JACC Adv. 2026 Jun;5(6 Pt 2):102801. doi: 10.1016/j.jacadv.2026.102801.
ABSTRACT
BACKGROUND: Hypertrophic cardiomyopathy (HCM) affects 20 million individuals globally, with increased risk of sudden death and heart failure. Although cardiac myosin inhibitors show great promise as disease-specific treatment, current indications are for obstructive HCM. Obstruction is not always well characterized by echocardiography. Artificial intelligence might assist in the improving the underdiagnosis of left ventricular outflow tract (LVOT) obstruction.
OBJECTIVES: The authors aimed to develop a deep learning model to detect LVOT obstruction from non-Doppler B-mode echocardiography.
METHODS: We identified 2,396 patients with LVOT obstruction and 6,177 control patients matched by age, sex, and septal thickness. LVOT obstruction was defined as the presence of an LVOT gradient or systolic anterior motion of the mitral valve on final echocardiography report. A deep learning model was trained on non-Doppler apical 4-chamber B-mode echocardiographic videos to detect the presence of outflow obstruction identified later in the same study by spectral Doppler. We evaluated our model on held-out test sets from Cedars-Sinai Medical Center, Stanford Healthcare, and Kaiser Permanente Northern California.
RESULTS: In a test set of 3,848 videos from Cedars-Sinai Medical Center, our model demonstrated strong performance, detecting LVOT obstruction with area under the receiver operating characteristic curve (AUC) of 0.858 (95% CI: 0.847-0.870). The model demonstrated generalizable performance in the Kaiser Permanente Northern California cohort with AUC of 0.817 (95% CI: 0.740-0.922) and Stanford Healthcare with AUC 0.836 (95% CI: 0.807-0.827). Performance was consistent across patient subgroups, including those with hyperdynamic left ventricular function, pre-existing valvular disease, and small left ventricular cavity size.
CONCLUSIONS: In this study, we developed an artificial intelligence model to detect LVOT obstruction from standard apical 4-chamber videos, highlighting patients who may benefit from more detailed cardiac workup for obstructive HCM.
PMID:42312785 | DOI:10.1016/j.jacadv.2026.102801