Explainable machine learning framework for biomarker discovery by combining biological age and frailty prediction (Preprint)

Abstract

Biological age (BA) and frailty represent two distinct health measures that offer valuable insights into the aging process. Existing machine learning (ML) predictors of BA and frailty, derived from blood-based biomarkers, lack the capability to compare and analyze these biomarkers comprehensively. Such comparisons may provide deeper insights into these two distinct aging pathways. Objective: This study aimed to develop a framework to compare and analyze biomarkers by combining BA and frailty ML predictors with eXplainable Artificial Intelligence (XAI) techniques.

This study aimed to develop a framework to compare and analyze biomarkers by combining BA and frailty ML predictors with eXplainable Artificial Intelligence (XAI) techniques.

We utilized data from middle-aged and older Chinese adults (≥45 years) in the 2011/2012 wave (n=9702) and the 2015/2016 wave (n=9455, as test set validation) of the China Health and Retirement Longitudinal Study (CHARLS). Sixteen blood-based biomarkers were used to predict BA and frailty. Four tree-based ML algorithms were employed in the training and validation, and performance metrics were compared to select the best models. Then, SHapley Additive exPlanations (SHAP) analysis was conducted on the selected models.

CatBoost performed the best in the BA predictor, and Gradient Boosting performed the best in the frailty predictor. Traditional ML feature importance identified cystatin C and glycated hemoglobin as the major contributors for their respective models. However, subsequent SHAP analysis demonstrated that only cystatin C was the primary contributor in both models, suggesting that it plays an important role in both pathways.

Our novel framework integrates BA and frailty predictors with XAI techniques to compare and analyze biomarkers. The present approach leverages routine blood biomarkers and can easily incorporate additional biomarkers, providing a scalable and comprehensive toolset that offers a quantitative understanding of interesting biomarkers and complex physiological traits.