Assimilated LVEF: A Bayesian technique combining human intuition with machine measurement for sharper estimates of left ventricular ejection fraction and stronger association with outcomes

TL;DR

This paper introduces a Bayesian method that combines visual and machine-guided LVEF measurements to improve accuracy and better predict patient outcomes in heart failure assessment.

Contribution

It presents a novel Bayesian approach that integrates human intuition with machine data for more precise LVEF estimates, enhancing outcome prediction.

Findings

Reduced measurement errors in LVEF estimates

Stronger association between LVEF and clinical outcomes

Improved predictive accuracy for patient prognosis

Abstract

The cardiologist's main tool for measuring systolic heart failure is left ventricular ejection fraction (LVEF). Trained cardiologist's report both a visual and machine-guided measurement of LVEF, but only use this machine-guided measurement in analysis. We use a Bayesian technique to combine visual and machine-guided estimates from the PARTNER-IIA Trial, a cohort of patients with aortic stenosis at moderate risk treated with bioprosthetic aortic valves, and find our combined estimate reduces measurement errors and improves the association between LVEF and a 1-year composite endpoint.