(An) empirical comparative study on validation of biological age estimation algorithms with an application of work ability index (WAI)

Abstract

In this study, we described the characteristics of five different biological age estimation algorithms, including i) multiple linear regression, ii) principal component analysis, and somewhat unique methods developed by iii) Hochschild, and iv) Klemera & Doubal and v) a variant of Klemera & Doubal’s method. The objective of this study is to find the most appropriate computational algorithm of biological age estimation by comparing the association between the empirical data of Work Ability Index (WAI) and the differences of each algorithm’s estimates from chronological age. The WAI was found to be a measure that reflects an individual’s current health status rather than the deterioration caused by a serious dependency with the age; and thus, it becomes a good subject for comparison of various BA estimation algorithms, where the interest is in how well each algorithm detects the current health status of an individual given the chronological age of the person. Experiments were conducted on 200 Korean male participants using a BA estimation system developed principally under the concept of non-invasive, simple to operate and human function-based. In accordance with this concept, as well as the supporting evidence from past research activities, 12 biomarker tests which delivered 16 variables were selected - Hearing capacity, Pulmonary functions, Handgrip strength, Vibrotactile Sensitivity, Visual accommodation, Numeric memory, Associated memory, Topological Memory, Concentration, Acoustic reaction time, Visual reaction time and Muscular reaction time. Any possible improvements by modification of the proposed algorithms are also investigated. In particular, a few improvements were made with the Hochschild’s method on the derivation of weights for the mortality risk factors by an application of the WAI. Since many of the biomarkers variables are likely to be inter-correlated, multicollinearity is one of great concerns in biological age estimation. To resolve the ...