An artificial intelligence model to detect abnormal ejection fraction from non-contrast chest computed tomography: the CT-LVEF study.
Authors
Affiliations (14)
Affiliations (14)
- Seymour, Paul, and Gloria Milstein Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center/NewYork-Presbyterian Hospital, New York, NY, USA.
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, NewYork, NY, USA.
- Sutter Health, Emeryville, CA, USA.
- Cornell Tech, NewYork, NY, USA.
- Department of Computer Science, Cornell University, Ithaca, NY, USA.
- Information Technology Data Science, NewYork-Presbyterian Hospital, New York, NY, USA.
- NewYork-Presbyterian Hospital, New York, NY, USA.
- Department of Radiology, Columbia University Irving Medical Center, NewYork, NY, USA.
- Department of Radiology, Weill Cornell Medicine, NewYork, NY, USA.
- Departments of Biomedical Informatics, Columbia University, NewYork, NY, USA.
- Division of Cardiology, Mayo Clinic, Rochester, MN, USA.
- Division of Cardiology, Department of Medicine, Weil Cornell Medicine, NewYork, NY, USA.
- School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA.
- Department of Radiology, Weill Cornell Medical School, NewYork, NY, USA.
Abstract
Heart failure (HF), a major global health challenge, affects millions worldwide and poses substantial healthcare and economic burdens. It is estimated that a large proportion of those with early systolic dysfunction remain asymptomatic at a stage when guideline-directed medical therapies have been shown to prevent disease progression. To develop an artificial intelligence (AI) model capable of predicting abnormal left ventricular ejection fraction (EF) directly from static, non-gated, non-contrast chest computed tomography (CT) scans as a form of opportunistic screening. Using a multi-institutional dataset of 34 058 paired non- contrast CT images and echocardiogram reports from two academic centres, we trained our model of classification for predicting left-ventricle ejection fraction (LVEF) categories: abnormal EF (EF < 50%) vs. normal on 25 948 studies. We validated the model on 8110 paired chest CT and echocardiogram results from a separate institution. The model achieved an area under the receiver operating characteristic (AUROC) curve of 0.786 on the hold-out test set and 0.762 on external validation to detect an abnormal EF (<50%). Beyond strong predictive performance, the AI model surpassed expert radiologists in both accuracy and efficiency and provided interpretable visualizations highlighting imaging features linked to reduced LVEF. In this study, we developed and validated an AI model capable of predicting abnormal LVEF directly from static, non-gated, non-contrast chest CT scans, a novel application for an imaging modality typically used for unrelated indications as a form of opportunistic screening. This technology holds significant promise for early detection of systolic HF, reducing the diagnostic gap, and improving outcomes in asymptomatic HF patients.