Quantitative Prediction of Right Ventricular Size and Function From the ECG

Son Q. Duong*, Akhil Vaid, Vy Thi Ha My, Liam R. Butler, Joshua Lampert, Robert H. Pass, Alexander W. Charney, Jagat Narula, Rohan Khera, Ankit Sakhuja, Hayit Greenspan, Bruce D. Gelb, Ron Do, Girish N. Nadkarni

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

BACKGROUND: 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. METHODS AND RESULTS: We trained a deep learning–ECG model to predict RV dilation (RVEDV >120 mL/m2), 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 (MSHoriginal [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSHvalidation; 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/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.91/0.81/0.92, respectively. MSHoriginal mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m2. 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; P=0.031). CONCLUSIONS: 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.

Original languageEnglish
Article numbere031671
JournalJournal of the American Heart Association
Volume13
Issue number1
DOIs
StatePublished - 2 Jan 2024
Externally publishedYes

Funding

FundersFunder number
National Institutes of HealthR01HL155915
National Institutes of Health
National Heart, Lung, and Blood Institute
National Center for Advancing Translational SciencesUL1TR004419
National Center for Advancing Translational Sciences

    Keywords

    • ECG
    • cardiac MRI
    • deep learning
    • right ventricle

    Fingerprint

    Dive into the research topics of 'Quantitative Prediction of Right Ventricular Size and Function From the ECG'. Together they form a unique fingerprint.

    Cite this