The Accuracy of Artificial Intelligence-Based Models Applied to 12-Lead Electrocardiograms for the Diagnosis of Acute Coronary Syndrome: A Systematic Review
Bibliographic record
Abstract
Objectives: 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). Methods: 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). Results: 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. Conclusion: 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.007 | 0.004 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.003 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".