Key result
ChatGPT 4.0 predicts MACE with ~0.78 AUROC using sequential troponins but misclassifies several as non-urgent.
Why the study?
Chest pain is a frequent emergency department presentation, but accurately assessing the risk of major adverse cardiac events remains challenging.
Does ChatGPT 4.0 accurately predict MACE in patients presenting to the emergency department with chest pain?
Observational (n=178)
No
Does ChatGPT 4.0 accurately predict MACE in patients presenting to the emergency department with chest pain?
Effect estimate: AUROC 0.776 (95% CI 0.681-0.871)
p-value: p=0.039
ChatGPT 4.0 demonstrated potential in predicting MACE in ED chest pain patients, but its misclassification of some MACE cases as non-urgent indicates it is not yet safe for routine clinical implementation.
Chest pain is a frequent cause of emergency department (ED) visits, yet accurately assessing the risk of major adverse cardiac events (MACE) remains challenging. This study evaluated the potential of ChatGPT 4.0 as a clinical decision-support tool for predicting MACE in patients with chest pain. We conducted a prospective observational study at the Rovereto Hospital ED from March to August 2024, analyzing 178 patients. ChatGPT received patient data in three sequential phases: initial clinical history and ECG, first troponin test, and second troponin test. Its predictive performance improved with additional data, with the area under the receiver operating characteristic curve (AUROC) increasing from 0.699 in the first phase to 0.776 after the second troponin test (p=0.039). However, ChatGPT misclassified several MACE cases as non-urgent, raising concerns about sensitivity and risk stratification. While ChatGPT demonstrated potential in identifying MACE cases, its current performance does not support routine ED implementation. Further refinements in AI-based models are needed to improve real-time risk assessment and ensure safer, more reliable clinical integration.
No takes yet. Share an insight, caveat, or question.
Malalan et al. (2025) conducted an observational in Chest pain (n=178). ChatGPT 4.0 vs. Actual clinical outcomes (MACE occurrence) was evaluated on Predictive accuracy for major adverse cardiac events (MACE) within 3 months (AUROC 0.776, 95% CI 0.681-0.871, p=0.039). ChatGPT 4.0 predicted major adverse cardiac events with an AUROC of 0.776 after incorporating sequential troponin data, though it misclassified several cases as non-urgent.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: