AI-PRISM (Artificial Intelligence for Precision Recommendations and Integrated Scoring in Medicine

Focused Research Program
Special Track: Health Data Science

Our Focus

AI and machine learning (ML) have transformed various industries, yet their full potential in clinical medicine remains untapped due to concerns about interpretability, robustness, and integration into real-world decision-making. This FRP aims to apply AI and machine learning to clinical care applications to (1) optimize prescriptions for hypertension and (2) compute NIH Stroke Scales from unstructured clinical notes, emphasizing safety, robustness, and explainability.

Focused Research Program led by: 

Dr. Charlene J. Ong, MD, MPHS (Neurointensivist, BU Chobanian & Avedisian School of Medicine)

Dr. Ioannis (Yannis) Paschalidis, PhD (Distinguished Professor, BU Engineering; Founding Professor, Computing & Data Sciences; Director, Hariri Institute for Computing)

Dr. Nicholas Cordella, MD, MSc (Medical Director of Quality and Safety, BMC; Assistant Professor of Medicine, BU Chobanian & Avedisian School of Medicine)

Research Thrusts

1. Prescriptive Analytics for Optimized and Personalized Hypertension
Control

This thrust seeks to implement an ML/AI approach (Chen and Paschalidis, NeurIPS 2019; Hu, Cordella, Mishuris, and Paschalidis, BMC Med. Informatics & Decision Making, 2025) for personalized hypertension treatment recommendations in clinical practice, ensuring practical applicability and improved patient outcomes. To strengthen clinical-grade precision, this thrust will also establish rigorous evaluation methods to enhance model safety and reliability.

2. Agentic LLMs for Automated Stroke Assessment Leveraging Clinical Records

The goal of this thrust is to develop a LLM-driven multi-agent system that extracts clinical information from unstructured neurology ICU records to automatically compute NIHSS scores. This thrust aims to automate and standardize stroke severity assessment, reducing inter-rater variability and improving real-time clinical decision-making in stroke care.

Sponsors

This Health Data Sciences Focused Research Program is funded by the School of Public Health Center for Health Data Science, the Clinical and Translational Science Institute, the Evans Center for Interdisciplinary Biomedical Research, and the Digital Health Initiative at the Hariri Institute for Computing at Boston University.

How to get involved?

For program specific inquiries and questions, please contact FRP leaders: Charlene Ong, Yannis Paschalidis or Nicholas Cordella.

Faculty interested in submitting a Focused Research Programs proposal are strongly encouraged to discuss their ideas with Yannis Paschalidis, director of the Hariri Institute for Computing.

To learn more details about the Hariri Institute’s Focused Research Programs, visit here.