Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning.

BACKGROUND

Myocardial perfusion imaging (MPI) is frequently used to provide risk stratification, but methods to improve the accuracy of these predictions are needed.

OBJECTIVES

The authors developed an explainable deep learning (DL) model (HARD MACE [major adverse cardiac events]-DL) for the prediction of death or nonfatal myocardial infarction (MI) and validated its performance in large internal and external testing groups.

METHODS

Patients undergoing single-photon emission computed tomography MPI were included, with 20,401 patients in the training and internal testing group (5 sites) and 9,019 in the external testing group (2 different sites). HARD MACE-DL uses myocardial perfusion, motion, thickening, and phase polar maps combined with age, sex, and cardiac volumes. The primary outcome was all-cause mortality or nonfatal MI. Prognostic accuracy was evaluated using area under the receiver-operating characteristic curve (AUC).

RESULTS

During internal testing, patients with normal perfusion and elevated HARD MACE-DL risk were at higher risk than patients with abnormal perfusion and low HARD MACE-DL risk (annualized event rate, 2.9% vs 1.2%; P < 0.001). Patients in the highest quartile of HARD MACE-DL score had an annual rate of death or MI (4.8%) 10-fold higher than patients in the lowest quartile (0.48% per year). In external testing, the AUC for HARD MACE-DL (0.73; 95% CI: 0.71-0.75) was higher than a logistic regression model (AUC: 0.70), stress total perfusion deficit (TPD) (AUC: 0.65), and ischemic TPD (AUC: 0.63; all P < 0.01). Calibration, a measure of how well predicted risk matches actual risk, was excellent in both groups (Brier score, 0.079 for internal and 0.070 for external).

CONCLUSIONS

The DL model predicts death or MI directly from MPI, by estimating patient-level risk with good calibration and improved accuracy compared with traditional quantitative approaches. The model incorporates mechanisms to explain to the physician which image regions contribute to the adverse event prediction.

Informations de copyright

Copyright © 2023 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.

Déclaration de conflit d'intérêts

Funding Support and Author Disclosures This research (principal investigator: Dr Slomka) was supported in part by grant R01HL089765 from the National Heart, Lung and Blood Institute of the National Institutes of Health. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Mr Kavanagh has participated in software royalties for QPS software at Cedars-Sinai Medical Center. Dr Einstein has served as a consultant to GE Healthcare and W.L. Gore & Associates; and his institution has received research support from GE Healthcare, Philips Healthcare, Toshiba America Medical Systems, Roche Medical Systems, and W.L. Gore & Associates. Dr Ruddy has received research grant support from GE Healthcare and Advanced Accelerator Applications. Dr Edward Miller has served as a consultant to GE Healthcare. Dr Dorbala has served as a consultant to GE Healthcare and Bracco Diagnostics; and her institution has received grant support from Astellas. Dr Di Carli has received research grant support from Spectrum Dynamics; and has received consulting honoraria from Sanofi and GE Healthcare. Dr Berman has participated in software royalties for QPS software at Cedars-Sinai Medical Center; and has served as a consultant to GE Healthcare. Dr Slomka has participated in software royalties for QPS software at Cedars-Sinai Medical Center; and has received research grant support from Siemens Medical Systems. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.