Artificial Intelligence-guided Detection of Under-recognized Cardiomyopathies on Point-of-care Cardiac Ultrasound: a Multi-center Study

Overview

Journal medRxiv

Date 2024 Apr 1

PMID 38559021

Authors

Evangelos K Oikonomou

Akhil Vaid

Gregory Holste

Andreas Coppi

Robert L McNamara

Cristiana Baloescu

Harlan M Krumholz

Zhangyang Wang

Donald J Apakama

Girish N Nadkarni

Rohan Khera

Affiliations

Soon will be listed here.

Abstract

Background: Point-of-care ultrasonography (POCUS) enables cardiac imaging at the bedside and in communities but is limited by abbreviated protocols and variation in quality. We developed and tested artificial intelligence (AI) models to automate the detection of underdiagnosed cardiomyopathies from cardiac POCUS.

Methods: In a development set of 290,245 transthoracic echocardiographic videos across the Yale-New Haven Health System (YNHHS), we used augmentation approaches and a customized loss function weighted for view quality to derive a POCUS-adapted, multi-label, video-based convolutional neural network (CNN) that discriminates HCM (hypertrophic cardiomyopathy) and ATTR-CM (transthyretin amyloid cardiomyopathy) from controls without known disease. We evaluated the final model across independent, internal and external, retrospective cohorts of individuals who underwent cardiac POCUS across YNHHS and Mount Sinai Health System (MSHS) emergency departments (EDs) (2011-2024) to prioritize key views and validate the diagnostic and prognostic performance of single-view screening protocols.

Findings: We identified 33,127 patients (median age 61 [IQR: 45-75] years, n=17,276 [52·2%] female) at YNHHS and 5,624 (57 [IQR: 39-71] years, n=1,953 [34·7%] female) at MSHS with 78,054 and 13,796 eligible cardiac POCUS videos, respectively. An AI-enabled single-view screening approach successfully discriminated HCM (AUROC of 0·90 [YNHHS] & 0·89 [MSHS]) and ATTR-CM (YNHHS: AUROC of 0·92 [YNHHS] & 0·99 [MSHS]). In YNHHS, 40 (58·0%) HCM and 23 (47·9%) ATTR-CM cases had a positive screen at median of 2·1 [IQR: 0·9-4·5] and 1·9 [IQR: 1·0-3·4] years before clinical diagnosis. Moreover, among 24,448 participants without known cardiomyopathy followed over 2·2 [IQR: 1·1-5·8] years, AI-POCUS probabilities in the highest (vs lowest) quintile for HCM and ATTR-CM conferred a 15% (adj.HR 1·15 [95%CI: 1·02-1·29]) and 39% (adj.HR 1·39 [95%CI: 1·22-1·59]) higher age- and sex-adjusted mortality risk, respectively.

Interpretation: We developed and validated an AI framework that enables scalable, opportunistic screening of treatable cardiomyopathies wherever POCUS is used.

Funding: National Heart, Lung and Blood Institute, Doris Duke Charitable Foundation, BridgeBio.

References

Perego S, Zambon A, Nistri S, Bruni A, Motta S, Cavalieri doro L . Prevalence, clinical correlates, and burden of undiagnosed aortic stenosis in older patients: a prospective study in a non-cardiologic acute hospital ward. Aging Clin Exp Res. 2020; 32(8):1533-1540. DOI: 10.1007/s40520-020-01471-w. View

Rajkomar A, Hardt M, Howell M, Corrado G, Chin M . Ensuring Fairness in Machine Learning to Advance Health Equity. Ann Intern Med. 2018; 169(12):866-872. PMC: 6594166. DOI: 10.7326/M18-1990. View

Goto S, Solanki D, John J, Yagi R, Homilius M, Ichihara G . Multinational Federated Learning Approach to Train ECG and Echocardiogram Models for Hypertrophic Cardiomyopathy Detection. Circulation. 2022; 146(10):755-769. PMC: 9439630. DOI: 10.1161/CIRCULATIONAHA.121.058696. View

Akerman A, Porumb M, Scott C, Beqiri A, Chartsias A, Ryu A . Automated Echocardiographic Detection of Heart Failure With Preserved Ejection Fraction Using Artificial Intelligence. JACC Adv. 2024; 2(6):100452. PMC: 11198161. DOI: 10.1016/j.jacadv.2023.100452. View

DArcy J, Coffey S, Loudon M, Kennedy A, Pearson-Stuttard J, Birks J . Large-scale community echocardiographic screening reveals a major burden of undiagnosed valvular heart disease in older people: the OxVALVE Population Cohort Study. Eur Heart J. 2016; 37(47):3515-3522. PMC: 5216199. DOI: 10.1093/eurheartj/ehw229. View

Alexander K, Orav J, Singh A, Jacob S, Menon A, Padera R . Geographic Disparities in Reported US Amyloidosis Mortality From 1979 to 2015: Potential Underdetection of Cardiac Amyloidosis. JAMA Cardiol. 2018; 3(9):865-870. PMC: 6233639. DOI: 10.1001/jamacardio.2018.2093. View

Obi C, Mostertz W, Griffin J, Judge D . ATTR Epidemiology, Genetics, and Prognostic Factors. Methodist Debakey Cardiovasc J. 2022; 18(2):17-26. PMC: 8932385. DOI: 10.14797/mdcvj.1066. View

Dorbala S, Ando Y, Bokhari S, Dispenzieri A, Falk R, Ferrari V . ASNC/AHA/ASE/EANM/HFSA/ISA/SCMR/SNMMI Expert Consensus Recommendations for Multimodality Imaging in Cardiac Amyloidosis: Part 1 of 2-Evidence Base and Standardized Methods of Imaging. Circ Cardiovasc Imaging. 2021; 14(7):e000029. DOI: 10.1161/HCI.0000000000000029. View

Ouyang D, He B, Ghorbani A, Yuan N, Ebinger J, Langlotz C . Video-based AI for beat-to-beat assessment of cardiac function. Nature. 2020; 580(7802):252-256. PMC: 8979576. DOI: 10.1038/s41586-020-2145-8. View

10.

Oikonomou E, Holste G, Yuan N, Coppi A, McNamara R, Haynes N . A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression. JAMA Cardiol. 2024; 9(6):534-544. PMC: 10999005. DOI: 10.1001/jamacardio.2024.0595. View

11.

Baumgartner Chair H, Hung Co-Chair J, Bermejo J, Chambers J, Edvardsen T, Goldstein S . Recommendations on the echocardiographic assessment of aortic valve stenosis: a focused update from the European Association of Cardiovascular Imaging and the American Society of Echocardiography. Eur Heart J Cardiovasc Imaging. 2017; 18(3):254-275. DOI: 10.1093/ehjci/jew335. View

12.

Kittleson M, Ruberg F, Ambardekar A, Brannagan T, Cheng R, Clarke J . 2023 ACC Expert Consensus Decision Pathway on Comprehensive Multidisciplinary Care for the Patient With Cardiac Amyloidosis: A Report of the American College of Cardiology Solution Set Oversight Committee. J Am Coll Cardiol. 2023; 81(11):1076-1126. DOI: 10.1016/j.jacc.2022.11.022. View

13.

Krishna H, Desai K, Slostad B, Bhayani S, Arnold J, Ouwerkerk W . Fully Automated Artificial Intelligence Assessment of Aortic Stenosis by Echocardiography. J Am Soc Echocardiogr. 2023; 36(7):769-777. DOI: 10.1016/j.echo.2023.03.008. View

14.

Holste G, Oikonomou E, Mortazavi B, Coppi A, Faridi K, Miller E . Severe aortic stenosis detection by deep learning applied to echocardiography. Eur Heart J. 2023; 44(43):4592-4604. PMC: 11004929. DOI: 10.1093/eurheartj/ehad456. View

15.

Gonzalez-Lopez E, Gallego-Delgado M, Guzzo-Merello G, de Haro-Del Moral F, Cobo-Marcos M, Robles C . Wild-type transthyretin amyloidosis as a cause of heart failure with preserved ejection fraction. Eur Heart J. 2015; 36(38):2585-94. DOI: 10.1093/eurheartj/ehv338. View

16.

Duffy G, Cheng P, Yuan N, He B, Kwan A, Shun-Shin M . High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep Learning. JAMA Cardiol. 2022; 7(4):386-395. PMC: 9008505. DOI: 10.1001/jamacardio.2021.6059. View

17.

Eberly L, Day S, Ashley E, Jacoby D, Jefferies J, Colan S . Association of Race With Disease Expression and Clinical Outcomes Among Patients With Hypertrophic Cardiomyopathy. JAMA Cardiol. 2019; 5(1):83-91. PMC: 6902181. DOI: 10.1001/jamacardio.2019.4638. View

18.

Goto S, Mahara K, Beussink-Nelson L, Ikura H, Katsumata Y, Endo J . Artificial intelligence-enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms. Nat Commun. 2021; 12(1):2726. PMC: 8113484. DOI: 10.1038/s41467-021-22877-8. View

19.

Narang A, Bae R, Hong H, Thomas Y, Surette S, Cadieu C . Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use. JAMA Cardiol. 2021; 6(6):624-632. PMC: 8204203. DOI: 10.1001/jamacardio.2021.0185. View

20.

Hswen Y, Voelker R . New AI Tools Must Have Health Equity in Their DNA. JAMA. 2023; 330(17):1604-1607. DOI: 10.1001/jama.2023.19293. View