@article{10.11648/j.sr.20261405.12,
  author = {Wang Ru and Cai Jinyi and Liu Jinsu and Min Xiaoqing and She Meng and Lu Shan},
  title = {Risk Identification of Abdominal Obesity in Chinese Working-Aged Adults Based on Multidimensional Lifestyle Data and Its Implications for AI-Driven Health Management},
  journal = {Science Research},
  volume = {14},
  number = {5},
  pages = {273-279},
  doi = {10.11648/j.sr.20261405.12},
  url = {https://doi.org/10.11648/j.sr.20261405.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sr.20261405.12},
  abstract = {This cross-sectional study aimed to assess the prevalence of abdominal obesity and identify modifiable risk factors among working-aged adults (aged 18–65 years) in urban and rural China using multidimensional lifestyle data, and to explore the translational implications for AI-driven health management. A survey was conducted in Nanjing from 2024 to 2025, enrolling 1,014 working-aged adults from both urban and rural areas. Multidimensional data were collected, encompassing sociodemographic characteristics, occupational attributes, commuting modes, lifestyle behaviors, dietary patterns, and nutrition knowledge awareness. Multivariate unconditional logistic regression was employed to identify independent risk and protective factors for abdominal obesity after adjusting for potential confounders, and the applicability of these variables as core inputs for AI-based health management systems was further evaluated based on their data accessibility and clinical interpretability. The overall prevalence of abdominal obesity was 58.5% (593/1,014). Multivariate logistic regression revealed that female sex (OR=2.671), consumption of baijiu (Chinese liquor, OR=2.812), intake of sugar-sweetened beverages (OR=4.433), and habitual tea drinking (OR=5.698) were independently associated with increased odds of abdominal obesity (all P < 0.05), while walking to work emerged as a significant protective factor (P < 0.05). All identified variables demonstrated satisfactory data availability and clinical interpretability, supporting their integration as key input features in AI-driven health management models. The prevalence of abdominal obesity among Chinese working-aged adults is alarmingly high, affecting nearly three in five individuals. The multidimensional modifiable factors identified not only provide actionable targets for conventional interventions but also constitute an interpretable feature set for AI-based health management systems. Future research may integrate real-time data from wearable devices with deep learning algorithms to establish an intelligent platform encompassing risk stratification, dynamic early warning, and personalized intervention, facilitating a paradigm shift from reactive treatment to proactive prevention in occupational health and offering empirical evidence for AI-empowered chronic disease control.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Risk Identification of Abdominal Obesity in Chinese Working-Aged Adults Based on Multidimensional Lifestyle Data and Its Implications for AI-Driven Health Management
AU  - Wang Ru
AU  - Cai Jinyi
AU  - Liu Jinsu
AU  - Min Xiaoqing
AU  - She Meng
AU  - Lu Shan
Y1  - 2026/08/26
PY  - 2026
N1  - https://doi.org/10.11648/j.sr.20261405.12
DO  - 10.11648/j.sr.20261405.12
T2  - Science Research
JF  - Science Research
JO  - Science Research
SP  - 273
EP  - 279
PB  - Science Publishing Group
SN  - 2329-0927
UR  - https://doi.org/10.11648/j.sr.20261405.12
AB  - This cross-sectional study aimed to assess the prevalence of abdominal obesity and identify modifiable risk factors among working-aged adults (aged 18–65 years) in urban and rural China using multidimensional lifestyle data, and to explore the translational implications for AI-driven health management. A survey was conducted in Nanjing from 2024 to 2025, enrolling 1,014 working-aged adults from both urban and rural areas. Multidimensional data were collected, encompassing sociodemographic characteristics, occupational attributes, commuting modes, lifestyle behaviors, dietary patterns, and nutrition knowledge awareness. Multivariate unconditional logistic regression was employed to identify independent risk and protective factors for abdominal obesity after adjusting for potential confounders, and the applicability of these variables as core inputs for AI-based health management systems was further evaluated based on their data accessibility and clinical interpretability. The overall prevalence of abdominal obesity was 58.5% (593/1,014). Multivariate logistic regression revealed that female sex (OR=2.671), consumption of baijiu (Chinese liquor, OR=2.812), intake of sugar-sweetened beverages (OR=4.433), and habitual tea drinking (OR=5.698) were independently associated with increased odds of abdominal obesity (all P < 0.05), while walking to work emerged as a significant protective factor (P < 0.05). All identified variables demonstrated satisfactory data availability and clinical interpretability, supporting their integration as key input features in AI-driven health management models. The prevalence of abdominal obesity among Chinese working-aged adults is alarmingly high, affecting nearly three in five individuals. The multidimensional modifiable factors identified not only provide actionable targets for conventional interventions but also constitute an interpretable feature set for AI-based health management systems. Future research may integrate real-time data from wearable devices with deep learning algorithms to establish an intelligent platform encompassing risk stratification, dynamic early warning, and personalized intervention, facilitating a paradigm shift from reactive treatment to proactive prevention in occupational health and offering empirical evidence for AI-empowered chronic disease control.
VL  - 14
IS  - 5
ER  - 

Copy | Download