Heart Model ^A.I. Three-Dimensional Echocardiographic Evaluation of Left Ventricular Function and Parameter Setting

Area of Science:

• Cardiology
• Medical Imaging
• Artificial Intelligence in Medicine

Background:

• Left ventricular function assessment is crucial in cardiovascular diagnostics.
• Traditional echocardiography methods can be time-consuming and operator-dependent.
• Advancements in artificial intelligence (AI) offer potential improvements in cardiac imaging analysis.

Purpose of the Study:

• To evaluate the feasibility of HeartModel A.I. (HM) three-dimensional echocardiography (3DE) for assessing left ventricular function.
• To identify optimal border parameter settings for HM 3DE analysis.
• To compare HM 3DE performance against conventional 3DE methods.

Main Methods:

• 113 patients underwent echocardiography using both HM 3DE and conventional 3DE.
• HM 3DE was applied with various end-diastolic (ED) and end-systolic (ES) border settings.
• Key parameters analyzed included LVEDV, LVESV, LVEF, and LAVmax, comparing HM 3DE results with conventional 3DE.

Main Results:

• HM 3DE showed strong correlations with conventional 3DE for LVEF, LVEDV, and LVESV.
• Optimal agreement for LVEF was achieved with ED/ES settings of 70/30, and for LVEDV/LVESV with 40/20.
• HM 3DE demonstrated superior reproducibility and reduced measurement time compared to conventional 3DE.

Conclusions:

• HM 3DE is a feasible, reproducible, and efficient tool for evaluating left ventricular function.
• Specific border parameter settings (ED 70, ES 30) are recommended for optimal left ventricular function assessment in the Chinese population.
• Further refinement may be needed for accurate assessment of left atrial volume (LAVmax) using HM 3DE.