Background: Some authors advocate that ECGs with conventional computer algorithm (CCA) interpretations of “normal” need not be immediately reviewed. However, such ECGs may actually manifest findings of acute coronary occlusion myocardial infarction (OMI). We sought to determine if such cases can be detected by artificial intelligence (AI). Methods: We studied a retrospective series (2014–2024) of cases with ≥1 pre-angiography ECGs with a proven OMI outcome with a CCA ECG interpretation of “normal”. The OMI outcome was defined as (1) the diagnosis of acute type I MI, (2) an angiographic culprit with intervention, and (3) one of the following, (a) TIMI-0-2 flow, or (b) TIMI-3 or unknown flow, with high peak troponin or new wall abnormality. Each ECG as retrospectively interpreted by the PMcardio OMI AI ECG model. The primary analysis was the performance of AI in diagnosing "OMI" among these CCA “normal” ECGs. Results: Forty-two patients with OMI met the inclusion criteria. The first ECG was interpreted as “normal” by the CCA in 88% of cases; AI interpreted 81% as OMI and 86% as abnormal. Of the 78 total ECGs interpreted by the CCA, 73% were diagnosed as “normal”. Of this 73%, AI identified 81% as abnormal and 72% as OMI. Conclusion: The Conventional Computer Algorithm may interpret an ECG manifesting OMI as “normal”. AI not only recognized these as abnormal, but in 81% of patients, correctly recognized OMI on the first ECG and recognized 72% of all the CCA “normal” ECGs as OMI. It was rare for AI to diagnose a normal ECG for any OMI patient.

Background: Millimetric ST-segment elevation (STEMI) rules miss more than half of angiographic coronary occlusions. Re-casting acute infarction as Occlusion MI (OMI) versus Non-Occlusion MI (NOMI) and embedding that paradigm in Bayesian reasoning could shorten time to reperfusion while limiting unnecessary activations. Methods: We derived age- and sex-specific baseline prevalences of OMI from national emergency-department surveillance data and contemporary angiographic series. Pre-test probabilities were adjusted with published likelihood ratios (LRs) for chest-pain descriptors and clinical risk factors, then updated again with either (1) the stand-alone accuracy of ST-elevation or (2) the pooled accuracy of a broader OMI ECG spectrum. Two decision thresholds were prespecified: post-test probability >10% to trigger catheterization and >75% to justify fibrinolysis when angiography was unavailable. The framework was applied to five consecutive real-world cases that had elicited diagnostic disagreement in clinical practice. Results: The Bayesian scaffold re-classified three “NSTEMI” tracings as intermediate or high-probability OMI (post-test 27–65%) and prompted immediate reperfusion; each was confirmed as a totally occluded artery. A fourth patient with crushing pain and a normal ECG retained a 17% post-ECG probability and was later found to have an occluded circumflex. The fifth case, an apparent South-African-Flag pattern, initially rose to 75% but fell after a normal bedside echo and normal troponins. Conclusions: Layering pre-test context with sign-specific LRs transforms ECG interpretation from a binary rule into a transparent probability calculation. The OMI/NOMI Bayesian framework detected occult occlusions that classic STEMI criteria missed.

Background: Some authors advocate that ECGs with conventional computer algorithm (CCA) interpretations of “normal” need not be immediately reviewed. However, such ECGs may actually manifest findings of acute coronary occlusion myocardial infarction (OMI). We sought to determine if such cases can be detected by artificial intelligence (AI). Methods: Retrospective series (2014 - 2024) of cases with ≥ 1 pre-angiography ECGs with proven OMI outcome with a CCA ECG interpretation of “normal.” OMI outcome was defined as 1) diagnosis of acute type I MI, 2) angiographic culprit with intervention, 3) one of the following: a) TIMI 0-2 flow, or b) TIMI-3 or unknown flow, with high peak troponin or new wall abnormality. Each ECG was retrospectively interpreted by the PMcardio OMI AI ECG model. The primary analysis was the diagnostic performance of AI for the interpretation of CCA “normal” ECGs for OMI. Results: 42 patients with OMI met inclusion criteria. The first ECG was interpreted as “normal” by the CCA in 88% of cases; AI interpreted 81% as OMI and 86% as abnormal. Of 78 total ECGs interpreted by the CCA, 73% were diagnosed as “normal.” Of this 73%, AI identified 81% as abnormal and 72% as OMI. Conclusion: The CCA may interpret an ECG manifesting OMI as “normal.” AI not only recognized these as abnormal, but, in 81% of patients, correctly recognized OMI on the first ECG, and recognized 72% of all CCA “normal” ECGs as OMI. It was rare for AI to diagnose a normal ECG in any OMI patient.

The electrocardiogram (ECG) is the only rapid, non-invasive diagnostic test that can identify coronary occlusion warranting reperfusion therapy at the bedside. The diagnostic paradigm of ST-segment elevation (STE) myocardial infarction (STEMI)/non-STEMI (NSTEMI) is based on millimetre STE criteria as stated in the 4th Universal Definition of MI. It has identified candidates for emergent reperfusion for decades, but is limited by the low sensitivity and specificity of STE for acute coronary occlusion. A paradigm shift to occlusion MI/non-occlusion MI (OMI/NOMI) has been proposed in response. Although the ECG is not embedded in the OMI/NOMI nomenclature as it is in STEMI/NSTEMI, it remains critical to the initial diagnosis of OMI. This review outlines six principles—dynamicity, acuteness, reciprocity, proportionality, totality, and surrogacy—that organize expert interpretation of the ischaemic ECG and are essential to the ECG diagnosis of OMI. Each is drawn from established scholarship; the contribution here is their integration into one framework linked to coronary pathology.