Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey
Background: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteris...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Komiyama Printing Co. Ltd
2025-01-01
|
| Series: | Environmental Health and Preventive Medicine |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/ehpm/30/0/30_24-00270/_html/-char/en |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582311918436352 |
|---|---|
| author | Manhui Zhang Xian Xia Qiqi Wang Yue Pan Guanyi Zhang Zhigang Wang |
| author_facet | Manhui Zhang Xian Xia Qiqi Wang Yue Pan Guanyi Zhang Zhigang Wang |
| author_sort | Manhui Zhang |
| collection | DOAJ |
| description | Background: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteristics of patients with new onset hypertension. Methods: We analyzed data from the 2011 China Health and Nutrition Survey cohort of individuals who were not hypertensive at baseline and had follow-up results available for prediction by 2015. We tested and evaluated the performance of four traditional machine learning algorithms commonly used in epidemiological studies: Logistic Regression, Support Vector Machine, XGBoost, LightGBM, and two deep learning algorithms: TabNet and AMFormer model. We modeled using 16 and 29 features, respectively. SHAP values were applied to select key features associated with new onset hypertension. Results: A total of 4,982 participants were included in the analysis, of whom 1,017 developed hypertension during the 4-year follow-up. Among the 16-feature models, Logistic Regression had the highest AUC of 0.784(0.775∼0.806). In the 29-feature prediction models, AMFormer performed the best with an AUC of 0.802(0.795∼0.820), and also scored the highest in MCC (0.417, 95%CI: 0.400∼0.434) and F1 (0.503, 95%CI: 0.484∼0.505) metrics, demonstrating superior overall performance compared to the other models. Additionally, key features selected based on the AMFormer, such as age, province, waist circumference, urban or rural location, education level, employment status, weight, WHR, and BMI, played significant roles. Conclusion: We used the AMFormer model for the first time in predicting new onset hypertension and achieved the best results among the six algorithms tested. Key features associated with new onset hypertension can be determined through this algorithm. The practice of machine learning algorithms can further enhance the predictive efficacy of diseases and identify risk factors for diseases. |
| format | Article |
| id | doaj-art-77aca0397fe94f35a08d254092cb2332 |
| institution | Kabale University |
| issn | 1342-078X 1347-4715 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Komiyama Printing Co. Ltd |
| record_format | Article |
| series | Environmental Health and Preventive Medicine |
| spelling | doaj-art-77aca0397fe94f35a08d254092cb23322025-01-30T00:05:38ZengKomiyama Printing Co. LtdEnvironmental Health and Preventive Medicine1342-078X1347-47152025-01-01303310.1265/ehpm.24-00270ehpmApplication of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition SurveyManhui Zhang0Xian Xia1Qiqi Wang2Yue Pan3Guanyi Zhang4Zhigang Wang5Department of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General HospitalDepartment of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General HospitalOffice of Epidemiology (Technical Guidance Office for Patriotic Health Work), Chinese Center for Disease Control and PreventionDepartment of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General HospitalDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical UniversityDepartment of Disease Control and Prevention, The Seventh Medical Center of Chinese PLA General HospitalBackground: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteristics of patients with new onset hypertension. Methods: We analyzed data from the 2011 China Health and Nutrition Survey cohort of individuals who were not hypertensive at baseline and had follow-up results available for prediction by 2015. We tested and evaluated the performance of four traditional machine learning algorithms commonly used in epidemiological studies: Logistic Regression, Support Vector Machine, XGBoost, LightGBM, and two deep learning algorithms: TabNet and AMFormer model. We modeled using 16 and 29 features, respectively. SHAP values were applied to select key features associated with new onset hypertension. Results: A total of 4,982 participants were included in the analysis, of whom 1,017 developed hypertension during the 4-year follow-up. Among the 16-feature models, Logistic Regression had the highest AUC of 0.784(0.775∼0.806). In the 29-feature prediction models, AMFormer performed the best with an AUC of 0.802(0.795∼0.820), and also scored the highest in MCC (0.417, 95%CI: 0.400∼0.434) and F1 (0.503, 95%CI: 0.484∼0.505) metrics, demonstrating superior overall performance compared to the other models. Additionally, key features selected based on the AMFormer, such as age, province, waist circumference, urban or rural location, education level, employment status, weight, WHR, and BMI, played significant roles. Conclusion: We used the AMFormer model for the first time in predicting new onset hypertension and achieved the best results among the six algorithms tested. Key features associated with new onset hypertension can be determined through this algorithm. The practice of machine learning algorithms can further enhance the predictive efficacy of diseases and identify risk factors for diseases.https://www.jstage.jst.go.jp/article/ehpm/30/0/30_24-00270/_html/-char/enmachine learning algorithmspredictionnew onset hypertensionchns |
| spellingShingle | Manhui Zhang Xian Xia Qiqi Wang Yue Pan Guanyi Zhang Zhigang Wang Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey Environmental Health and Preventive Medicine machine learning algorithms prediction new onset hypertension chns |
| title | Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey |
| title_full | Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey |
| title_fullStr | Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey |
| title_full_unstemmed | Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey |
| title_short | Application of machine learning algorithms in predicting new onset hypertension: a study based on the China Health and Nutrition Survey |
| title_sort | application of machine learning algorithms in predicting new onset hypertension a study based on the china health and nutrition survey |
| topic | machine learning algorithms prediction new onset hypertension chns |
| url | https://www.jstage.jst.go.jp/article/ehpm/30/0/30_24-00270/_html/-char/en |
| work_keys_str_mv | AT manhuizhang applicationofmachinelearningalgorithmsinpredictingnewonsethypertensionastudybasedonthechinahealthandnutritionsurvey AT xianxia applicationofmachinelearningalgorithmsinpredictingnewonsethypertensionastudybasedonthechinahealthandnutritionsurvey AT qiqiwang applicationofmachinelearningalgorithmsinpredictingnewonsethypertensionastudybasedonthechinahealthandnutritionsurvey AT yuepan applicationofmachinelearningalgorithmsinpredictingnewonsethypertensionastudybasedonthechinahealthandnutritionsurvey AT guanyizhang applicationofmachinelearningalgorithmsinpredictingnewonsethypertensionastudybasedonthechinahealthandnutritionsurvey AT zhigangwang applicationofmachinelearningalgorithmsinpredictingnewonsethypertensionastudybasedonthechinahealthandnutritionsurvey |