Deployment and Evaluation of Artificial Intelligence Software for Electrocardiogram Analysis and Management in Primary Care

Not Applicable

Not yet recruiting

• Conditions: Primary Care Provider; Structural Heart Disease

• Registration Number: NCT06637293
• Lead Sponsor: Montreal Heart Institute

Brief Summary

The DAISEA-ECG project aims to improve the diagnosis of heart diseases in primary care through the DeepECG platform, which combines ECG-AI and ECHONeXT algorithms. This study uses a stepped wedge design, where each Family Medicine Group acts as its own control. The FMGs will gradually transition from the control period (without AI recommendations) to the intervention period (with AI recommendations activated) in a randomized sequence.

The primary objective is to compare the sensitivity of family physicians in detecting cardiac pathologies, with and without the assistance of the DeepECG platform. Sensitivity is defined as the proportion of patients correctly referred to cardiology or for transthoracic echocardiography (TTE) among those who indeed required cardiovascular evaluation, as confirmed by an independent adjudication committee.

Detailed Description

Mathematically, sensitivity is calculated as True Positive / (True Positive + False Negative), where True Positive represents correctly referred patients and false negatives represents patients who should have been referred but were not.

The secondary objectives include determining the rate of cardiovascular evaluation referrals before and after the intervention (implementation of the DeepECG platform), the individual characteristics of the intervention (PPV, NPV, and specificity), as well as evaluating the feasibility of implementing AI-based automatic ECG interpretation in primary care through surveys of family physicians and cardiologists.

PPV: Positive predictive value NPV: Negative predictive value

Study Timeline

• Status Verified: 2024-10
• Study First Submitted: 2024-10-09
• Study First Submitted QC: 2024-10-09
• Last Update Submitted: 2024-10-09
• Study First Posted: 2024-10-11
• Last Update Posted: 2024-10-11
• Study Start: 2024-12-01
• Primary Completion: 2026-01-01
• Study Completion: 2026-01-01

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: All
• Target Recruitment: 2000

Inclusion Criteria

Family Physicians or Nurse Practitioners

Family physicians or nurse practitioners (NPs) practicing in one of the participating FMGs.

Family physicians who have given their free and informed consent. Patients

Adult patients (18 years or older). Patients without follow-up in cardiology or internal medicine for cardiovascular issues (arrhythmia, heart failure, myocardial infarction, atherosclerotic coronary artery disease, valvular heart disease) or those who had a negative investigation in the past with no additional follow-up.

ECG

Any 12-lead ECG performed with the MUSE GE 360 machine. ECG of adequate technical quality for interpretation (otherwise, it will be automatically rejected by the platform).

Exclusion Criteria

• Family Physicians or Nurse Practitioners

Family physicians practicing exclusively in pediatrics (patients under 18 years old).

Family physicians unable to follow the project guidelines.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Primary Outcome Measures

Name	Time	Method
sensitivity of cardiology referrals	18 months	Compare the sensitivity of cardiology referrals made by family physicians and nurse practitioners before and after the activation of AI-assisted diagnostics and recommendations from the DeepECG platform.

Secondary Outcome Measures

Name	Time	Method
specificity, negative predictive value, and positive predictive value of cardiology referrals	18 months	Compare the specificity, negative predictive value, and positive predictive value of cardiology referrals made by family physicians and nurse practitioners before and after the activation of AI-assisted diagnostics and recommendations.

Trial Locations

Locations (1)

Montreal Heart Institute; 🇨🇦 Montreal, Quebec, Canada