Suffolk Reporter

Two researchers from Stony Brook University are developing machine learning models to predict patient outcomes, focusing on opioid use disorder and overdose. Richard N. Rosenthal, MD, a Professor in the Department of Psychiatry and Behavioral Health, collaborates with Fusheng Wang, PhD, a Professor in Biomedical Informatics and Computer Science. Their work is supported by a $1.05 million grant from the Patient-Centered Outcomes Research Institute (PCORI).

Wang's research aims to create models predicting the likelihood of patients developing opioid-related issues. "Most AI model development in health care is done by the developers so that there is little if any feedback into the process by the end users, such as clinicians," said Rosenthal. The team uses a "stakeholder-in-the-loop approach," allowing clinicians to provide feedback to improve model accuracy and usability.

"I think probably the most important contribution in this type of model is our stakeholder-in-the-loop approach," said Wang. Stakeholders will be involved throughout the model design and evaluation process. The complexity of patient data presents challenges, but involving clinicians can help integrate clinical knowledge into predictions.

The project includes collaboration with patient partners, clinicians, computer scientists, researchers, and community representatives from the New York State Office of Mental Health and Suffolk County Department of Health. The team hopes to expand their method to other diseases and test it in clinical settings like emergency departments.