AI task-shifting for echocardiographic LVEF assessment in Singapore: an economic evaluation.

Abstract

Background: Accurate assessment of left ventricular ejection fraction (LVEF) is crucial for heart failure (HF) diagnosis but requires skilled sonographers. Artificial intelligence-enabled point-of-care (AI-POC) devices may enable novices to assess LVEF, potentially reducing healthcare costs. We conducted a cost-minimization analysis comparing conventional sonographer-performed echocardiography versus novice-operated AI-POC devices.

Methods: Using a decision tree model, we compared the costs of diagnosing LVEF <50% in patients with suspected heart failure across two pathways: novice-operated AI-POC devices versus standard transthoracic echocardiogram (TTE) performed by sonographers. The model incorporated LVEF <50% prevalence, diagnostic accuracy metrics, and comprehensive cost data for both approaches. We conducted a probabilistic sensitivity analysis to test the robustness of our findings under varying assumptions.

Results: The AI-POC pathway demonstrated substantial cost savings, averaging S$1185 [US$1422] per patient compared to S$1403 [US$1684] for conventional TTE. In a single tertiary referral centre in Singapore, implementing AI-POC devices for LVEF assessment in 100 patients resulted in savings of S$21 669 [US$26 013]. Probabilistic sensitivity analysis suggested a 99.9% probability that the AI-POC approach would be cost-saving compared to standard TTE.

Conclusions: This study provides economic evidence that task-shifting echocardiographic assessment of LVEF to novices using AI-POC devices is likely cost-saving compared to standard TTE. This task-shifting strategy offers a cost-saving alternative to conventional sonographer-led TTE.