Machine-Learning Score using Stress CMR and CCTA for prediction of cardiovascular events in patients with obstructive CAD

Abstract

Introduction

In patients with newly diagnosed coronary artery disease (CAD), traditional prognostic risk assessment is based on a limited selection of clinical and imaging findings as coronary computed tomography angiography (CCTA) and stress cardiovascular magnetic resonance (CMR). Machine learning (ML) methods can take into account a greater number and complexity of variables.

Objective

To investigate the feasibility and accuracy of ML using both stress CMR and CCTA data to predict major adverse cardiovascular events (MACE) in patients with newly diagnosed CAD, and compared its performance with existing clinical, CMR or CCTA scores.

Method

Between 2008–2020, consecutive symptomatic patients without known CAD referred for CCTA were screened. Patients with obstructive CAD (at least 1 ≥ 50% stenosis on CCTA) were further referred for stress CMR. Twenty clinical, 9 CCTA and 12 CMR parameters were evaluated. ML involved automated feature selection by LASSO, model building with a XGBoost algorithm (Figure 1A). The primary composite outcome was MACE defined by cardiovascular death or nonfatal myocardial infarction. The external validation cohort of the ML score was performed in another center (Lariboisiere Hospital).

Results

Of 2,210 patients who completed CMR, 2,038 (47% male, age 69 ± 12 years) completed the follow-up (median 6.8 [IQR 5.9–9.2] years), and 281 experienced a MACE (13.8%). The ML score exhibited a higher area under the curve compared with ESC risk score, QRISK3 score, Framingham risk score, SIS-core and CCTA or stress CMR data alone for prediction of MACE (ML-score: 0.85 vs. SIS-score: 0.71, stress CMR-score: 0.66, C-CMR-10-score: 0.62, QRISK3-score: 0.60, ESC-score: 0.55, FRS: 0.50, all p < 0.001, Figure 1 B). The ML score also exhibited a good area under the curve in the external cohort (0.85).

Conclusion

The ML score including multimodality imaging data with both CCTA and stress CMR findings exhibited a higher prognostic value to predict MACE compared with any existing traditional method, traditional scores, and scores using only CCTA or CMR data.