A systematic review and meta-analysis of the diagnostic accuracy of the Queen of Hearts (PMcardio) AI-ECG algorithm for detection of acute coronary occlusion compared to conventional ECG interpretation methods

This registration documents the protocol for a systematic review and meta-analysis evaluating the diagnostic test accuracy of the Queen of Hearts (QoH) artificial intelligence algorithm for detecting acute coronary occlusion on 12-lead electrocardiograms. BACKGROUND: Acute coronary occlusion requires urgent reperfusion therapy, yet conventional STEMI criteria miss a substantial proportion of patients. The Queen of Hearts algorithm, a neural network-based ECG interpretation tool deployed via PMcardio, has been evaluated in approximately 13 studies across 40,000 patients in multiple countries. OBJECTIVES: To systematically synthesize all available evidence on QoH diagnostic accuracy, pool sensitivity and specificity using bivariate meta-analysis, generate hierarchical summary ROC curves, compare QoH performance against conventional ECG interpretation methods (STEMI millimeter criteria, ECG machine algorithms), and explore heterogeneity by clinical setting, algorithm version, and reference standard. METHODS: Comprehensive search of PubMed, Embase, Scopus, Web of Science, and Cochrane Library using hybrid product-specific and technology-focused search strategy. Dual independent screening and quality assessment using QUADAS-2 adapted for AI diagnostic studies. Bivariate random-effects meta-analysis with HSROC curves. Pre-specified subgroup analyses by clinical setting, QoH version, comparator type, and reference standard hierarchy. EXPECTED OUTCOMES: Pooled estimates of QoH diagnostic accuracy, comparative performance versus conventional methods, identification of sources of heterogeneity, and GRADE evidence certainty ratings. REGISTRATION RATIONALE: PROSPERO does not currently accept diagnostic test accuracy systematic reviews. This OSF registration provides transparent, timestamped pre-specification of all methods prior to literature screening. PROTOCOL PUBLICATION: This protocol will be submitted to Systematic Reviews journal for peer review and publication.