Analysis of ECGio to Predict Coronary Stenosis Against a Mixed Reference Standard

NCT07375810 | Not Yet Recruiting FDA Device

• 1 other identifier: HIO0004A
• Study Type: observational
• Target: 978
• Locations: 1 country
• Sites: 2

Brief Summary

The study objective is to evaluate the effectiveness of the ECGio algorithm in predicting clinically significant coronary artery disease . ECGio's diagnostic performance during the trial will be compared against an objective performance ¬criteria using a mixed reference standard of quantitative coronary angiography and quantitative coronary computed tomography angiography in patients a general adult population under suspicion of coronary artery disease.

Conditions

Coronary Artery Disease (CAD)

Keywords

Artificial Intelligence; Electrocardiogram; Coronary Artery Disease

Outcome Measures

Primary Outcomes (1)

• Sensitivity & Specificity

  The lower 95% bound of ECGio's sensitivity and specificity in patients who underwent invasive angiography or computed tomography angiography (Co-primary endpoints)

  Within 30 days of enrollment

Secondary Outcomes (3)

• Sensitivity & Specificity

  For the first 300 patients referred to invasive angiography through study completion, an average of 90 days

• Demographic Performance

  For patients in the 30 days following computed tomography angiography

• Angiographic Stenosis Prediction

  For the first 300 patients referred to invasive angiography through study completion, an average of 90 days

Study Arms (3)

CT Angiogram

This is the Cohort which received only Computed Tomography Angiography as a part of the study

Device: AI-ECG Analysis

Invasive Angiography

This is the Cohort which received both Computed Tomography Angiography and Invasive Angiography as a part of the study

Device: AI-ECG Analysis

Enrollment Period 2

This Cohort is the continuation of enrollment of invasive angiogram patients beyond the completion of the primary endpoint

Device: AI-ECG Analysis

Interventions

AI-ECG Analysis DEVICE

The AI-Analysis done on the ECGs in a retrospective fashion

CT Angiogram; Enrollment Period 2; Invasive Angiography

Eligibility Criteria

• Age: 18 Years - 89 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population will be made up of all-comers to Coronary Computed Tomography Angiography from each site taking up to the first 250, consecutive patients recruited for the analysis.

You may qualify if:

• Patients 18 years of age or older at time of data collection.
• Patients with medical records stored in a digitized format.
• Patients under suspicion of coronary artery disease (both suspicion of significant coronary artery disease as well as to rule out significant CAD) who present to the site with an electrocardiogram recorded up to 30 days prior to Coronary Computed Tomography Angiography.

You may not qualify if:

• Patients with acute coronary syndrome.
• Patients who previously underwent coronary artery bypass grafting.
• Patients whose electrocardiogram tracing has extreme noise or artifact to the extent that it would be recommended to redo the tracing.
• Patients with prior percutaneous coronary intervention resulting in stenting.
• Unanalyzable invasive coronary angiogram.
• Unanalyzable Coronary Computed Tomography Angiography.
• Unanalyzable electrocardiogram signal.
• Incomplete invasive coronary angiogram (e.g., only the right coronary artery was injected and visualized).
• Patient core lab analyzed Coronary Computed Tomography Angiography showed ≥ 50% blockage in any vessel but patient was not referred to invasive coronary angiogram.

Sponsors & Collaborators

• Heart Input Output Inc: lead

Study Sites (2)

Medstar Washington Hospital Center

Washington D.C., District of Columbia, 20010, United States

Location

Cena Research Institute

Houston, Texas, 77055, United States

Location

Related Publications (1)

• Leasure M, Jain U, Butchy A, Otten J, Covalesky VA, McCormick D, Mintz GS. Deep Learning Algorithm Predicts Angiographic Coronary Artery Disease in Stable Patients Using Only a Standard 12-Lead Electrocardiogram. Can J Cardiol. 2021 Nov;37(11):1715-1724. doi: 10.1016/j.cjca.2021.08.005. Epub 2021 Aug 20.

  PMID: 34419615 BACKGROUND

MeSH Terms

Conditions

Coronary Artery Disease

Condition Hierarchy (Ancestors)

Coronary Disease; Myocardial Ischemia; Heart Diseases; Cardiovascular Diseases; Arteriosclerosis; Arterial Occlusive Diseases; Vascular Diseases

Study Officials

• Gary S Mintz

  CardioVascular Research Foundation

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Michael Leasure

CONTACT

6104517343; Michael.Leasure@heartio.ai

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: January 21, 2026
• First Posted: January 29, 2026
• Study Start: April 1, 2026
• Primary Completion (Estimated): July 1, 2026
• Study Completion (Estimated): September 1, 2026
• Last Updated: March 30, 2026

Record last verified: 2026-03

Data Sharing

• IPD Sharing: Will not share

Locations

US (2)