A research team led by the School of Pharmacy and Pharmaceutical Sciences at the University at Buffalo in New York has developed an artificial intelligence model that predicts which cardiac patients are at risk of hospital readmission within 90 days with 95% accuracy.
Leaders collaborated with the Gainesville-based University of Florida and Tallahassee-based Florida A&M University to build the model using patient-reported behavioral data rather than retrospective clinical records, according to a Jan. 26 news release.
The study included more than 1,300 adults with at least one cardiovascular risk factor, such as hypertension or diabetes. Of the participants, 35% reported at least one hospitalization and 10.4% were readmitted within 90 days.
The model identified race, employment status, insurance status, number of medications and chronic disease burden as key predictors of readmission. Findings were published in the December 2025 issue of BMJ Health & Care Informatics.
Leaders said the team is seeking partnerships with hospitals in Buffalo to integrate the AI tool into clinical workflows and help frontline clinicians flag patients at risk for early intervention.
At the Becker’s 32nd Annual Meeting: The Business and Operations of ASCs, taking place October 29-31 in Chicago, ASC leaders, surgeons and healthcare executives will explore strategies to drive growth, enhance operational performance, navigate reimbursement challenges and prepare for the future of ambulatory surgery. Apply for complimentary registration now.
