Global longitudinal strain measurement in the modern era - is artificial intelligence the answer ?

Abstract Background Global longitudinal strain (GLS) enhances the assessment of left ventricular (LV) function beyond ejection fraction (EF) in 2D echocardiography (Echo). However, manual GLS measurement, the most common technique, is operator dependent. A novel vendor-independent artificial intelligence (AI)-based software streamlines automated 2D-Echo exam evaluation and GLS calculation. Purpose We sought to evaluate the ability of the AI to automatically identify LV 4-, 2-, and 3-chamber views (CV) from 2D-Echo exams and to validate GLS against the conventional manual method. Methods 540 patients underwent standard 2D-Echo exams. The server-based AI recognized the optimal LV CVs from 2D-Echo exams and automatically calculated triplane GLS by endocardial delineation (n=489, 91%). Manual LV GLS was performed independently by accredited cardiologists. Pearson’s correlation (R) and Bland-Altman analysis were performed to assess bias and limits of agreement (LOA) for GLS. Multivariate between-method regression was performed using ordinary least squares to disclose possible sources of possible bias. Significance was defined as a 2-tailed P value < 0.05. Results Patients’ median age was 70 years [18-93], 59% were males. The 2D-Echo indications were coronary artery disease (36%), valvular heart disease (15%), non-ischemic heart failure (15%) and others (34%). The feasibility of the AI to calculate GLS was 91% (n=489) due to endocardial border delineation issues. AI correctly classified all CVs. An excellent correlation (r=0.92, p<0.001) was observed between AI and manual GLS, with low bias (0.5%) and narrow LOAs (-3.1 and +4.2%) (Figure 1, top row). We identified LV end-diastolic volume and EF as statistically significant confounders (p < 0.05) with only small effect as depicted in Figure 1 (bottom row). Neither sex, age, acoustic window, body mass index, nor heart rate, along with the interaction with sex, end-diastolic volume, or EF, were significant (p > 0.23). Conclusion AI-based LV GLS calculation in 2D-Echo shows promising feasibility and accuracy. Strong agreement between AI-derived GLS and manual measurements supports its reliability. The AI's ability to identify optimal LV views underscores its robustness. Further validation and refinement are warranted, highlighting the transformative potential of AI in advancing cardiovascular diagnostics.