When few diagnostics are available, it may make sense to use machine learning models to get the most out of them. It’s quite possible that a machine learning model that incorporates components from the CBC with diff/indices and the comprehensive metabolic panel could triage patients by predicting risk of conditions for which specific diagnostics are not locally available.
STUDY OBJECTIVE:
Sepsis is a common and major health crisis in hospitals globally. An innovative and feasible tool for predicting sepsis remains elusive. However, early and accurate prediction of sepsis could help physicians with proper treatments and minimize the diagnostic uncertainty. Machine learning models could help to identify potential clinical variables and provide higher performance than existing traditional low-performance models. We therefore performed a meta-analysis of observational studies to quantify the performance of a machine learning model to predict sepsis.