Achieving Value by Risk Stratification With Machine Learning Model or Clinical Risk Score in Acute Upper Gastrointestinal Bleeding: A Cost Minimization Analysis

Abstract

Introduction: We estimate the economic impact of applying risk assessment tools to identify very-low-risk patients with upper gastrointestinal bleeding (UGIB) who can be safely discharged from the emergency department using a cost minimization analysis. Methods: We compare triage strategies (Glasgow-Blatchford Score (GBS)=0/0-1 or validated machine-learning model) to usual care using a Markov chain model from a U.S. healthcare payer perspective. Results: Over 5 years, the GBS triage strategy produced national cumulative savings over usual care of over $2.7 billion, and the machine-learning strategy of over $3.4 billion. Conclusion: Implementing risk assessment models for UGIB reduces costs, thereby increasing value.