Key result
Multimodal p-Cal AI predicts pericarditis with 0.89 AUC, outperforming ECG-only and clinical-only models.
Why the study?
Pericarditis can be clinically challenging to diagnose, creating a clinical need for automated artificial intelligence screening aids to assist in early and accurate detection.
Does a multimodal fusion AI model integrating EMR data and ECG signals improve the prediction of pericarditis compared to single-modality models?
Observational (n=7,810)
Yes
Does a multimodal fusion AI model integrating EMR data and ECG signals improve the prediction of pericarditis compared to single-modality models?
A multimodal AI model fusing clinical EMR data and ECG images demonstrates robust predictive capability for pericarditis screening, outperforming single-modality models.
Answers are grounded in this paper and cite their sources.
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“In 6508 patients, including 902 with clinically confirmed pericarditis, the fused model outperformed either component alone, with an area under the receiver operating characteristic curve of 0.89 compared with 0.85 for the ECG model and 0.74 for the tabular model. At the selected threshold, the negative predictive value was 0.96, although the positive predictive value remained 0.48.”
“A false-positive result may generate unnecessary echocardiography, cardiac magnetic resonance, inflammatory testing or specialist referral; a false-negative result may provide inappropriate reassurance. Decision-curve analysis, workload estimates and patient-level outcomes will be more informative than discrimination alone.”
“A second issue is disease heterogeneity. The training set combined acute, recurrent, effusive, tamponade, effusive-constrictive and chronic constrictive presentations across diverse aetiologies. Such breadth is a strength for exploration, but it also creates a broad target label encompassing biologically and electrocardiographically distinct entities.”
May aid early pericarditis screening via fused clinical-ECG data; leaves open prospective validation before clinical use.
Background Pericarditis may be associated with significant morbidity and mortality and can be a clinically challenging entity to diagnose. There is a clinical need for automated artificial intelligence (AI) algorithms to act as a screening aid to assist with the early and accurate detection of pericarditis. Methods We developed p-Cal, a browser-based pericarditis risk calculator that fuses the patient clinical data and 12-lead ECG image to estimate risk for pericarditis. The ECG encoder was designed based on a pretrained MedCLIP Vision Transformer and random forest classifier was used for the clinical tabular data. These two modalities were fused at the decision-level using a meta classifier. Model reasoning for both modalities was assessed using advanced explainable AI techniques—attention maps from the transformer model were used to interpret ECG images, while SHapley Additive exPlanations (SHAP) force plots were applied to analyse the tabular data. Results A total of 6508 patients (mean age 54.8±16.1 years, 50.9% female) were used for training and internal validation of the AI model, of whom 902 patients had a confirmed diagnosis of pericarditis (13.8%) and the remainder were normal controls. On 1302 hold-out test patients, the Fusion Model demonstrated the best discriminatory performance, achieving an area under the curve (AUC) of 0.89, which surpassed the ECG (AUC = 0.85) and the clinical data only models (AUC = 0.74) performance. On external validation in the Medical Information Mart for Intensive Care (MIMIC) Database, the fusion model achieved an AUC of 0.81. Conclusion A late fusion AI model integrating tabular clinical electronic medical record data and ECG signal has robust predictive capability for pericarditis as a screening tool.
No takes yet. Share an insight, caveat, or question.
Ayoub et al. (2026) conducted an observational in Pericarditis (n=7,810). p-Cal (multimodal fusion AI model of EMR data and ECG signals) vs. ECG-only model and clinical data-only model was evaluated on Discriminatory performance (AUC) for pericarditis prediction (AUC 0.89). The p-Cal multimodal AI model integrating clinical data and ECG signals achieved an AUC of 0.89 for predicting pericarditis, outperforming ECG-only (AUC 0.85) and clinical-only (AUC 0.74) models.
Synapse has enriched 10 related papers. Consider them for comparative context: