Predicting peak cardiorespiratory fitness and its response to cardiac rehabilitation using machine learning

초록

Background Peak cardiorespiratory fitness (CRF), commonly quantified as peak oxygen consumption (VO2 peak), is an important prognostic marker in cardiovascular disease (CVD). This study developed machine-learning (ML) models to estimate VO2 peak from clinical and functional information and to predict its longitudinal change during cardiac rehabilitation (CR).Methods This retrospective longitudinal cohort study included 333 visits from 162 patients with CVD. Task 1 estimated VO2 peak at eligible visits using 29 clinical and functional candidate predictors without CPET-derived predictors. Task 2 predicted the change in VO2 peak between consecutive visits (Delta VO2 peak) using two approaches: Task 2-1 combined clinical, functional, and inter-visit exercise information with the VO2 peak predicted by Task 1, whereas Task 2-2 combined pre-CR CPET-derived and inter-visit exercise information. Four linear regression approaches and six ML algorithms were evaluated using 5-fold patient-grouped cross-validation.Results In Task 1, CatBoost yielded an RMSE of 4.17 +/- 0.24 mL & centerdot;kg-1 & centerdot;min-1; the 6-minute walk distance, age, Korean Activity Scale Index, hand grip strength, and body mass index were among the highest-ranked features. In Task 2, CatBoost yielded similar internal prediction errors in the pathway incorporating the Task 1-predicted VO2 peak (Task 2-1: RMSE, 3.46 +/- 0.78 mL & centerdot;kg-1 & centerdot;min-1) and the CPET-based pathway (Task 2-2: RMSE, 3.39 +/- 0.75 mL & centerdot;kg-1 & centerdot;min-1). Recent cardiac intervention in Task 2-1 and measured baseline VO2 peak in Task 2-2 were the highest-ranked features for predicting Delta VO2 peak.Conclusions ML models showed promising internal performance for estimating VO2 peak and predicting its inter-visit change in this single-center cohort. These results are exploratory and do not establish clinical utility or replacement of CPET. Independent multicenter validation and prospective evaluation are required.

키워드