# The Accuracy of Artificial Intelligence-Based Models Applied to 12-Lead Electrocardiograms for the Diagnosis of Acute Coronary Syndrome: A Systematic Review

## TL;DR

This review assesses how well AI models can diagnose heart attacks using ECGs, finding high accuracy but also variability and transparency issues.

## Contribution

The study systematically evaluates AI diagnostic accuracy for acute coronary syndrome using 12-lead ECGs and compares it to clinician performance.

## Key findings

- AI models showed sensitivity ranging from 68% to 98% and specificity from 41% to 98% for diagnosing ACS.
- AI outperformed clinicians in sensitivity and PPV but had lower NPV in most studies.
- Only 3 out of 24 studies reported code availability, highlighting transparency challenges.

## Abstract

This systematic review aims to evaluate the diagnostic accuracy of artificial intelligence (AI) algorithms in acute coronary syndrome (ACS) detection using 12-lead electrocardiograms (ECGs).

Adhering to Preferred Reporting Items for Systematic Reviews guidelines, Ovid MEDLINE, Ovid Embase, Cochrane Central, and Cochrane Database of Systematic Reviews were searched up to June 15, 2023. Eligible studies involved adults with suspected ACS and employed AI for 12-lead ECG interpretation. The primary outcomes were sensitivity and specificity, with secondary outcomes including positive predictive value (PPV), negative predictive value (NPV), and accuracy. Risk of bias was evaluated using Prediction model Risk Of Bias Assessment Tool (PROBAST).

From 2051 records, 24 studies were included. The sensitivity of AI-based diagnosis for ACS among the 24 studies varied from 68% to 98%, and the specificity varied from 41% to 98%. For subgroup analysis of ST-elevated myocardial infarction/occlusion myocardial infarction, sensitivity ranged from 68% to 97% and specificity from 68% to 99%. AI models outperformed clinicians interpreting ECGs retrospectively without knowledge of outcomes in sensitivity (90% of studies) and PPV (100% of studies), whereas clinicians had better NPV (70% of studies). One study compared AI with real-time emergency department physician interpretations. Three studies reported code availability. Thirty-eight percentage of studies showed a high risk of bias, with 50% showing unclear risk, although applicability concerns were minimal.

AI models show high diagnostic accuracy for ACS using 12-lead ECGs, with potential to enhance early diagnosis. However, variability in performance, transparency challenges with limited code availability, a high risk of bias in some studies, and minimal real-time comparisons underscore the necessity for standardized reporting and open-access practices.