Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep learning-enabled ECG analysis for estimation of right ventricular (RV) size or function is unexplored.
We trained a deep learning-ECG model to predict RV dilation (RVEDV >120 mL/m), RV dysfunction (RVEF ≤40%), and numerical RVEDV and RVEF from a 12-lead ECG paired with reference-standard cardiac magnetic resonance imaging volumetric measurements in UK Biobank (UKBB; n=42 938). We fine-tuned in a multicenter health system (MSH [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSH; n=115). We evaluated performance with area under the receiver operating characteristic curve for categorical and mean absolute error for continuous measures overall and in key subgroups. We assessed the association of RVEF prediction with transplant-free survival with Cox proportional hazards models. The prevalence of RV dysfunction for UKBB/MSH/MSH cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSH/MSH cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSH/MSH cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSH/MSH cohorts was 0.91/0.81/0.92, respectively. MSH mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m. The performance of the RVEF model was similar in key subgroups including with and without left ventricular dysfunction. Over a median follow-up of 2.3 years, predicted RVEF was associated with adjusted transplant-free survival (hazard ratio, 1.40 for each 10% decrease; =0.031).
Deep learning-ECG analysis can identify significant cardiac magnetic resonance imaging RV dysfunction and dilation with good performance. Predicted RVEF is associated with clinical outcome.
