Application of machine learning and deep learning approaches for prediction modeling with time-to-event outcomes in...

Clinical prediction models (CPM) are essential tools for diagnosis and prognosis in clinical epidemiology. Machine learning (ML) and deep learning (DL) approaches provide flexible methods that can complement regression-based methods for CPM when complex predictors such as clinical biomarkers are of interest. However, concerns have been raised on the ability of ML and DL to address desired properties of CPMs such as parsimony, generalizability, and interpretability.

In this study, we evaluated and applied selected regression-based, ML and DL approaches for time-to-event outcomes in a clinical study integrating protein biomarkers and lipids in an existing CPM for cardiovascular risk.

We observed considerable advantages from the application of gradient boosting machines (GBM: C-statistic=0.72; Brier Score=0.052), which provided the best balance between model flexibility, discrimination, calibration, and parsimony, the latter being directly related to one of the model parameters (shrinking rate). Further, GBM results can be used for individual risk prediction, providing an interpretable tool for CPM implementation.

We compared ML and DL methods for CPM with time-to-event outcomes and discussed practical aspects of their implementation in clinical epidemiology including generalizability and interpretability. Adequately trained ML approaches can provide advantages in prediction modeling, especially when integrating complex predictors.