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

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

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.