Echocardiography plays a crucial role in the diagnosis and management of patients with cardiovascular disease. Accurate quantitative assessment of cardiac structure and function is essential for initial evaluation, treatment planning and follow-up. However, while quantitative echocardiographic evaluation has undoubtedly improved patient care, the current manual measurements of echocardiographic parameters require time-consuming tasks even for the experienced clinician. In addition to strong dependence on the level of experience, the procedures are prone to intra- and inter-observer variability.
Artificial intelligence (AI) is rapidly evolving in the field of diagnostic medical imaging including echocardiography. Of importance, deep learning (DL), which has dramatically improved the accuracy of AI algorithms, enables efficient, accurate and consistent automated measurement in echocardiography. HeartAssist™ is a DL-powered AI software based on a SONIX HEALTH™ algorithm developed by ON:TACT HEALTH, and is commercially available as a built-in feature on the V7/V8 (Samsung Medison Co., Ltd., Seoul, Korea). By eliminating observer-dependent manual intervention, HeartAssistTM is expected to reduce variability which in turn can allow reproducible measurements without repetitive and tedious tasks. Considering the increasing burden of cardiovascular disease and the parallel growth in
demand for echocardiographic studies, fully automated quantitative echocardiographic evaluation can be extremely advantageous in reducing workload for the examiner and making echocardiographic laboratory sustainable.