Artificial Intelligence-Driven Electrocardiogram Analysis for Risk Stratification in Pulmonary Embolism

Abstract Background Among patients with acute pulmonary embolism (PE), rapid identification of those with highest clinical risk can help guide life-saving treatment. However, current risk stratification algorithms involve a multi-step process requiring physical exam, imaging and laboratory results. Objectives We investigated the utility of electrocardiogram (ECG) alone to rapidly identify patients at elevated clinical risk by developing and validating a feature-based artificial intelligence (AI) model to predict clinical risk. Methods Patients who were diagnosed with PE over a nine-year period, had an ECG within 1 day of presentation, and were evaluated by our PE Response Team (PERT) were included. A feature-based random-forest model was trained to predict the PERT team’s risk stratification from the ECG alone. The ability of the model to predict the clinical risk categorization, and the accuracy of both risk stratification approaches in predicting mortality were examined on a hold-out test set. Results Of the overall cohort of 1,376 patients, 55% had a submassive (intermediate risk) or massive (high risk) PE, which were grouped together as ‘severe PE’. The AI-ECG model was able to predict the clinical classification (low-risk vs severe PE) with an AUC of 0.83 and F1 score of 0.78 in a hold-out test set. 30-day mortality and in-hospital mortality were significantly different between patients classified by the model as low versus elevated risk. Conclusions Artificial intelligence-based analysis of 12-lead ECGs may provide a useful tool in the risk stratification of PE, allowing for rapid identification and treatment of those at highest risk of adverse outcomes.