } |
Jung, Hye-Young; Gichoya, Judy Wawira; Vest, Joshua R Providers’ Access of Imaging Versus Only Reports: A System Log File Analysis Journal Article Journal of the American College of Radiology, 14 (2), pp. 217–223, 2017. @article{jung2017providers, title = {Providers’ Access of Imaging Versus Only Reports: A System Log File Analysis}, author = { Hye-Young Jung and Judy Wawira Gichoya and Joshua R Vest}, year = {2017}, date = {2017-01-01}, journal = {Journal of the American College of Radiology}, volume = {14}, number = {2}, pages = {217--223}, publisher = {Elsevier}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Gichoya, Judy Wawira; Kohli, Marc D; Haste, Paul; Abigail, Elizabeth Mills; Johnson, Matthew S Proving Value in Radiology: Experience Developing and Implementing a Shareable Open Source Registry Platform Driven by Radiology Workflow Journal Article Journal of digital imaging, 30 (5), pp. 602–608, 2017. @article{gichoya2017proving, title = {Proving Value in Radiology: Experience Developing and Implementing a Shareable Open Source Registry Platform Driven by Radiology Workflow}, author = { Judy Wawira Gichoya and Marc D Kohli and Paul Haste and Elizabeth Mills Abigail and Matthew S Johnson}, year = {2017}, date = {2017-01-01}, journal = {Journal of digital imaging}, volume = {30}, number = {5}, pages = {602--608}, publisher = {Springer}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Purkayastha, Saptarshi; Gichoya, Judy W; Addepally, Siva Abhishek Implementation of a single sign-on system between practice, research and learning systems Journal Article Applied Clinical Informatics, 8 (01), pp. 306-312, 2017, ISSN: 1869-0327. @article{purkayastha2017implementation, title = {Implementation of a single sign-on system between practice, research and learning systems}, author = { Saptarshi Purkayastha and Judy W Gichoya and Siva Abhishek Addepally}, doi = {10.4338/ACI-2016-10-CR-0171}, issn = {1869-0327}, year = {2017}, date = {2017-01-01}, journal = {Applied Clinical Informatics}, volume = {8}, number = {01}, pages = {306-312}, publisher = {Schattauer GmbH}, abstract = {Background: Multiple specialized electronic medical systems are utilized in the health enterprise. Each of these systems has their own user management, authentication and authorization process, which makes it a complex web for navigation and use without a coherent process workflow. Users often have to remember multiple passwords, login/logout between systems that disrupt their clinical workflow. Challenges exist in managing permissions for various cadres of health care providers. Objectives: This case report describes our experience of implementing a single sign-on system, used between an electronic medical records system and a learning management system at a large academic institution with an informatics department responsible for student education and a medical school affiliated with a hospital system caring for patients and conducting research. Methods: At our institution, we use OpenMRS for research registry tracking of interventional radiology patients as well as to provide access to medical records to students studying health informatics. To provide authentication across different users of the system with different permissions, we developed a Central Authentication Service (CAS) module for OpenMRS, released under the Mozilla Public License and deployed it for single sign-on across the academic enterprise. The module has been in implementation since August 2015 to present, and we assessed usability of the registry and education system before and after implementation of the CAS module. 54 students and 3 researchers were interviewed. Results: The module authenticates users with appropriate privileges in the medical records system, providing secure access with minimal disruption to their workflow. No passwords requests were sent and users reported ease of use, with streamlined workflow. Conclusions: The project demonstrates that enterprise-wide single sign-on systems should be used in healthcare to reduce complexity like “password hell”, improve usability and user navigation. We plan to extend this to work with other systems used in the health care enterprise.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background: Multiple specialized electronic medical systems are utilized in the health enterprise. Each of these systems has their own user management, authentication and authorization process, which makes it a complex web for navigation and use without a coherent process workflow. Users often have to remember multiple passwords, login/logout between systems that disrupt their clinical workflow. Challenges exist in managing permissions for various cadres of health care providers. Objectives: This case report describes our experience of implementing a single sign-on system, used between an electronic medical records system and a learning management system at a large academic institution with an informatics department responsible for student education and a medical school affiliated with a hospital system caring for patients and conducting research. Methods: At our institution, we use OpenMRS for research registry tracking of interventional radiology patients as well as to provide access to medical records to students studying health informatics. To provide authentication across different users of the system with different permissions, we developed a Central Authentication Service (CAS) module for OpenMRS, released under the Mozilla Public License and deployed it for single sign-on across the academic enterprise. The module has been in implementation since August 2015 to present, and we assessed usability of the registry and education system before and after implementation of the CAS module. 54 students and 3 researchers were interviewed. Results: The module authenticates users with appropriate privileges in the medical records system, providing secure access with minimal disruption to their workflow. No passwords requests were sent and users reported ease of use, with streamlined workflow. Conclusions: The project demonstrates that enterprise-wide single sign-on systems should be used in healthcare to reduce complexity like “password hell”, improve usability and user navigation. We plan to extend this to work with other systems used in the health care enterprise. |
2016 |
Gichoya, Judy W; Kasthurirathne, Suranga; Genereaux, Brad; Karunarathne, Milan; Purkayastha, Saptarshi; Kahn, Charles E Using HL7 FHIR to Integrate Structured Reporting Reports into an Open Source Medical Records System Conference SIIM 2016 Scientific Session, Enterprise Imaging 2016. @conference{genereauxusing, title = {Using HL7 FHIR to Integrate Structured Reporting Reports into an Open Source Medical Records System}, author = {Judy W. Gichoya and Suranga Kasthurirathne and Brad Genereaux and Milan Karunarathne and Saptarshi Purkayastha and Charles E Kahn}, year = {2016}, date = {2016-07-01}, booktitle = {SIIM 2016 Scientific Session}, series = {Enterprise Imaging}, abstract = {The radiology report is the core tool of communication between radiologists and ordering clinicians. In the current healthcare delivery model, there is interaction with various departments and across multiple providers requiring interchange of the radiology reports. The MRRT (Management of Radiology Report Templates) profile developed by the Integrating the Healthcare Enterprise (IHE) radiology workgroup defines the format of radiology templates and the mechanism to query, retrieve and store the templates. Various studies on the use of MRRT enabled reporting templates postulate a delivery model where there is a central repository of MRRT reports such as the RSNA radiology report template library or a specialty focused repository of reports as proposed by the Society of interventional Radiology (SIR). The MRRT format would be queried by radiologists using a reporting system and loaded as a template that the radiologist can dictate into the fields. The completed report would then be saved into the radiology information system (RIS) and PACS and other applications in the enterprise. Previous work using the MRRT profile described the development of the standard and conversion of available reports from the RSNA report template library to the MRRT profile. Vendors remain in the early phases of adoption of the MRRT standard, and the technical process of how to implement the profile is not documented. Various standards that allow exchange of clinical data include HL7 v1,v2 and v3; CDA (Clinical Document Architecture). FHIR (Fast Health Interoperability Resources) is a standard developed by HL7 to exchange data between clinical applications in a consistent, easy to implement and rigorous mechanism. We describe a technical implementation of MRRT profile that allows exchange of MRRT generated reports with an open-source medical records system (OpenMRS) using actual CT Pulmonary embolism reports. }, keywords = {}, pubstate = {published}, tppubtype = {conference} } The radiology report is the core tool of communication between radiologists and ordering clinicians. In the current healthcare delivery model, there is interaction with various departments and across multiple providers requiring interchange of the radiology reports. The MRRT (Management of Radiology Report Templates) profile developed by the Integrating the Healthcare Enterprise (IHE) radiology workgroup defines the format of radiology templates and the mechanism to query, retrieve and store the templates. Various studies on the use of MRRT enabled reporting templates postulate a delivery model where there is a central repository of MRRT reports such as the RSNA radiology report template library or a specialty focused repository of reports as proposed by the Society of interventional Radiology (SIR). The MRRT format would be queried by radiologists using a reporting system and loaded as a template that the radiologist can dictate into the fields. The completed report would then be saved into the radiology information system (RIS) and PACS and other applications in the enterprise. Previous work using the MRRT profile described the development of the standard and conversion of available reports from the RSNA report template library to the MRRT profile. Vendors remain in the early phases of adoption of the MRRT standard, and the technical process of how to implement the profile is not documented. Various standards that allow exchange of clinical data include HL7 v1,v2 and v3; CDA (Clinical Document Architecture). FHIR (Fast Health Interoperability Resources) is a standard developed by HL7 to exchange data between clinical applications in a consistent, easy to implement and rigorous mechanism. We describe a technical implementation of MRRT profile that allows exchange of MRRT generated reports with an open-source medical records system (OpenMRS) using actual CT Pulmonary embolism reports. |
Kasthurirathne, Suranga N; Dixon, Brian E; Gichoya, Judy; Xu, Huiping; Xia, Yuni; Mamlin, Burke; Grannis, Shaun J Toward better public health reporting using existing off the shelf approaches: A comparison of alternative cancer detection approaches using plaintext medical data and non-dictionary based feature selection Journal Article Journal of biomedical informatics, 60 , pp. 145–152, 2016. @article{kasthurirathne2016toward, title = {Toward better public health reporting using existing off the shelf approaches: A comparison of alternative cancer detection approaches using plaintext medical data and non-dictionary based feature selection}, author = { Suranga N Kasthurirathne and Brian E Dixon and Judy Gichoya and Huiping Xu and Yuni Xia and Burke Mamlin and Shaun J Grannis}, year = {2016}, date = {2016-01-01}, journal = {Journal of biomedical informatics}, volume = {60}, pages = {145--152}, publisher = {Elsevier}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2015 |
Maheshwari, Manika; Purkayastha, Saptarshi Designing a drawing-based tool to manage EBRT process in an open-source oncology EMR system Inproceedings AMIA Symposium 2015 2015. @inproceedings{maheshwari2015designing, title = {Designing a drawing-based tool to manage EBRT process in an open-source oncology EMR system}, author = { Manika Maheshwari and Saptarshi Purkayastha}, year = {2015}, date = {2015-01-01}, organization = {AMIA Symposium 2015}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Purkayastha, S; Price, A; Biswas, R; Ganesh, AU Jai; Otero, P From Dyadic Ties to Information Infrastructures: Care-Coordination between Patients, Providers, Students and Researchers Journal Article Yearbook of Medical Informatics, 10 (1), pp. 68, 2015. @article{purkayastha2015dyadic, title = {From Dyadic Ties to Information Infrastructures: Care-Coordination between Patients, Providers, Students and Researchers}, author = { S Purkayastha and A Price and R Biswas and AU Jai Ganesh and P Otero}, doi = {10.15265/IY-2015-008}, year = {2015}, date = {2015-01-01}, journal = {Yearbook of Medical Informatics}, volume = {10}, number = {1}, pages = {68}, publisher = {Schattauer Publishers}, abstract = {Objective To share how an effectual merging of local and online networks in low resource regions can supplement and strengthen the local practice of patient centered care through the use of an online digital infrastructure powered by all stakeholders in healthcare. User Driven Health Care offers the dynamic integration of patient values and evidence based solutions for improved medical communication in medical care. Introduction This paper conceptualizes patient care-coordination through the lens of engaged stakeholders using digital infrastructures tools to integrate information technology. We distinguish this lens from the prevalent conceptualization of dyadic ties between clinician-patient, patient-nurse, clinician-nurse, and offer the holistic integration of all stakeholder inputs, in the clinic and augmented by online communication in a multi-national setting. Methods We analyze an instance of the user-driven health care (UDHC), a network of providers, patients, students and researchers working together to help manage patient care. The network currently focuses on patients from LMICs, but the provider network is global in reach. We describe UDHC and its opportunities and challenges in care-coordination to reduce costs, bring equity, and improve care quality and share evidence. Conclusion UDHC has resulted in coordinated global based local care, affecting multiple facets of medical practice. Shared information resources between providers with disparate knowledge, results in better understanding by patients, unique and challenging cases for students, innovative community based research and discovery learning for all.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Objective To share how an effectual merging of local and online networks in low resource regions can supplement and strengthen the local practice of patient centered care through the use of an online digital infrastructure powered by all stakeholders in healthcare. User Driven Health Care offers the dynamic integration of patient values and evidence based solutions for improved medical communication in medical care. Introduction This paper conceptualizes patient care-coordination through the lens of engaged stakeholders using digital infrastructures tools to integrate information technology. We distinguish this lens from the prevalent conceptualization of dyadic ties between clinician-patient, patient-nurse, clinician-nurse, and offer the holistic integration of all stakeholder inputs, in the clinic and augmented by online communication in a multi-national setting. Methods We analyze an instance of the user-driven health care (UDHC), a network of providers, patients, students and researchers working together to help manage patient care. The network currently focuses on patients from LMICs, but the provider network is global in reach. We describe UDHC and its opportunities and challenges in care-coordination to reduce costs, bring equity, and improve care quality and share evidence. Conclusion UDHC has resulted in coordinated global based local care, affecting multiple facets of medical practice. Shared information resources between providers with disparate knowledge, results in better understanding by patients, unique and challenging cases for students, innovative community based research and discovery learning for all. |
Purkayastha, Saptarshi The Genus of Information Infrastructures: Architecture, Governance & Praxis. PhD Thesis Norwegian University of Science and Technology, Trondheim, Norway, 2015. @phdthesis{purkayastha2015genus, title = {The Genus of Information Infrastructures: Architecture, Governance & Praxis.}, author = { Saptarshi Purkayastha}, year = {2015}, date = {2015-01-01}, school = {Norwegian University of Science and Technology, Trondheim, Norway}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } |
2014 |
Purkayastha, Saptarshi OpenScrum: Scrum methodology to improve shared understanding in an open-source community Journal Article 2014. @article{purkayastha2014openscrum, title = {OpenScrum: Scrum methodology to improve shared understanding in an open-source community}, author = { Saptarshi Purkayastha}, year = {2014}, date = {2014-01-01}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Purkayastha, Saptarshi; Staring, Knut Special Issue on Theory Driven Interventions: Are We Looking at Social and Organizational Aspects of Health Care Technology in the Field of Medical Informatics? Journal Article International Journal of User-Driven Healthcare (IJUDH), 4 (1), pp. 4, 2014. @article{purkayastha2014special, title = {Special Issue on Theory Driven Interventions: Are We Looking at Social and Organizational Aspects of Health Care Technology in the Field of Medical Informatics?}, author = { Saptarshi Purkayastha and Knut Staring}, year = {2014}, date = {2014-01-01}, journal = {International Journal of User-Driven Healthcare (IJUDH)}, volume = {4}, number = {1}, pages = {4}, publisher = {IGI-Global}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
2013 |
Purkayastha, Saptarshi; ø, J Overview, not Overwhelm: Framing Operational BI Tools using Organizational Capabilities Journal Article 2013. @article{purkayastha2013overview, title = {Overview, not Overwhelm: Framing Operational BI Tools using Organizational Capabilities}, author = { Saptarshi Purkayastha and J{ø}rn Braa}, year = {2013}, date = {2013-01-01}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Publications
2021 |
Usability and Security of Different Authentication Methods for an Electronic Health Records System Conference Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (HEALTHINF), 2021. |
Failures hiding in success for artificial intelligence in radiology Journal Article Journal of the American College of Radiology, 18 (3), pp. 517-519, 2021. |
Human Activity Recognition using Deep Learning Models on Smartphones and Smartwatches Sensor Data Conference Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021), 5 , Science and Technology Publications, 2021, ISBN: 978-989-758-490-9. |
2020 |
Current clinical applications of artificial intelligence in radiology and their best supporting evidence Journal Article Journal of the American College of Radiology, 17 (11), pp. 1371-1381, 2020. |
Wireless vital signs monitoring of opioid-exposed newborns during skin-to-skin care: Biomedical device innovation Presentation 28.10.2020. |
Enabling Secure and Effective Biomedical Data Sharing through Cyberinfrastructure Gateways Conference Gateways 2020, 2020. |
Digital health innovations, tools, and resources to support Helping Babies Survive programs Journal Article Pediatrics, 146 (Supplement 2), pp. S165-S182, 2020, ISSN: 0031-4005. |
Blood Glucose Level Prediction as Time-Series Modeling using Sequence-to-Sequence Neural Networks Inproceedings Bach, Kerstin; Bunescu, Razvan; Marling, Cindy; Wiratunga, Nirmalie (Ed.): Proceedings of the 5th International Workshop on Knowledge Discovery in Healthcare Data co-located with 24th European Conference on Artificial Intelligence (ECAI 2020), pp. 125-130, CEUR-WS Workshop Proceedings, 2020. |
Essential Care for Every Baby: Neonatal Clinical Decision Support Tool Conference International Conference on Applied Human Factors and Ergonomics, 1205 , 2020, ISBN: 978-3-030-50837-1. |
The Artificial Intelligence Journal Club (# RADAIJC): A Multi-Institutional Resident-Driven Web-Based Educational Initiative Journal Article Academic radiology, 27 (1), pp. 136–139, 2020. |
AuthN-AuthZ: Integrated, User-Friendly and Privacy-Preserving Authentication and Authorization Inproceedings 2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), pp. 189–198, IEEE 2020. |
Engagement and Usability of a Cognitive Behavioral Therapy Mobile App Compared With Web-Based Cognitive Behavioral Therapy Among College Students: Randomized Heuristic Trial Journal Article JMIR Human Factors, 7 (1), pp. e14146, 2020. |
Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes Journal Article arXiv preprint arXiv:2003.07507, 2020. |
Developing and Deploying Machine Learning Pipelines against Real-Time Image Streams from the PACS Journal Article arXiv preprint arXiv:2004.07965, 2020. |
Artificial Intelligence for Global Health: Learning From a Decade of Digital Transformation in Health Care Journal Article arXiv preprint arXiv:2005.12378, 2020. |
eHBB/mHBS-DHIS2: Mobile Virtual Reality Provider Training in Helping Babies Breathetextregistered Miscellaneous 2020. |
Pre-Training Cognitive and Psychomotor Gaps in Healthcare Worker Neonatal Resuscitation Skills for Helping Babies Breathe--A Report from the eHBB/mHBS Study Miscellaneous 2020. |
Was there COVID-19 back in 2012? Challenge for AI in Diagnosis with Similar Indications Journal Article arXiv preprint arXiv:2006.13262, 2020. |
2019 |
The Development and Usability Testing of a Decision Support Mobile App for the Essential Care for Every Baby (ECEB) Program Conference International Conference on Human-Computer Interaction Springer, Cham, 2019. |
Evaluating the Implementation of Deep Learning in LibreHealth Radiology on Chest X-Rays Conference Computer Vision Conference, Springer, Cham, 2019. |
Comparison of Open-Source Electronic Health Record Systems Based on Functional and User Performance Criteria Journal Article Healthcare informatics research, 25 (2), pp. 89-98, 2019. |
Journal of medical Internet research, 21 (7), pp. e13809, 2019. |
Development and Implementation of a Dashboard for Diabetes Care Management in OpenMRS Journal Article arXiv preprint arXiv:1910.11437, 2019. |
Learning Gains of Process Oriented Guided Inquiry Learning in an Online Course Setting Inproceedings European Conference on e-Learning, pp. 495–XII, Academic Conferences International Limited 2019. |
Natural language processing of MIMIC-III clinical notes for identifying diagnosis and procedures with neural networks Journal Article arXiv preprint arXiv:1912.12397, 2019. |
Trends in RED Blood CELL Transfusions within the Biologics Effectiveness and Safety (BEST) Initiative Network, 2012-2018 Inproceedings 2019 Annual Meeting, AABB 2019. |
Critical Components of Formative Assessment in Process-Oriented Guided Inquiry Learning for Online Labs Journal Article Electronic Journal of e-Learning, 17 (2), 2019. |
Full training versus fine tuning for radiology images concept detection task for the Image Conference 2019, ISSN: 1613-0073. |
2018 |
Implementing Guided Inquiry Learning and Measuring Engagement Using an Electronic Health Record System in an Online Setting Conference European Conference on e-Learning, Academic Conferences International Limited, 2018. |
Improving "Desktop medicine" efficiency using Guided Inquiry Learning in an Electronic Health Records System Conference Communications in Computer and Information Science, vol 852, Springer, Cham, 2018. |
A Platform for Innovation and Standards Evaluation: a Case Study from the OpenMRS Open-Source Radiology Information System Journal Article Journal of digital imaging, pp. 1–10, 2018. |
Phronesis of AI in radiology: Superhuman meets natural stupidity Journal Article arXiv preprint arXiv:1803.11244, 2018. |
2017 |
Know thy eHealth user: Development of biopsychosocial personas from a study of older adults with heart failure Journal Article International Journal of Medical Informatics, 108 , pp. 158-167, 2017, ISSN: 1386-5056. |
Comparative Performance Analysis of Different Fingerprint Biometric Scanners for Patient Matching. Conference MedInfo 2017, 245 , 2017. |
Using cognitive fit theory to evaluate patient understanding of medical images Inproceedings Engineering in Medicine and Biology Society (EMBC), 2017 39th Annual International Conference of the IEEE, pp. 2430-2433, IEEE 2017. |
Mobile-Application Based Cognitive Behavior Therapy (CBT) for Identifying and Managing Depression and Anxiety Inproceedings V., Duffy (Ed.): International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management, pp. 3–12, Springer, Cham, 2017, ISBN: 978-3-319-58466-9. |
Conversion of JPG Image into DICOM Image Format with One Click Tagging Inproceedings International Conference on Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management, pp. 61-70, Springer, Cham 2017, ISBN: 978-3-319-58466-9. |
Implementing clinical practice guidelines for chronic obstructive pulmonary disease in an EHR system Inproceedings Healthcare Innovations and Point of Care Technologies (HI-POCT), 2017 IEEE, pp. 148–151, IEEE 2017. |
Creating an interventional oncology translational database: early experience at Indiana University Presentation 01.01.2017. |
Providers’ Access of Imaging Versus Only Reports: A System Log File Analysis Journal Article Journal of the American College of Radiology, 14 (2), pp. 217–223, 2017. |
Proving Value in Radiology: Experience Developing and Implementing a Shareable Open Source Registry Platform Driven by Radiology Workflow Journal Article Journal of digital imaging, 30 (5), pp. 602–608, 2017. |
Implementation of a single sign-on system between practice, research and learning systems Journal Article Applied Clinical Informatics, 8 (01), pp. 306-312, 2017, ISSN: 1869-0327. |
2016 |
Using HL7 FHIR to Integrate Structured Reporting Reports into an Open Source Medical Records System Conference SIIM 2016 Scientific Session, Enterprise Imaging 2016. |
Toward better public health reporting using existing off the shelf approaches: A comparison of alternative cancer detection approaches using plaintext medical data and non-dictionary based feature selection Journal Article Journal of biomedical informatics, 60 , pp. 145–152, 2016. |
2015 |
Designing a drawing-based tool to manage EBRT process in an open-source oncology EMR system Inproceedings AMIA Symposium 2015 2015. |
From Dyadic Ties to Information Infrastructures: Care-Coordination between Patients, Providers, Students and Researchers Journal Article Yearbook of Medical Informatics, 10 (1), pp. 68, 2015. |
The Genus of Information Infrastructures: Architecture, Governance & Praxis. PhD Thesis Norwegian University of Science and Technology, Trondheim, Norway, 2015. |
2014 |
OpenScrum: Scrum methodology to improve shared understanding in an open-source community Journal Article 2014. |
Special Issue on Theory Driven Interventions: Are We Looking at Social and Organizational Aspects of Health Care Technology in the Field of Medical Informatics? Journal Article International Journal of User-Driven Healthcare (IJUDH), 4 (1), pp. 4, 2014. |
2013 |
Overview, not Overwhelm: Framing Operational BI Tools using Organizational Capabilities Journal Article 2013. |