A Machine Learning-Based Aging Measure Among Middle-Aged and Older Chinese Adults: The China Health and Retirement Longitudinal Study

Abstract

Objective: Biological age (BA) has been accepted as a more accurate proxy of aging than chronological age (CA). This study aimed to use machine learning (ML) algorithms to estimate BA in the Chinese population.Materials and methods: We used data from 9,771 middle-aged and older Chinese adults (≥45 years) in the 2011/2012 wave of the China Health and Retirement Longitudinal Study and followed until 2018. We used several ML algorithms (e.g., Gradient Boosting Regressor, Random Forest, CatBoost Regressor, and Support Vector Machine) to develop new measures of biological aging (ML-BAs) based on physiological biomarkers. R-squared value and mean absolute error (MAE) were used to determine the optimal performance of these ML-BAs. We used logistic regression models to examine the associations of the best ML-BA and a conventional aging measure—Klemera and Doubal method-BA (KDM-BA) we previously developed—with physical disability and mortality, respectively.Results: The Gradient Boosting Regression model performed the best, resulting in an ML-BA with an R-squared value of 0.270 and an MAE of 6.519. This ML-BA was significantly associated with disability in basic activities of daily living, instrumental activities of daily living, lower extremity mobility, and upper extremity mobility, and mortality, with odds ratios ranging from 1 to 7% (per 1-year increment in ML-BA, all P < 0.001), independent of CA. These associations were generally comparable to that of KDM-BA.Conclusion: This study provides a valid ML-based measure of biological aging for middle-aged and older Chinese adults. These findings support the application of ML in geroscience research and may help facilitate preventive and geroprotector intervention studies.

A machine learning-based data mining in medical examination data: a biological features-based biological age prediction model

“…The methods commonly used in BA models are mostly based on univariate or multivariate regression methods [7], such as PCA [16], MLP [17], and KDM [18]. Although these classical methods perform well in predicting adverse aging outcomes, they have limitations in multidimensional data processing and biomarker interactions [19][20][21]. While recently, new approaches applying machine learning (ML) algorithms have shown considerable accuracy and e ciency in BA prediction [22,23], and have caused wide attention [24].…”

“…heart disease, kidney disease) can further examine its potential as a biomarker of aging in the general population [6,29,30]. We found in the previous ML-BA that the correlation between BA and CA in the full data and the test data showed signi cant differences [19,31]. This might be because the model trained on the training set predicted the full dataset's BA, introducing the interference of parameter tuning and training over tting.…”

“…But in public health research, incomplete dataset is a major problem in data mining [32], and related medical databases are often lost for various reasons [33,34]. Ignoring samples with missing values will greatly limit the downstream analysis performance [19]. Using interpolation methods to estimate incomplete datasets contribute to improving the performance of subsequent analysis [35,36].…”

“…Using interpolation methods to estimate incomplete datasets contribute to improving the performance of subsequent analysis [35,36]. The most universal interpolation was lled with mean, median, mode, zero or random values [19]. Some machine learningbased (ML-based) methods have exhibited great application potential in recent years [37][38][39][40].…”

“…and ML-BA based on large Chinese population data (more than 30,000 people) was still very limited [19].…”