Predicting Readmission Risk in Patients Undergoing Revascularization for Chronic Limb-Threatening Ischemia Using Machine Learning

Poster Number: P95
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Clinical Decision Support, Machine Learning, Chronic Care Management
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

This study employs machine learning to predict 90-day readmission and ED visit risks in CLTI patients post-revascularization surgery, using University of Florida Health IDR data from 2015 to 2023. SVM and Regularized Logistic Regression outperformed other models, with significant predictors including physical distance to UF Health, ER visit history, and specific health conditions. These findings underscore the potential of machine learning in improving clinical decision-making, which can be further improved using post-discharge information.

Speaker(s):
Mei Liu, PhD
University of Florida

Author(s):
Qi Xu, Ph.D - University of Florida; Megan Gregory, Ph.D. - University of Florida; Mei Liu, PhD - University of Florida; Samir Shah, MD, MPH - University of Florida; Ho Yin Chan, PhD - University of Florida; Nicole Hammer, B.A. - University of Florida - Department of Health Outcomes and Biomedical Informatics; Todd Manini, PhD - University of Florida; Miad Alfaqih, Phd - University of Florida; Sean Pajak, B.S. - University of Florida; Chase Antilla, B.S. - University of Florida;