Centroid of Age Neighborhoods: A Generalized Approach to Estimate Biological Age

Abstract

Estimation of human biological age is an important and difficult challenge. In this work, we generalize a biological age estimation method and investigate the performance of the method against popular approaches. We introduce a centroid based approach, using the notion of age neighborhoods. We develop a model, based on which we compute biological age using blood biomarkers, body measurements, and a combination of both, by considering the centroid of specially selected age neighborhoods. Experiments were performed on the NHANES dataset (21451 individuals). Our experiments show that the proposed age neighborhood model results in an improved performance in biological age prediction.