Machine Learning Enhances Diagnosis of Necrotizing Soft Tissue Infections with Superior Accuracy

Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Machine Learning, Infectious Diseases and Epidemiology, Diagnostic Systems
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Machine learning enhances necrotizing soft tissue infection (NSTI) diagnosis by leveraging standard clinical data to produce an interpretable risk prediction tool. This approach surpasses the Laboratory Risk Indicator for Necrotizing Fasciitis (LRINEC)—a commonly used risk stratification score that underperforms in external validation. The new model shows strong potential for seamless clinical integration, improving accuracy and supporting timely decision-making to help reduce mortality from NSTI.

Speaker(s):
Anita Subbarao, MD
University of Washington

Author(s):
Anita Subbarao, MD - University of Washington; Jane Hall, PhD - University of Washington; Robert Doerning, MD, MBA, MS - University of Washington; Eileen Bulger, MD, FACS - University of Washington; Erika Bisgaard, MD - University of Washington; M. Kennedy Hall, MD MHS - University of Washington School of Medicine;