Key result
Ordinal AI-ECG model matches hs-cTnT discrimination for occlusion MI with ~0.89 AUC.
Why the study?
The occlusion myocardial infarction (OMI) paradigm shifts focus from rigid ECG criteria to underlying acute coronary occlusion requiring urgent reperfusion. However, a direct comparison of an ordinal AI-ECG model against an ordinal troponin-based logistic regression model for OMI/NOMI detection in unselected emergency department patients at presentation was lacking.
Does an ordinal AI-ECG model improve the diagnosis of occlusion myocardial infarction compared to an ordinal hs-cTnT logistic regression model in unselected emergency department patients presenting with chest pain?
Observational (n=4,728)
Yes
Does an ordinal AI-ECG model improve the diagnosis of occlusion myocardial infarction compared to an ordinal hs-cTnT logistic regression model in unselected emergency department patients presenting with chest pain?
In unselected emergency department patients with chest pain, a fine-tuned ordinal AI-ECG model demonstrates strong overall discrimination for occlusion myocardial infarction comparable to hs-cTnT logistic regression at a 0.7 PPV threshold, but performs worse in the NSTEMI-OMI subgroup.
Answers are grounded in this paper and cite their sources.
AI-ECG yields similar OMI detection to LR-Trop at PPV 0.7 threshold; leaves open incremental value in suspected ACS.
Background In the occlusion myocardial infarction (OMI) paradigm, the focus shifts from rigid electrocardiogram (ECG) criteria to the underlying pathology of acute coronary occlusion requiring urgent reperfusion. Direct comparison of an ordinal AI-ECG model against an ordinal troponin-based logistic regression model for OMI/NOMI detection in unselected emergency department (ED) patients at presentation is lacking. Methods This study fine-tuned an ordinal AI-ECG model from a foundation model (pre-trained on pooled cohorts n=10.7 million), with preliminary fine-tuning on retrospective cohorts (n=338’580) using ICD-10 codes and final fine-tuning on pooled cohorts (n=13’879) with ordinal OMI/NOMI outcomes. An ordinal logistic regression model using hs-cTnT (LR-Trop) as predictor was fitted in parallel. Models were externally validated and compared in a prospective multicenter study of unselected ED patients with chest pain (validation n=4728), with ECG and hs-cTnT at presentation. Diagnoses were centrally adjudicated. Primary outcome was Occlusion Myocardial infarction (angiographic culprit with TIMI 0–1, or TIMI 2–3 with peak hs-cTnT ≥1000 ng/L). TIMI flow was assessed by two cardiologists. Performance was evaluated by receiver operating characteristic curves (ROC) and precision-recall curves (PR). A sensitivity analysis was performed in the combined group of patients with NSTEMI-OMI and those without MI. Results Among 4728 patients, occlusion myocardial infarction (OMI) was the final diagnosis in 300 (6.3%), of whom 122 (41%) had STEMI. Model discrimination for OMI was high (AI-ECG AUC 0.89 [0.87-0.90] vs LR-Trop 0.93 [0.92-0.95]). For a threshold with PPV of 0.7, the proportion of patients with OMI identified was similar (AI-ECG 0.35 [0.30-0.41] vs LR-Trop 0.41 [0.35-0.47], p >0.05) (Figures A and C). In patients with NSTEMI-OMI or no MI, model discrimination dropped for AI-ECG while it remained high for LR-Trop (AI-ECG AUC 0.84 [0.81-0.87] vs LR-Trop 0.93 [0.91-0.95]). For a threshold with PPV of 0.7, the proportion of patients with NSTEMI-OMI identified was significantly lower for AI-ECG compared to LR-Trop (0.07 [0.04-0.11] vs 0.26 [0.20-0.33], p < 0.05) (Figures B and D). Conclusions & clinical implications In this prospective multicenter validation of unselected emergency department patients with chest pain, the fine-tuned ordinal AI-ECG model demonstrated strong discrimination for OMI and identified a comparable proportion of cases to the hs-cTnT-based LR-Trop. While the performance of AI-ECG was high for OMI, it was inferior to ordinal logistic regression with cardiac troponin testing in patients with NSTEMI-OMI, highlighting the need for optimised models in this vulnerable population.
No takes yet. Share an insight, caveat, or question.
Strebel et al. (2026) conducted an observational in Occlusion Myocardial Infarction (OMI) in patients presenting with chest pain (n=4,728). Ordinal AI-ECG model vs. Ordinal hs-cTnT logistic regression model (LR-Trop) was evaluated on Occlusion Myocardial Infarction (angiographic culprit with TIMI 0-1, or TIMI 2-3 with peak hs-cTnT >=1000 ng/L) (AUC 0.89 vs 0.93, 95% CI 0.87-0.90, p=>0.05). An ordinal AI-ECG model showed high discrimination for OMI (AUC 0.89 vs 0.93 for hs-cTnT model) and identified a similar proportion of OMI cases at 0.7 PPV (35% vs 41%, p>0.05).
Synapse has enriched 10 related papers. Consider them for comparative context: