Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCM
Circulation: Cardiovascular Imaging · 2026
DOI: 10.1161/circimaging.126.019956 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Circulation: Cardiovascular Imaging, 2026. Verfasst von Owen R Crystal und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiovascular Medicine (O.R.C., J.M.F., I.G.S., C.A., C.V.E., L.C., R.A., S.J.L.), Mayo Clinic, Phoenix, AZ. Hauptthemen laut MEDLINE: Cardiomyopathy, Hypertrophic, Ventricular Outflow Obstruction, Left, Echocardiography, Doppler, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: Accurate assessment of left ventricular outflow tract (LVOT) gradients is critical for hypertrophic cardiomyopathy management, yet Doppler-based measurements are technically demanding and require expertise. The objective of this work was to develop a multi-view deep learning model capable of classifying LVOT obstruction (>20 mm Hg) using routine 2-dimensional echocardiographic windows without reliance on Doppler imaging. METHODS: We trained and externally validated a cross-attention-based video-to-video fusion framework that integrated EchoPrime-derived video representations from 3 standard transthoracic echocardiographic views to classify LVOT gradients. RESULTS: Training was performed on a derivation cohort (N=1833) from a tertiary care system in the United States, with model performance evaluated on an internally held-out test set (N=275) and a Korean external validation cohort (N=46). Single-view baselines showed limited discrimination (external area under the receiver operating curves, 0.47–0.70). Conversely, the domain-specific foundational model (EchoPrime) achieved superior single-view performance (area under the receiver operating curves, 0.75–0.80 internal; 0.79–0.83 external), highlighting the importance of echo-specific pretraining and temporal modeling. The proposed multi-view fusion further enhanced predictive performance, with the late fusion model reaching an area under the receiver operating curve of 0.84 on the external cohort with significant population-shift. CONCLUSIONS: These results suggest LVOT physiology is encoded in routine 2-dimensional imaging and can be leveraged for clinically relevant gradient classification without Doppler input. The proposed artificial intelligence-guided strategy demonstrates substantial cost savings compared with the screen-all approach. By integrating complementary spatial-temporal information across multiple views, our approach generalizes robustly across populations and may enable real-time decision support, extend LVOT assessment to portable or resource-limited settings, and complement Doppler-based evaluation for longitudinal hypertrophic cardiomyopathy management.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiovascular Medicine (O.R.C., J.M.F., I.G.S., C.A., C.V.E., L.C., R.A., S.J.L.), Mayo Clinic, Phoenix, AZ.
- Division of Cardiology, Department of Internal Medicine, International St. Mary's Hospital, Catholic Kwandong University College of Medicine, Incheon, South Korea (H.B.P.).
- Department of Cardiology, Incheon St. Mary's Hospital, The Catholic University of Korea, Seoul, South Korea (K.A.K.).
- Department of Radiology (I.B.), Mayo Clinic, Phoenix, AZ.
ORCID-Profile: Owen R Crystal, Juan M Farina, Isabel G Scalia, Chadi Ayoub, Cecilia C Villa Etchegoyen, Laurève Chollet, Hyung Bok Park, Kyung An Kim, Reza Arsanjani, Imon Banerjee
Zitieren
APA
Crystal, O. R., Farina, J. M., Scalia, I. G., Ayoub, C., Villa Etchegoyen, C. C., Chollet, L., Park, H. B., Kim, K. A., Arsanjani, R., Lester, S. J., & Banerjee, I. (2026). Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCM. Circulation: Cardiovascular Imaging. https://doi.org/10.1161/circimaging.126.019956
Vancouver
Crystal OR, Farina JM, Scalia IG, Ayoub C, Villa Etchegoyen CC, Chollet L, et al. Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCM. Circulation: Cardiovascular Imaging. 2026. doi:10.1161/circimaging.126.019956
BibTeX
@article{Crystal2026,
author = {Crystal, Owen R and Farina, Juan M and Scalia, Isabel G and Ayoub, Chadi and Villa Etchegoyen, Cecilia C and Chollet, Laurève and Park, Hyung Bok and Kim, Kyung An and Arsanjani, Reza and Lester, Steven J and Banerjee, Imon},
title = {Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCM},
journal = {Circulation: Cardiovascular Imaging},
year = {2026},
doi = {10.1161/circimaging.126.019956}
}
EUVIMED