Marcela Vasconcelos Montenegro

Early identification of acute myocardial infarction (AMI) remains challenging, particularly in non-ST-segment elevation presentations and occluded myocardial infarction, where conventional electrocardiogram (ECG) interpretation has limited sensitivity. Artificial intelligence–enabled ECG (AI-ECG) has emerged as a promising strategy to enhance early triage and diagnostic accuracy. To systematically evaluate the diagnostic performance of AI-enabled ECG algorithms for the detection of AMI, including ST-segment elevation myocardial infarction (STEMI) and non-ST-segment elevation myocardial infarction (NSTEMI), across diverse clinical settings. This diagnostic systematic review and meta-analysis was conducted in accordance with PRISMA guidelines and registered in PROSPERO (CRD420261292271). PubMed, Embase, and Cochrane CENTRAL were searched through January 2026. Studies evaluating AI-based ECG models for AMI detection and reporting sufficient data to reconstruct 2 × 2 contingency tables were included. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were estimated using random-effects models (restricted maximum likelihood). Summary receiver operating characteristic (SROC) curves and area under the curve (AUC) were generated. Pre-specified subgroup analyses were performed for STEMI and NSTEMI Ten observational studies comprising 94 510 participants were included. For overall AMI detection,. AI-ECG demonstrated a pooled sensitivity of 89.4% (95% CI, 79.7–94.8) and specificity of 96% (95% CI, 91.2–98.2). The pooled NPV was 98.7% (95% CI, 94.1–99.7), and the pooled PPV was 73.3% (95% CI, 50.2–88.2). The SROC AUC was 0.97 (95% CI, 0.92–0.98). In STEMI, pooled sensitivity and specificity were 94.4% and 97.5%, respectively (AUC 0.98). In NSTEMI, pooled sensitivity was lower at 65.0%, with specificity of 87.5% and an AUC of 0.71. Heterogeneity was substantial, particularly among NSTEMI cohorts. AI-enabled ECG demonstrates high sensitivity and consistently excellent negative predictive value for AMI detection, supporting its role as a scalable, non-invasive triage adjunct at first medical contact. These findings highlight the potential of AI-ECG to facilitate early rule-out strategies and improve prioritization of patients requiring urgent ischaemic evaluation. Beyond diagnostic accuracy, AI-ECG may support probabilistic risk stratification and integration into early clinical decision-making pathways.

Patients with type 2 diabetes mellitus (T2DM) who survive myocardial infarction (MI) remain at high risk for recurrent cardiovascular events and heart failure (HF). Although glucagon-like peptide-1 receptor agonist (GLP-1 RA) reduces cardiovascular events in stable atherosclerotic disease, its impact among patients with established MI has not been comprehensively synthesized. To evaluate the association between GLP-1 RA use and cardiovascular outcomes in patients with T2DM across MI-defined cohorts. We searched MEDLINE, Embase, and Cochrane Central Register of Controlled Trials. Hazard ratios (HRs) with 95% confidence intervals (CIs) were pooled using random-effects models. Heterogeneity was evaluated using the I² statistic, and 95% prediction intervals (PIs) were calculated to estimate the expected range of true effects in future clinical settings. Outcomes included all-cause mortality, cardiovascular death, study-defined major adverse cardiovascular events (MACE), MI, stroke, and HF or hospitalization for HF. A sensitivity analysis using the Hartung-Knapp-Sidik-Jonkman (HKSJ) adjustment was performed to account for the small number of included studies and substantial heterogeneity. Statistical analysis was performed using R software version 4.5.0. Seven studies, including 37,393 patients with T2DM from MI-defined populations (9556 receiving GLP-1 RA), were analyzed. GLP-1 RA use was associated with lower all-cause mortality (HR, 0.67; 95% CI, 0.49-0.90; I² = 87.3%; PI, 0.27-1.63; P = 0.0085), reduced study-defined MACE (HR, 0.69; 95% CI, 0.56-0.84; I² = 55.6%; PI, 0.44-1.06; P = 0.0002), and fewer HF events or hospitalizations for HF (HR, 0.78; 95% CI, 0.62-0.98; I² = 77.6%; PI, 0.42-1.45; P = 0.0306). No significant associations were observed for cardiovascular death (HR, 0.85; 95% CI, 0.67-1.06; I² = 0%; PI, 0.42-1.69; P = 0.15), recurrent MI (HR, 0.82; 95% CI, 0.62-1.09; I² = 63%; PI, 0.41-1.63; P = 0.1753), or stroke (HR, 0.91; 95% CI, 0.68-1.22; I² = 61.2%; PI, 0.40-2.05; P = 0.5237). In the sensitivity analysis using the HKSJ adjustment, statistical significance was lost for all endpoints, including all-cause mortality (P = 0.05), study-defined MACE (P = 0.13), and HF or hospitalization for HF (P = 0.06). In patients with T2DM across MI-defined populations, GLP-1 RA use showed signals toward lower all-cause mortality, study-defined MACE, and HF-related events; however, these findings remain exploratory because of substantial heterogeneity, wide PIs, and attenuation of statistical significance under HKSJ adjustment. PROSPERO identifier no. CRD420251270326.