An empirical comparative study on biological age estimation algorithms with an application of Work Ability Index (WAI)
Introduction
There have been various attempts on assessing biological age (BA) by a range of computational algorithms. However, few studies are reported on direct comparison of these algorithms, revealing which algorithm is most reliable and acceptable as to be implemented on a BA estimation system.
BA is an abstract concept. Although the concept of BA can be found in many scientific papers throughout last half a century, a concrete and precise definition that can be generally accepted is difficult to find. Klemera and Doubal (2006) explained it as a quantity expressing the “true global state” of ageing organism, or “true life expectancy” of the individual better than corresponding chronological age (CA). As it is obvious, CA does not correlate perfectly with BA. Two people may be of the same age, but differ in their mental and physical capacities. BA describes a person's general condition at a particular time of the CA. It is determined by the individual's physical, psychological, and social characteristics, rather than chronology. Thus, the BA of a person could be defined as the CA at which ‘most normal’ people are in the physical state of that person.
The common assess to BA estimation is through measurements of various age-dependent variables, so-called biomarkers, and aggregating these measures into a value in units of years with some computational algorithms. The algorithms include multiple linear regression (MLR) methods, principal component analysis (PCA), and somewhat unique and novel methods as Hochschild, 1989a, Hochschild, 1989b, Hochschild, 1994 and Klemera and Doubal had proposed. Using the data obtained from experiments, this paper examines these methods as well as some variations of them, and ultimately, proposes the most suitable method for valid BA estimation. The details of each method are discussed in the following sections.
Validation of BA has always been a controversial issue, as the term itself is an abstract concept, and the absence of the true value in the reality makes it difficult to evaluate the validity of the estimated BA. (This is not to deny the existence of the conceptual value of BA.) Ingram (1988) and McClearn (1997) offered inspiration how to deal with the validation issue. They asserted that the validation of BA is ascertained by examining the validity of biomarkers from which the BA is estimated. Ingram pointed out that two types of validity should be established in the development of biomarkers of ageing; they are construct validity and predictive validity. Construct validity refers to how well a candidate biomarker reflects the construct, and predictive validity refers to the usefulness of a biomarker in longitudinal studies (Ingram, 1988).
The focus of this paper is not on the selection of biomarkers (which is still very important), but rather on the validity of the final estimated value of BA with various computational algorithms. Therefore, instead of examining whether individual biomarkers are actually measuring ageing process, the present authors propose the use of Work Ability Index (WAI) as an alternative measure taken in the real world to be examined for the correspondence with the attributes of BA estimates (BAE). The objective of this study is to find the most appropriate method of BA estimation by examining the association between WAI and the differences of each algorithm's BAE from CA.
Section snippets
Selection of biomarkers
Anstey et al. (1996) published an outstanding review of extensive studies related to measurement of BA and empirical findings of the correlation of more than 170 biomarkers with the ageing rates. According to the authors, the biomarkers are classified into seven categories—anthropometric/morphologic, sensorimotor, cognitive, psychosocial, physiological/biomedical, behavioral and dentition. From author to author of BA-related research, the reasons given for the choice of biomarkers vary. Some of
Descriptive statistics of the data
Table 3 shows the mean and standard deviations of the biomarker variables derived from the experiment. From one-way ANOVA, the results of the significance tests on differences of means among 5-year age groups were obtained. They indicated that all physical and cognitive function tests are statistically significant at or beyond the 0.1% level. Visual and muscular reaction time (rVRT and rMRT) tests showed relatively less significant level, whereas acoustic reaction time (rART) test was not
Discussion
The Klemera and Doubal's methods, KD1 and KD2, turned out to be most correlated with WAI, indicating that the estimates of the methods adequately correspond to the health status of the individuals. The two methods both presented satisfactory values for all the criteria used in this study, including (i) Pearson correlation with WAI scores, (ii) the standard deviation and (iii) discrimination ability between healthy and unhealthy individuals. Although KD1 showed a little higher
Acknowledgments
The authors wish to thank Dr. Kyung Chul Chae, professor, Stochastic Modeling Laboratory, Department of Industrial & Systems Engineering, KAIST, for valuable advice and constructive comments. We would also like to thank Dr. Sung-Taek Chung, professor, Integrated Media System Laboratory, Department of Computer Engineering, Korea Polytechnic University, for his kind assistance in the execution of the experiment. We also thank the referee for helpful comments that considerably improved the
References (34)
- et al.
Development of models for predicting biological age (BA) with physical, biochemical, and hormonal parameters
Arch. Gerontol. Geriat.
(2008) - et al.
Physiological fitness measures and sensory and motor performance in aging
Exp. Gerontol.
(1987) - et al.
Biological age and its estimation. III. Introduction of a correction to the multiple regression model of biological age in cross-sectional and longitudinal studies
Exp. Gerontol.
(1984) Improving the precision of biological age determinations. Part 1: a new approach to calculating biological age
Exp. Gerontol.
(1989)Improving the precision of biological age determinations. Part 2: automatic human tests, age norms and variability
Exp. Gerontol.
(1989)- et al.
Models of the biological age of the rat. I. A factor model of age parameters
Mech. Ageing Dev.
(1980) Key questions in developing biomarkers of aging
Exp. Gerontol.
(1988)- et al.
A new approach to the concept and computation of biological age
Mech. Ageing Dev.
(2006) - et al.
The relation of age, work ability index and stress-inducing factors among bus drivers
Int. J. Ind. Ergon.
(2000) - et al.
Assessment of biological age by principal component analysis
Mech. Ageing Dev.
(1988)
Biomarkers of age and aging
Exp. Gerontol.
Problems associated with biological age
Exp. Gerontol.
Measuring human aging using a two-compartmental mathematical model and the vitality concept
Arch. Gerontol. Geriat.
Measuring human functional age: a review of empirical findings
Exp. Aging Res.
Regression Diagnostics: Identifying Influential Data and Sources of Collinearity
Assessment of biological age using a profile of physical parameters
J. Gerontol.
Test-retest reliability of the Work Ability Index questionnaire
Occup. Med.
Cited by (57)
Distinct biological ages of organs and systems identified from a multi-omics study
2022, Cell ReportsCitation Excerpt :The concept of BA has been investigated since the 1970s (Comfort, 1969). Multiple methods were developed later, including multiple linear regression (Bae et al., 2008; Cho et al., 2010; Dubina et al., 1984; Hollingsworth et al., 1965; Krøll and Saxtrup, 2000), principal component analysis (Hofecker et al., 1980; Nakamura and Miyao, 2007; Nakamura et al., 1988), and the Klemera and Doubal method (KMD) (Klemera and Doubal, 2006). The major difference among these methods is the role of CA.
Risk score-embedded deep learning for biological age estimation: Development and validation
2022, Information SciencesCitation Excerpt :With advances in machine learning, several machine-learning methods have been applied to BA estimation, and meaningful BA indices have been developed using various data such as gene expression and EMR [3,16,18,19,24,28,29]. BA has also been estimated by incorporating with the age-dependent variables, mentioned as biomarkers that are associated with health status in existing health indicators [10]. Three general types of methods have been used to estimate BA: (1) regression for CA, (2) simulation learning, and (3) latent feature extraction.
Multi-omics approaches to human biological age estimation
2020, Mechanisms of Ageing and DevelopmentCitation Excerpt :Commonly special indexes are used for precise indication of biological age. The MLR (multiple linear regression) approach (used for the cohorts >50 years old, based on the linear correlation of the numerous biomarkers of aging) (Bae et al., 2008; Hollingsworth et al., 1965; Krøll and Saxtrup, 2000); the PCA (Principal component analysis) method unites correlation analysis, redundancy analysis, PCA, and equation construction (Bai et al., 2010; Zhang et al., 2014); Hochschild’s method estimates biomarkers according to their effects on life expectancy (parameters are aggregated into composite validation variables) (Hochschild, 1989); Klemera and Doubal method (KDM) (Klemera and Doubal, 2006) and KDM2 (Cho et al., 2010) uses chronological age as one of the biomarkers, are the most popular ones. The central challenge of biological age estimation: the role of chronological age in different methods of measurement has been still unknown.
Comparison of Seven Healthy Lifestyle Scores Cardiometabolic Health: Age, Sex, and Lifestyle Interactions in the NutrIMDEA Web-Based Study
2023, Journal of Epidemiology and Global Health