Abstract
INTRODUCTION: Biological age (BA) can represent the actual state of human aging more accurately than chronological age (CA). METHODS: Using hematological data from 112,925 participants in southwestern China, collected between 2015 and 2021, this study constructed BA predictors using 7 machine learning (ML) methods (tailored separately for male and female populations). This study then analyzed the association between BA acceleration and type 2 diabetes mellitus (T2DM) within this data using logistic regression. Additionally, it examined the impact of glycemic control on BA in individuals with diabetes. RESULTS: Among all ML models, deep neural networks (DNN) delivered the best performance in male [mean absolute error (MAE)=6.89, r=0.75] and female subsets (MAE=6.86, r=0.74). BA acceleration showed positive correlations with T2DM in both male [odds ratio (OR): 2.22, 95% confidence interval (CI): 1.77-2.77] and female subsets (OR: 3.10, 95% CI: 2.16-4.46), while BA deceleration showed negative correlations in both male (OR: 0.32, 95% CI: 0.27-0.39) and female subsets (OR: 0.42, 95% CI: 0.33-0.53). Individuals with diabetes with normal fasting glucose had significantly lower BAs than those with impaired fasting glucose in all CA groups except for patients older than 80. DISCUSSION: Artificial intelligence (AI)-based hematological BA predictors show promise as advanced tools for assessing aging in epidemiological studies. Implementing AI-based BA predictors in public health initiatives could facilitate proactive aging management and disease prevention.