Artificial Intelligence-Assisted Point-of-Care Ultrasound for Evaluating Left Ventricular Ejection Fraction: A...

Artificial intelligence (AI) embedded in point-of-care ultrasound (POCUS) could reduce operator dependence in left ventricular ejection fraction (LVEF) assessment and accelerate bedside decision making by non-cardiologists and non-radiologists. Prospective comparative studies evaluating real-time AI-assisted POCUS for LVEF across point-of-care settings were systematically reviewed. The PubMed/MEDLINE, Embase, and Cochrane databases were searched from inception to June 11, 2025. The authors included prospective analytical observational studies in intensive care unit (ICU), emergency department, perioperative, ward, or home settings that used AI during image acquisition and/or interpretation to estimate LVEF in real time against a reference standard. Risk of bias was appraised using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Because of heterogeneity, the findings were narratively synthesized. Twelve studies met the inclusion criteria across ICU, emergency department, perioperative, ward, and community settings. For continuous outcomes, agreement (r) between AI-derived and reference LVEF ranged from 0.56 to 0.92 and intraclass correlation coefficients ranged from 0.84 to 0.94. Bland-Altman analyses demonstrated broad limits of agreement, from approximately -31.8% to +20.0%, often indicating a tendency for AI to underestimate LVEF compared with reference measures. For categorical classification at a 50% threshold, sensitivities ranged from 70% to 93%; specificities, from 89% to 100%; and areas under the receiver operating characteristic curves, from 0.85 to 0.98. Weighted κ values ranged from 0.49 to 0.83. No study achieved a low risk of bias across all QUADAS-2 domains. AI-assisted POCUS can approximate reference LVEF and reasonably classify reduced LVEF at the bedside, supporting its use as a screening and triage tool in settings in which comprehensive echocardiography is not immediately available. Future studies should adopt intention-to-diagnose designs, standardize the Simpson biplane reference, minimize test delay, report calibration and failure rates, and incorporate image quality feedback.