A model integrating clinical data with ECG waveforms may improve prediction of pulmonary embolism (PE), according to a study published in European Heart Journal-Digital Health. Sulaiman S. Somani, MD, and colleagues created a retrospective cohort of 21,183 patients at moderate to high suspicion of PE, with 23,793 CT pulmonary angiograms (10.0% positive for PE), 320,746 ECGs (12.8% positive for PE), and encounter-level clinical data. To predict PE likelihood, three machine learning models were developed: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. The Fusion model outperformed both the ECG and EHR models (area under the receiver operating characteristic curve [AUROC], 0.81±0.01 vs 0.59±0.01 and 0.65±0.01, respectively). The Fusion model also achieved greater specificity (0.18) and performance (AUROC, 0.84±0.01) than four commonly evaluated clinical scores (Wells’ Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score) in a sample of 100 patients (AUROC, 0.50 to 0.58; specificity, 0.00-0.05).