Key result
ECG Buddy outperforms ChatGPT-4o in diagnosing MI from ECG images, achieving ~99% AUC.
Why the study?
Whether multimodal large language models analyze waveform patterns or rely on text cues remained unclear, underscoring the need for direct comparisons with dedicated ECG artificial intelligence tools for diagnosing myocardial infarction.
Does ChatGPT-4o accurately diagnose myocardial infarction from ECG images compared to a dedicated AI tool (ECG Buddy)?
Observational (n=928)
No
Does ChatGPT-4o accurately diagnose myocardial infarction from ECG images compared to a dedicated AI tool (ECG Buddy)?
Absolute Event Rate: 98.8% vs 57.34%
p-value: p=<0.001
General-purpose multimodal LLMs like ChatGPT-4o currently underperform significantly compared to dedicated ECG AI tools for diagnosing myocardial infarction from ECG images.
Clinicians should avoid ChatGPT-4o for ECG-based MI diagnosis; challenges readiness of general-purpose LLMs for specialized cardiac imaging.
Background Accurate and timely electrocardiogram (ECG) interpretation is critical for diagnosing myocardial infarction (MI) in emergency settings. Recent advances in multimodal Large Language Models (LLMs), such as Chat Generative Pre-trained Transformer (ChatGPT), have shown promise in clinical interpretation for medical imaging. However, whether these models analyze waveform patterns or simply rely on text cues remains unclear, underscoring the need for direct comparisons with dedicated ECG artificial intelligence (AI) tools. Methods This retrospective study evaluated and compared AI models for classifying MI using a publicly available 12-lead ECG dataset from Pakistan, categorizing cases into MI-positive (239 images) and MI-negative (689 images). ChatGPT (GPT-4o, version 2024-11-20) was queried with five MI confidence options, whereas ECG Buddy for Windows analyzed the images based on ST- elevation MI, acute coronary syndrome, and myocardial injury biomarkers. Results Among 928 ECG recordings (25.8% MI-positive), ChatGPT achieved an accuracy of 65.95% (95% confidence interval [CI]: 62.80–69.00), area under the curve (AUC) of 57.34% (95% CI: 53.44–61.24), sensitivity of 36.40% (95% CI: 30.30–42.85), and specificity of 76.20% (95% CI: 72.84–79.33). However, ECG Buddy reached an accuracy of 96.98% (95% CI: 95.67–97.99), AUC of 98.8% (95% CI: 98.3–99.43), sensitivity of 96.65% (95% CI: 93.51–98.54), and specificity of 97.10% (95% CI: 95.55–98.22). DeLong’s test confirmed that ECG Buddy significantly outperformed ChatGPT (all P < .001). In an error analysis of 40 cases, ChatGPT provided clinically plausible explanations in only 7.5% of cases, whereas 35% were partially correct, 40% were completely incorrect, and 17.5% received no meaningful explanation. Conclusion LLMs such as ChatGPT underperform relative to specialized tools such as ECG Buddy in ECG image-based MI diagnosis. Further training may improve ChatGPT; however, domain- specific AI remains essential for clinical accuracy. The high performance of ECG Buddy underscores the importance of specialized models for achieving reliable and robust diagnostic outcomes.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2025) conducted an observational in Myocardial Infarction (n=928). ECG Buddy vs. ChatGPT-4o was evaluated on Area under the curve (AUC) for myocardial infarction classification (95% CI 98.3-99.43, p=<0.001). ECG Buddy significantly outperformed ChatGPT-4o in diagnosing myocardial infarction from ECG images, achieving an AUC of 98.8% compared to 57.34% (p < 0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: