Neelufar Payrovnaziri, a PhD candidate in the School of Information, and Dr. Zhe He recently published their first paper in the Journal of the American Medical Informatics Association (JAMIA). The two worked together to explore the adoption of electronic health records in their paper titled, “Explainable Artificial Intelligence Models Using Real-World Electronic Health Records Data: a Systematic Scoping Review.”

“The wide adoption of electronic health records (EHR) systems by healthcare organizations have made the application of Artificial Intelligence in Medicine (AIM) feasible,” Neelufar explains. “However, the production of such systems for actual clinical use is challenging mainly due to a lack of trust in these systems from medical professionals’ side. AIM systems have limited effectiveness because humans are not able to understand why such systems make particular decisions. Thus, Explainable AI (XAI) for medicine is of vital importance to support the implementation of AI in clinical decision support systems. The increasing capabilities of AIM married to the necessity of XAI demand a review of the state-of-the-art research in the field. Our review summarizes a decade of research on the enhancement of interpretability in EHR-based AIM. We aim to provide insights into the current research trend by categorizing ML methods, XAI approaches and targeted ML prediction tasks to identify potential gaps and suggest future research direction in the field. We also assess the reproducibility of the included studies. Finally, we review and evaluate the studies from the medical profession’s perspective on their interpretability enhancement deliverables.”

JAMIA is one of the most prestigious and widely read journals in the field of health and biomedical informatics. “It’s extremely difficult to get a paper in JAMIA,” Dr. He says. “This is my first JAMIA paper after doing research in this field for over 11 years.” The two hope that this publication will benefit both the biomedical researchers as well as practitioners and have an impact on artificial intelligence in medicine.

Neelufar and Dr. He would like to thank their coauthors from FSU’s Department of Computer Science (Dr. Xiuwen Liu), College of Medicine and Tallahassee Memorial Hospital (Dr. Pablo Rengifo-Moreno), University of Florida (Dr. Jiang Bian and Dr. Zhaoyi Chen), University of Melbourne (Dr. Tim Miller), and Stanford University (Dr. Jonathan H. Chen).