| Title: | Associations Between Dietary Habits and Accelerated Aging and the Establishment of an Accelerated Aging Interpretable Risk Prediction Model via Shapley Additive Explanations: Cross-Sectional Study From Two Representative Populations |
| Journal: | JMIR Aging |
| Published: | 1 Dec 2025 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/41326017/ |
| DOI: | https://doi.org/10.2196/72020 |
Publication 16824
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
BACKGROUND: Research has revealed potential links between specific dietary habits and accelerated aging. However, most studies focus only on singular diets or lack ethnic diversity.</p>
OBJECTIVE: This study aimed to investigate the associations between 5 dietary indices and the risk of accelerated aging and develop an interpretable machine learning (ML) model for accelerated aging prediction.</p>
METHODS: We explored associations between dietary indices and the risk of accelerated aging using data from the US National Health and Nutrition Examination Survey (NHANES) and the UK Biobank. A weighted linear regression analysis was used to determine whether accelerated aging was linked to dietary habits, and the covariates were gradually adjusted to ensure that the association was stable. Nonlinear correlations were explored using restricted cubic spline curves. In addition, multiple ML algorithms were used to build predictive models of accelerated aging risk.</p>
RESULTS: Except for the Dietary Inflammation Index (β=0.35, 95% CI 0.23-0.74), the other 4 dietary indices (Alternative Healthy Eating Index, Alternative Mediterranean Diet, Healthy Eating Index-2020, and Dietary Approaches to Stop Hypertension) were negatively associated with the risk of accelerated aging in NHANES participants. Similar results were observed in UK Biobank participants. Nine ML algorithms were used to develop risk prediction models, among which the gradient boosting decision tree model showed the best overall performance. A web-based prediction platform was developed and made publicly available.</p>
CONCLUSIONS: Significant associations between accelerated aging and dietary indices were observed. High compliance with the Dietary Inflammation Index had a promoting effect on accelerated aging, while high compliance with the Alternative Healthy Eating Index, Alternative Mediterranean Diet, Healthy Eating Index-2020, and Dietary Approaches to Stop Hypertension showed varying degrees of protection against accelerated aging.</p>
17 Keywords
- Adult
- Aged
- Aging
- Aging, Premature
- Cross-Sectional Studies
- Diet, Healthy
- Feeding Behavior
- Female
- Humans
- Machine Learning
- Male
- Middle Aged
- Nutrition Surveys
- Risk Assessment
- Risk Factors
- United Kingdom
- United States
9 Authors
- Zhengyang Wu
- Ning Zhang
- Haiwei Wang
- Yang Yang
- Houhao Shen
- Qidi Zhang
- Yunxia Cao
- Yinan Du
- Dongmei Ji
1 Application
| Application ID | Title |
|---|---|
| 211452 | Effects of exposure to air pollutants and noise pollution on the health status of middle-aged and older adults |
Enabling scientific discoveries that improve human health