Predictive value of electrocardiogram Morphology-Voltage-P wave duration score for new episodes of atrial fibrillation in patients with acute myocardial infarction: a retrospective study

Background: -wave characteristics, has shown promise in predicting AF risk. New-onset atrial fibrillation (NOAF) following acute myocardial infarction (AMI) is associated with poor clinical outcomes. Methods: This retrospective study included 334 patients treated for AMI from January 2018 to April 2021. Patients were categorized into low-risk (202 cases), medium-risk (98 cases), and high-risk (34 cases) groups based on MVP ECG scores. NOAF incidence, stratified as early-onset (≤48 h) and late-onset (>48 h), was tracked over a 12-month follow-up period. Statistical analyses included group comparisons, Cox regression for multivariate adjustment, ROC analysis to evaluate and compare the predictive performance of the MVP score against both the CHA₂DS₂-VASc and the AF-specific C2HEST scores, and decision curve analysis (DCA) to assess clinical utility. Results: The MVP ECG risk score effectively predicted long-term AF incidence, showing a graded increase in risk across categories: 11.9% in low-risk, 28.6% in medium-risk, and 76.5% in high-risk patients. Incidence increased for both early-onset (4.0%, 10.2%, 29.4%) and late-onset NOAF (7.9%, 18.4%, 47.1%). The MVP score demonstrated superior discriminative ability for total NOAF (AUC = 0.908) compared to the CHA₂DS₂-VASc score (AUC = 0.643) and the C2HEST score (AUC = 0.715), with the highest performance observed for late-onset NOAF (AUC = 0.925). Addition of the MVP score to either clinical score significantly improved reclassification (NRI: 0.28-0.35, IDI: 0.07-0.08). DCA confirmed that using the MVP score provided a greater net clinical benefit than the comparator scores across realistic decision thresholds. Multivariate analysis confirmed the MVP score as an independent predictor of AF, with a stronger association for late-onset events. Conclusion: The MVP ECG risk score is a simple, non-invasive tool that provides superior prediction of NOAF in AMI patients compared to traditional clinical risk scores, exhibiting particular strength in identifying patients at risk for late-onset AF. It effectively identifies high-risk patients who may benefit from close monitoring and proactive management strategies.