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

Abstract

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