Author(s)

Yuhang Zhong ¹, Haiyuan Nong ², Yuxin Liu ², Guorui Zhao ²

Affiliation(s)

¹ School of Materials Science and Engineering, Guangdong Ocean University, Yangjiang, Guangdong, China
² School of Computer Science and Engineering, Guangdong Ocean University, Yangjiang, Guangdong, China

Corresponding Author

Guorui Zhao

ABSTRACT

Hypertension has become a significant health threat for residents. Investigating the relationship between disease risk and dietary and lifestyle habits is both theoretically important and practically valuable. This paper examines the connection between the risk of hypertension and the dietary and lifestyle choices of residents, using cross-sectional data from an epidemiological survey conducted in Shenzhen. To start, we developed an index system that integrates the Chinese Dietary Guidelines for residents with guidelines for managing hypertension. Next, we preprocessed the data using the 3σ criterion and a sample equalization method. We then constructed a random forest model to explore the relationship between the risk of hypertension and diet and lifestyle factors. To improve model interpretability, we applied the newly developed SHAP model for quantitative analysis. The results indicated that six factors were most strongly associated with the risk of hypertension: work intensity, milk intake, high-protein food consumption, exercise intensity, the weekly incidence of skipping breakfast, and vegetable intake. Among these, the interaction between high-protein food intake and work intensity was particularly significant. 

KEYWORDS

Hypertension risk, Eating habits, Living habits, Random forest, SHAP model

CITE THIS PAPER

Yuhang Zhong, Haiyuan Nong, Yuxin Liu, Guorui Zhao, Correlation Analysis of Hypertension Risk with Diet and Lifestyle Habits: Based on Random Forest and SHAP Model. Social Medicine and Health Management (2024) Vol. 5: 135-142. DOI: http://dx.doi.org/10.23977/socmhm.2024.050219.

REFERENCES

[1] The Chinese Hypertension Prevention and Control Guideline Revision Committee, the Hypertension League (China), the Chinese Medical Healthcare International Exchange Promotion Association Hypertension Branch, et al. Chinese Hypertension Prevention and Control Guideline (2024 Revised Edition) [J]. Chinese Journal of Hypertension (Chinese and English), 2024, 32(07): 603-700.
[2] Chinese Dietary Guidelines for Residents (2022): Balanced Diet Criteria [J]. Disease Prevention and Control Bulletin, 2024, 39(01):95.
[3] Xie Jianxiu, Chen Shuiqiong, Ye Cuihua, Hu Yanping. Analysis of the impact of community nursing intervention on the quality of life of elderly patients with hypertension [J]. Contemporary Medicine, 2013, 19(09):119-120.
[4] Sun Yanhong. A dietary survey and dietary guidance for 176 patients with hypertension [J]. Journal of Nursing, 2001(08):451-453.
[5] Mancia, G., & Grassi, G. (Eds.). Manual of Hypertension of the European Society of Hypertension (2nd ed.). CRC Press. 2014.
[6] Lin Jinxiu, Wu Kegui. Guidelines for the treatment of hypertension by the World Health Organization/International Society of Hypertension in 1999 [J]. Journal of Hypertension, 1999(02):4-7.
[7] Zhang Lina, Chen Jian'er, Zhang Tao, et al. Investigation on the prevalence characteristics and related factors of hypertension [J]. Chinese Journal of Public Health, 2006(01):93-94.
[8] Shi Ye-Wen, Ma Li-Na, Zhu Si-Min, et al. Construction of OSA-related hypertension prediction model based on line chart [J]. Journal of Clinical Otolaryngology - Head and Neck Surgery, 2024, 38(11): 1024-1030+1037.
[9] Wu Jingjie, Yang Lili. Research progress of machine learning in building hypertension risk model [J]. Nursing and Rehabilitation, 2019, 20(02):33-36.
[10] Wu X, Yuan X, Wang W, et al. Value of a Machine Learning Approach for Predicting Clinical Outcomes in Young Patients With Hypertension. Hypertension. 2020; 75(5):1271-1278.
[11] Adeleke O ,Adebayo S ,Aworinde H , et al. Machine learning evaluation of a hypertension screening program in a university workforce over five years.[J]. Scientific reports, 2024, 14(1):30255.
[12] Jeong, Yong Whi; Jung, Yeojin. Prediction Model for Hypertension and Diabetes Mellitus Using Korean Public Health Examination Data (2002–2017) [J]. Diagnostics (Basel), 2022, Aug.
[13] Chang, W. A Machine-Learning-Based Prediction Method for Hypertension Outcomes Based on Medical Data [J]. Diagnostics, 2019, 9: 178. DOI: 10.3390/diagnostics9040178. 
[14] Lundberg, Scott M., and Su-In Lee. "A unified approach to interpreting model predictions." Advances in neural information processing systems 30. 2017.
[15] Shapley, Lloyd S., A Value for N-Person Games. Santa Monica, CA: RAND Corporation, 1952. 
[16] S. Lundberg, G. Erion, S. Lee. Consistent Individualized Feature Attribution for Tree Ensembles. arXiv, 2018.  
[17] Zhang Xiaoyu, Li Fengri, Zhen Zhen, et al. Forest vegetation classification of land satellite-8 remote sensing images based on random forest model [J]. Journal of Northeast Forestry University, 2016, 44(06): 53-57+74.

Sponsors, Associates, and Links

---

• Information Systems and Economics
  
  
• Accounting, Auditing and Finance
  
  
• Industrial Engineering and Innovation Management
  
  
• Tourism Management and Technology Economy
  
  
• Journal of Computational and Financial Econometrics
  
  
• Financial Engineering and Risk Management
  
  
• Accounting and Corporate Management
  
  
• Social Security and Administration Management
  
  
• Population, Resources & Environmental Economics
  
  
• Statistics & Quantitative Economics
  
  
• Agricultural & Forestry Economics and Management
  
  
• Land Resource Management
  
  
• Information, Library and Archival Science
  
  
• Journal of Human Resource Development
  
  
• Manufacturing and Service Operations Management
  
  
• Operational Research and Cybernetics