Deviation of Physiological from
Chronological Age Is Associated with Health
Lin PERETZ
a
and Nadav RAPPOPORT
a,1
a
Software and Information Systems Engineering, Ben-Gurion University of the Negev,
ISRAEL
Abstract. Biological age may be of higher importance than chronological age, yet
biological age is not trivial to estimate. This study presents a regression model to
predict age using routine clinical tests like laboratory tests using the UK Biobank
(UKBB) data. We run different machine learning regression models for this
predictions task and compare their performance according to RMSE. The models
were trained using data from 472,189 subjects aged 37–82 years old and 61 different
laboratory tests results. Our chosen model was an XGboost model, which achieved
an RMSE of 6.67 years. Subjects whose the model predicted to be younger than
their actual age were found to be healthier as they had fewer diagnoses, fewer
operations, and had a lower prevalence of specific diseases than age-matched
controls. On the other hand, subjects predicted to be older than their chronological
age had no significant differences in the number of diagnoses, number of operations,
and specific diseases than age-matched controls.
Keywords. Biological age, Machine Learning, Laboratory tests, Chronological age,
Electronic Health Records, BioBank
1. Introduction
As the world's aging population grows at an unprecedented rate, there is a clear need to
learn more about the biological aging process and the determinants of healthy aging. To
achieve this goal, researchers seek biological markers and other factors that can track
biophysiological aging and, ideally, provide insight into the underlying mechanisms
[1,2,3,4].
Biological age (BA), also called physiological age, measures how well or poorly a
person’s body functions. BA is correlated with calendar age (CA), also called
chronological age, which is an objective measure of elapsed time since birth. The BA of
a person can be higher or lower than their CA, since aging is not only a matter of time
but is, in fact, a complex process with multiple causes. Studies have shown that young
individuals of the same chronological age varied in their BA. These individuals showed
cognitive decline and brain aging, self-reported worse health, and looked older [5].
There are several ways for determining BA, but none are definitive or truly accurate.
Previous studies used a variety of ways to estimate the BA of a person. For example,
studies used human physical activity as recorded by a wearable device [1], by cognitive
variation independently of chronological age [6]. Other studies used molecular
1
Corresponding Author, Nadav Rappoport, Department of Software and Information Systems
Engineering, Ben-Gurion University of the Negev, ISRAEL, 1 Ben-Gurion Boulevard, Beer-Sheva, ISRAEL;
E-mail: nadavrap@bgu.ac.il.
Challenges of Trustable AI and Added-Value on Health
B. Séroussi et al. (Eds.)
© 2022 European Federation for Medical Informatics (EFMI) and IOS Press.
This article is published online with Open Access by IOS Press and distributed under the terms
of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).
doi:10.3233/SHTI220442
224