Machine learning prediction of right ventricular volume and ejection fraction from two-dimensional echocardiography in patients with pulmonary regurgitation.

Abstract

Right ventricular (RV) end-diastolic volume (RVEDV) and ejection fraction (RVEF) by cardiac MRI (cMRI) guide management in chronic pulmonary regurgitation (PR). Two-dimensional echocardiography suboptimally correlate with RV volumes. This study tested whether combination of guideline-directed RV measures in a machine learning (ML) framework improves quantitative assessment of RVEDV and RVEF. RV measurements were obtained on subjects with > mild PR who had cMRI and echocardiogram within 90 days. A gradient-boosted trees algorithm predicted cMRI RV dilation (RVEDV > 160 ml/m²) and RV dysfunction (RVEF<47%), first with "guideline-only" measures, and then with "expanded-features" to include 44 total echocardiographic, clinical, and demographic variables. Model performance was compared to clinician visual assessment. Of 232 studies (56% tetralogy of Fallot, 20% pulmonary stenosis), the median age was 21.5 years, 21 (9%) had RV dilation, and 42 (18%) had RV dysfunction. For RV dilation prediction, the guideline-only model area under the receiver operating characteristic (AUROC)=0.68, and expanded-features model AUROC=0.85. At 90% sensitivity, the expanded-features model had 73% specificity, 25% positive predictive value (PPV), and 99% negative predictive value (NPV) This was similar to clinician performance (sensitivity 81%, specificity 81%, PPV 29%, NPV 98%). For prediction of RV dysfunction, the guideline-only AUROC= 0.71, additional features did not improve the model, and clinicians outperformed the model. In patients with PR, a ML model combining guidelines for RV assessment with demographic and additional echocardiographic parameters may effectively rule-out those with significant RV dilation at clinical thresholds for intervention, and performs similarly to expert clinicians.