Hybridizing machine learning in survival analysis of cardiac PET/CT imaging

Abstract

<p><strong>Background</strong></p><p>Machine Learning (ML) allows integration of the numerous variables delivered by cardiac PET/CT, while traditional survival analysis can provide explainable prognostic estimates from a restricted number of input variables. We implemented a <em>hybrid</em> ML-and-survival analysis of multimodal PET/CT data to identify patients who developed myocardial infarction (MI) or death in long-term follow up.</p><p><strong>Methods</strong></p><p>Data from 739 intermediate risk patients who underwent coronary CT and selectively stress ¹⁵O-water-PET perfusion were analyzed for the occurrence of MI and all-cause mortality. Images were evaluated segmentally for atherosclerosis and absolute myocardial perfusion through 75 variables that were integrated through ML into an ML-CCTA and an ML-PET score. These scores were then modeled along with clinical variables through Cox regression. This <em>hybridized</em> model was compared against an expert interpretation-based and a calcium score-based model.</p><p><strong>Results</strong><br></p><p>Compared with expert- and calcium score-based models, the hybridized ML-survival model showed the highest performance (CI .81 vs .71 and .64). The strongest predictor for outcomes was the ML-CCTA score.</p><p><strong>Conclusion</strong><br></p><p>Prognostic modeling of PET/CT data for the long-term occurrence of adverse events may be improved through ML imaging score integration and subsequent traditional survival analysis with clinical variables. This <em>hybridization</em> of methods offers an alternative to traditional survival modeling of conventional expert image scoring and interpretation.<br></p>