A Multimodality Video-Based AI Biomarker For Aortic Stenosis Development And Progression

Evangelos K Oikonomou; Gregory Holste; Neal Yuan; Andreas Coppi; Robert L McNamara; Norrisa Haynes; Amit N Vora; Eric J Velazquez; Fan Li; Venu Menon; Samir R Kapadia; Thomas M Gill; Girish N Nadkarni; Harlan M Krumholz; Zhangyang Wang; David Ouyang; Rohan Khera

doi:10.1101/2023.09.28.23296234

A Multimodality Video-Based AI Biomarker For Aortic Stenosis Development And Progression

medRxiv [Preprint]. 2024 Feb 29:2023.09.28.23296234. doi: 10.1101/2023.09.28.23296234.

Authors

Evangelos K Oikonomou¹, Gregory Holste^{1

2}, Neal Yuan^{3

4}, Andreas Coppi⁵, Robert L McNamara¹, Norrisa Haynes¹, Amit N Vora¹, Eric J Velazquez¹, Fan Li^{6

7}, Venu Menon⁸, Samir R Kapadia⁸, Thomas M Gill⁹, Girish N Nadkarni^{10

11}, Harlan M Krumholz^{1

5}, Zhangyang Wang², David Ouyang^{12

13}, Rohan Khera^{1

5

14

15

16}

Affiliations

¹ Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
² Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA.
³ Department of Medicine, University of California San Francisco, San Francisco, CA, USA.
⁴ Division of Cardiology, San Francisco Veterans Affairs Medical Center, San Francisco, CA, USA.
⁵ Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA.
⁶ Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA.
⁷ Center for Methods in Implementation and Prevention Science, Yale School of Public Health, New Haven, CT, USA.
⁸ Department of Cardiovascular Medicine, Heart and Vascular Institute, Cleveland Clinic Foundation, Cleveland, OH, USA.
⁹ Section of Geriatrics, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
¹⁰ The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
¹¹ Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
¹² Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
¹³ Division of Artificial Intelligence in Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
¹⁴ Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT.
¹⁵ Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT.
¹⁶ Associate Editor, JAMA.

Abstract

Importance: Aortic stenosis (AS) is a major public health challenge with a growing therapeutic landscape, but current biomarkers do not inform personalized screening and follow-up.

Objective: A video-based artificial intelligence (AI) biomarker (Digital AS Severity index [DASSi]) can detect severe AS using single-view long-axis echocardiography without Doppler. Here, we deploy DASSi to patients with no or mild/moderate AS at baseline to identify AS development and progression.

Design setting and participants: We defined two cohorts of patients without severe AS undergoing echocardiography in the Yale-New Haven Health System (YNHHS) (2015-2021, 4.1[IQR:2.4-5.4] follow-up years) and Cedars-Sinai Medical Center (CSMC) (2018-2019, 3.4[IQR:2.8-3.9] follow-up years). We further developed a novel computational pipeline for the cross-modality translation of DASSi into cardiac magnetic resonance (CMR) imaging in the UK Biobank (2.5[IQR:1.6-3.9] follow-up years). Analyses were performed between August 2023-February 2024.

Exposure: DASSi (range: 0-1) derived from AI applied to echocardiography and CMR videos.

Main outcomes and measures: Annualized change in peak aortic valve velocity (AV-V_max) and late (>6 months) aortic valve replacement (AVR).

Results: A total of 12,599 participants were included in the echocardiographic study (YNHHS: n=8,798, median age of 71 [IQR (interquartile range):60-80] years, 4250 [48.3%] women, and CSMC: n=3,801, 67 [IQR:54-78] years, 1685 [44.3%] women). Higher baseline DASSi was associated with faster progression in AV-V_max (per 0.1 DASSi increments: YNHHS: +0.033 m/s/year [95%CI:0.028-0.038], n=5,483, and CSMC: +0.082 m/s/year [0.053-0.111], n=1,292), with levels ≥ vs <0.2 linked to a 4-to-5-fold higher AVR risk (715 events in YNHHS; adj.HR 4.97 [95%CI: 2.71-5.82], 56 events in CSMC: 4.04 [0.92-17.7]), independent of age, sex, ethnicity/race, ejection fraction and AV-V_max. This was reproduced across 45,474 participants (median age 65 [IQR:59-71] years, 23,559 [51.8%] women) undergoing CMR in the UK Biobank (adj.HR 11.4 [95%CI:2.56-50.60] for DASSi ≥vs<0.2). Saliency maps and phenome-wide association studies supported links with traditional cardiovascular risk factors and diastolic dysfunction.

Conclusions and relevance: In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker is independently associated with AS development and progression, enabling opportunistic risk stratification across cardiovascular imaging modalities as well as potential application on handheld devices.

Keywords: aortic stenosis; artificial intelligence; computer vision; imaging; risk stratification.

Publication types

Preprint

Abstract

Publication types

Grants and funding