AI better assesses heart function from MRI than clinicians
Using artificial intelligence (AI) to assess heart function from magnetic resonance imaging (MRI) scans more strongly predicts survival than interpretation by clinicians, according to a study published online Nov. 2 in The Lancet Digital Health.
A new study published in The Lancet Digital Health has found that artificial intelligence (AI) can better assess heart function from magnetic resonance imaging (MRI) scans compared to clinicians. Using deep-learning AI segmentation of ejection fraction from cardiac MRI, researchers were able to predict all-cause mortality more accurately than expert clinician segmentation.
In an analysis of 27,382 patients, the AI ejection fraction showed a better model fit and marginally better discrimination in predicting mortality. When added to clinician ejection fraction, AI ejection fraction significantly improved model fit, while adding clinician ejection fraction to AI only resulted in a slight improvement.
After adjusting for age and sex, AI-derived ejection fraction still showed better model fit and marginal improvement in discrimination. Lead researcher George Joy stated that AI can measure this important marker with remarkable consistency and precision, leading to a small but meaningful improvement in identifying patients at higher risk of mortality.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
