Featured Scholar: Saptarshi Purkayastha, Ph.D.
Associate Professor, Data Science and Health Informatics
Director, Purkayastha Lab for Health Innovation
IU Indianapolis School of Informatics and Computing
Risks and Opportunities of AI Recognition of Patient Race in Medical Imaging
Professor Saptarshi Purkayastha initiates innovative research that focuses on data in the field of health care. He has worked on and helped to implement projects around the world involving:
- National health information systems
- Telemedicine
- CAD applications
- mHealth
- Real time decision-making in robots
- GPGPU acceleration
- Distributed video encoding
- Educational technology for dyslexics.
Professor Purkayastha is currently investigating methods for improving engagement in online education, by using guided inquiry learning in the study of health information management. He’s also assisting with a project that’s utilizing virtual reality technology to improve health care delivery for newborns in low- and middle-income nations.
On behalf of the World Health Organization, Purkayastha has served as a consultant to ministries of health in the South-East Asia Region for the implementation of health information systems. Countries that were part of this project included Bangladesh, Nepal, Bhutan, and North Korea.
At IU Indianapolis, the researchers he leads at the Purkayastha Laboratory for Health Innovation are working on projects in radiological information systems, biomedical data analysis, electronic medical records, and mobile and population health.
Previous studies in medical imaging have shown disparate abilities of artificial intelligence (AI) to detect a person's race, yet there is no known correlation for race on medical imaging that would be obvious to human experts when interpreting the images. His recent work published in Lancet Digital Health demonstrates that deep learning models have extremely high accuracy at identifying self-reported race from medical images such as X-rays, MRIs and CTs. This ability raises serious concerns among some researchers. Such software might group patients, or influence their care, by factoring in race. These AI models work very well on poor quality, distorted and even images where many parts of the image were deliberately cut out. These types of categorizations could lead to inequality in providing health care and making recommendations, and human decision makers might not understand how and why AI models are making the recommendations. Engineers, clinical researchers and informaticians need to get together to identify how AI models are able to have these superhuman capabilities.
Professor Purkayastha's translation of research into potential ways to identify and mitigate risks of deploying AI models in clinical practice to avoid racial issues in healthcare treatment is another example of how IU Indianapolis's faculty members are TRANSLATING their RESEARCH INTO PRACTICE.
Selected Publications in IU Indianapolis ScholarWorks
With several research works contributed to IU Indianapolis's free, open access repository, Professor Purkayastha has made translational research knowledge available to professionals, researchers, students, and communities around the world.
Rajapuri, A. S., Ravindran, R., Horan, K., Bucher, S., & Purkayastha, S. (2020). Essential Care for Every Baby: Neonatal Clinical Decision Support Tool. In J. Kalra & N. J. Lightner (Eds.), Advances in Human Factors and Ergonomics in Healthcare and Medical Devices (pp. 189–196). Springer International Publishing. https://hdl.handle.net/1805/28647
Nuthakki, S., Bucher, S., & Purkayastha, S. (2019). The Development and Usability Testing of a Decision Support Mobile App for the Essential Care for Every Baby (ECEB) Program. In C. Stephanidis & M. Antona (Eds.), HCI International 2019 – Late Breaking Posters (pp. 259–263). Springer International Publishing. https://hdl.handle.net/1805/24392
Sinha, P., Purkayastha, S., & Gichoya, J. (2019). Full Training versus Fine Tuning for Radiology Images Concept Detection Task for the ImageCLEF 2019 Challenge. In CLEF (Working Notes), 8. https://hdl.handle.net/1805/23379
Gichoya, J. W., Kohli, M., Ivange, L., Schmidt, T. S., & Purkayastha, S. (2018). A Platform for Innovation and Standards Evaluation: a Case Study from the OpenMRS Open-Source Radiology Information System. Journal of Digital Imaging, 31(3), 361–370. https://hdl.handle.net/1805/17485
Purkayastha, S., Naliyatthaliyazchayil, P. R. M., Surapaneni, A. K., Kowkutla, A., Maity, P. (2018, July). Improving “Desktop medicine” efficiency using Guided Inquiry Learning in an Electronic Health Records System. In: Stephanidis C. (eds) HCI International 2018 – Posters' Extended Abstracts. HCI 2018. Communications in Computer and Information Science, vol. 852. Springer, Cham. https://hdl.handle.net/1805/17008
Purkayastha, S., Surapaneni, A. K., & Maity, P. (2018). Implementing Guided Inquiry Learning and Measuring Engagement Using an Electronic Health Record System in an Online Setting. European Conference on E-Learning; Kidmore End, 481–488. https://hdl.handle.net/1805/20520
Walker, M., Ge, W., Gichoya, J. W., & Purkayastha, S. (2017, November). Implementing clinical practice guidelines for chronic obstructive pulmonary disease in an EHR system. In Healthcare Innovations and Point of Care Technologies (HI-POCT), 2017 IEEE (pp. 148-151). IEEE. https://hdl.handle.net/1805/18055
Oladiran, O., Gichoya, J., & Purkayastha, S. (2017). Conversion of JPG Image into DICOM Image Format with One Click Tagging. In Digital Human Modeling. Applications in Health, Safety, Ergonomics, and Risk Management: Health and Safety (pp. 61–70). Springer, Cham. https://hdl.handle.net/1805/15681
Addepally, S. A., & Purkayastha, S. (2017). Mobile-Application Based Cognitive Behavior Therapy (CBT) for Identifying and Managing Depression and Anxiety. In Digital Human Modeling. Applications in Health, Safety, Ergonomics, and Risk Management: Health and Safety (pp. 3–12). Springer, Cham. https://hdl.handle.net/1805/15579
Maheshwari, Manika and Saptarshi Purkayastha. “Designing a drawing-based tool to manage EBRT process in an open-source oncology EMR system.” AMIA (2015). https://hdl.handle.net/1805/12224
Purkayastha, S. and Braa, J. (2013) Overview, not Overwhelm – Operational BI Tools for Big Data in Health Information Systems. Operational BI for Healthcare in Developing Countries. https://hdl.handle.net/1805/8896