Key result
DROID-RV deep learning model detects RV dysfunction on echocardiography and predicts adverse cardiovascular outcomes.
Why the study?
Assessment of right ventricular size and function by two-dimensional transthoracic echocardiography is challenging despite its prognostic importance in cardiovascular diseases.
Does the DROID-RV deep learning model accurately estimate right ventricular size and function from 2D echocardiograms and predict cardiovascular outcomes in ambulatory cardiology and primary care patients?
Observational (n=27,084)
Does the DROID-RV deep learning model accurately estimate right ventricular size and function from 2D echocardiograms and predict cardiovascular outcomes in ambulatory cardiology and primary care patients?
A deep learning model can automate the assessment of right ventricular size and function from standard 2D echocardiography, enabling risk stratification for future cardiovascular events at scale.
May aid RV assessment on routine TTE; leaves open prospective validation before clinical use.
Right ventricular (RV) size and function inform prognosis in many cardiovascular diseases, but assessment by two-dimensional transthoracic echocardiography is challenging. Here we show that a deep learning model, Dimensional Reconstruction of Imaging Data-Right Ventricle (DROID-RV), can estimate RV end-diastolic diameter and identify RV systolic dysfunction from transthoracic echocardiography videos. We trained DROID-RV in 17,141 ambulatory cardiology patients (51,188 studies and 383,881 video clips) and validated model predictions in 9,112 primary care patients and 831 patients with RV ejection fraction assessed by three-dimensional transthoracic echocardiography. Across multiple test samples, DROID-RV accurately estimates RV end-diastolic diameter and identifies RV dysfunction, although model prediction error increases at extremes of RV size and function. We additionally show that RV size and function predictions are associated with incident mortality, atrial fibrillation and heart failure. Our work demonstrates how deep learning can automate RV assessment and risk stratification at scale using two-dimensional echocardiography.
No takes yet. Share an insight, caveat, or question.
Al‐Alusi et al. (2026) conducted an observational in Cardiovascular disease (n=27,084). Deep learning model (DROID-RV) was evaluated on RV end-diastolic diameter estimation, RV systolic dysfunction identification, and association with cardiovascular outcomes. The DROID-RV deep learning model accurately estimated right ventricular size and dysfunction from 2D echocardiograms, associating with incident mortality, atrial fibrillation, and heart failure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: