Identification and risk stratification of coronary disease by artificial intelligence-enabled ECGResearch in context

Samir Awasthi; Nikhil Sachdeva; Yash Gupta; Ausath G. Anto; Shahir Asfahan; Ruben Abbou; Sairam Bade; Sanyam Sood; Lars Hegstrom; Nirupama Vellanki; Heather M. Alger; Melwin Babu; Jose R. Medina-Inojosa; Robert B. McCully; Amir Lerman; Mark Stampehl; Rakesh Barve; Zachi I. Attia; Paul A. Friedman; Venky Soundararajan; Francisco Lopez-Jimenez

EClinicalMedicine (Nov 2023)

Identification and risk stratification of coronary disease by artificial intelligence-enabled ECGResearch in context

Samir Awasthi,
Nikhil Sachdeva,
Yash Gupta,
Ausath G. Anto,
Shahir Asfahan,
Ruben Abbou,
Sairam Bade,
Sanyam Sood,
Lars Hegstrom,
Nirupama Vellanki,
Heather M. Alger,
Melwin Babu,
Jose R. Medina-Inojosa,
Robert B. McCully,
Amir Lerman,
Mark Stampehl,
Rakesh Barve,
Zachi I. Attia,
Paul A. Friedman,
Venky Soundararajan,
Francisco Lopez-Jimenez

Affiliations

Samir Awasthi: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Nikhil Sachdeva: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Yash Gupta: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Ausath G. Anto: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Shahir Asfahan: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Ruben Abbou: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Sairam Bade: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Sanyam Sood: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Lars Hegstrom: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Nirupama Vellanki: nference, Inc, One Main Street, Cambridge, MA, USA; Beth Israel Deaconess Medical Center, Boston, MA, USA
Heather M. Alger: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Melwin Babu: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Jose R. Medina-Inojosa: Mayo Clinic, Rochester, MN, USA
Robert B. McCully: Mayo Clinic, Rochester, MN, USA
Amir Lerman: Mayo Clinic, Rochester, MN, USA
Mark Stampehl: Novartis Pharmaceuticals Corporation, East Hanover, NJ, USA
Rakesh Barve: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Zachi I. Attia: Mayo Clinic, Rochester, MN, USA
Paul A. Friedman: Mayo Clinic, Rochester, MN, USA
Venky Soundararajan: Anumana, Inc, One Main Street, Cambridge, MA, USA; nference, Inc, One Main Street, Cambridge, MA, USA
Francisco Lopez-Jimenez: Mayo Clinic, Rochester, MN, USA; Corresponding author.

Journal volume & issue: Vol. 65
p. 102259

Abstract

Read online

Summary: Background: Atherosclerotic cardiovascular disease (ASCVD) is the leading cause of death worldwide, driven primarily by coronary artery disease (CAD). ASCVD risk estimators such as the pooled cohort equations (PCE) facilitate risk stratification and primary prevention of ASCVD but their accuracy is still suboptimal. Methods: Using deep electronic health record data from 7,116,209 patients seen at 70+ hospitals and clinics across 5 states in the USA, we developed an artificial intelligence-based electrocardiogram analysis tool (ECG-AI) to detect CAD and assessed the additive value of ECG-AI-based ASCVD risk stratification to the PCE. We created independent ECG-AI models using separate neural networks including subjects without known history of ASCVD, to identify coronary artery calcium (CAC) score ≥300 Agatston units by computed tomography, obstructive CAD by angiography or procedural intervention, and regional left ventricular akinesis in ≥1 segment by echocardiogram, as a reflection of possible prior myocardial infarction (MI). These were used to assess the utility of ECG-AI-based ASCVD risk stratification in a retrospective observational study consisting of patients with PCE scores and no prior ASCVD. The study period covered all available digitized EHR data, with the first available ECG in 1987 and the last in February 2023. Findings: ECG-AI for identifying CAC ≥300, obstructive CAD, and regional akinesis achieved area under the receiver operating characteristic (AUROC) values of 0.88, 0.85, and 0.94, respectively. An ensembled ECG-AI identified 3, 5, and 10-year risk for acute coronary events and mortality independently and additively to PCE. Hazard ratios for acute coronary events over 3-years in patients without ASCVD that tested positive on 1, 2, or 3 versus 0 disease-specific ECG-AI models at cohort entry were 2.41 (2.14–2.71), 4.23 (3.74–4.78), and 11.75 (10.2–13.52), respectively. Similar stratification was observed in cohorts stratified by PCE or age. Interpretation: ECG-AI has potential to address unmet need for accessible risk stratification in patients in whom PCE under, over, or insufficiently estimates ASCVD risk, and in whom risk assessment over time periods shorter than 10 years is desired. Funding: Anumana.

Published in EClinicalMedicine

ISSN: 2589-5370 (Online)
Publisher: Elsevier
Country of publisher: United Kingdom
LCC subjects: Medicine: Medicine (General)
Website: https://www.thelancet.com/journals/eclinm/home

About the journal

Abstract

Keywords