Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms
ObjectiveThe prevention of hypertension in primary care requires an effective and suitable hypertension risk assessment model. The aim of this study was to develop and compare the performances of three machine learning algorithms in predicting the risk of hypertension for residents in primary care i...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2022.984621/full |
| _version_ | 1817980749460013056 |
|---|---|
| author | Ning Chen Feng Fan Jinsong Geng Yan Yang Ya Gao Hua Jin Hua Jin Hua Jin Hua Jin Qiao Chu Dehua Yu Dehua Yu Dehua Yu Dehua Yu Zhaoxin Wang Zhaoxin Wang Zhaoxin Wang Jianwei Shi Jianwei Shi Jianwei Shi |
| author_facet | Ning Chen Feng Fan Jinsong Geng Yan Yang Ya Gao Hua Jin Hua Jin Hua Jin Hua Jin Qiao Chu Dehua Yu Dehua Yu Dehua Yu Dehua Yu Zhaoxin Wang Zhaoxin Wang Zhaoxin Wang Jianwei Shi Jianwei Shi Jianwei Shi |
| author_sort | Ning Chen |
| collection | DOAJ |
| description | ObjectiveThe prevention of hypertension in primary care requires an effective and suitable hypertension risk assessment model. The aim of this study was to develop and compare the performances of three machine learning algorithms in predicting the risk of hypertension for residents in primary care in Shanghai, China.MethodsA dataset of 40,261 subjects over the age of 35 years was extracted from Electronic Healthcare Records of 47 community health centers from 2017 to 2019 in the Pudong district of Shanghai. Embedded methods were applied for feature selection. Machine learning algorithms, XGBoost, random forest, and logistic regression analyses were adopted in the process of model construction. The performance of models was evaluated by calculating the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, accuracy and F1-score.ResultsThe XGBoost model outperformed the other two models and achieved an AUC of 0.765 in the testing set. Twenty features were selected to construct the model, including age, diabetes status, urinary protein level, BMI, elderly health self-assessment, creatinine level, systolic blood pressure measured on the upper right arm, waist circumference, smoking status, low-density lipoprotein cholesterol level, high-density lipoprotein cholesterol level, frequency of drinking, glucose level, urea nitrogen level, total cholesterol level, diastolic blood pressure measured on the upper right arm, exercise frequency, time spent engaged in exercise, high salt consumption, and triglyceride level.ConclusionsXGBoost outperformed random forest and logistic regression in predicting the risk of hypertension in primary care. The integration of this risk assessment model into primary care facilities may improve the prevention and management of hypertension in residents. |
| first_indexed | 2024-04-13T22:57:14Z |
| format | Article |
| id | doaj.art-f5943b20acc74e3e96d383c9fca64d57 |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-04-13T22:57:14Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-f5943b20acc74e3e96d383c9fca64d572022-12-22T02:25:58ZengFrontiers Media S.A.Frontiers in Public Health2296-25652022-10-011010.3389/fpubh.2022.984621984621Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithmsNing Chen0Feng Fan1Jinsong Geng2Yan Yang3Ya Gao4Hua Jin5Hua Jin6Hua Jin7Hua Jin8Qiao Chu9Dehua Yu10Dehua Yu11Dehua Yu12Dehua Yu13Zhaoxin Wang14Zhaoxin Wang15Zhaoxin Wang16Jianwei Shi17Jianwei Shi18Jianwei Shi19School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaSchool of Medicine, Tongji University, Shanghai, ChinaSchool of Medicine, Nantong University, Nantong, ChinaSchool of Economics and Management, Tongji University, Shanghai, ChinaSchool of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of General Practice, Yangpu Hospital, Tongji University School of Medicine, Shanghai, ChinaShanghai General Practice and Community Health Development Research Center, Shanghai, ChinaAcademic Department of General Practice, Tongji University School of Medicine, Shanghai, ChinaClinical Research Center for General Practice, Tongji University, Shanghai, ChinaSchool of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of General Practice, Yangpu Hospital, Tongji University School of Medicine, Shanghai, ChinaShanghai General Practice and Community Health Development Research Center, Shanghai, ChinaAcademic Department of General Practice, Tongji University School of Medicine, Shanghai, ChinaClinical Research Center for General Practice, Tongji University, Shanghai, ChinaThe First Affiliated Hospital of Hainan Medical University, Haikou, China0Department of Social Medicine and Health Management, School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China1School of Management, Hainan Medical University, Haikou, ChinaDepartment of General Practice, Yangpu Hospital, Tongji University School of Medicine, Shanghai, ChinaShanghai General Practice and Community Health Development Research Center, Shanghai, China0Department of Social Medicine and Health Management, School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaObjectiveThe prevention of hypertension in primary care requires an effective and suitable hypertension risk assessment model. The aim of this study was to develop and compare the performances of three machine learning algorithms in predicting the risk of hypertension for residents in primary care in Shanghai, China.MethodsA dataset of 40,261 subjects over the age of 35 years was extracted from Electronic Healthcare Records of 47 community health centers from 2017 to 2019 in the Pudong district of Shanghai. Embedded methods were applied for feature selection. Machine learning algorithms, XGBoost, random forest, and logistic regression analyses were adopted in the process of model construction. The performance of models was evaluated by calculating the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, accuracy and F1-score.ResultsThe XGBoost model outperformed the other two models and achieved an AUC of 0.765 in the testing set. Twenty features were selected to construct the model, including age, diabetes status, urinary protein level, BMI, elderly health self-assessment, creatinine level, systolic blood pressure measured on the upper right arm, waist circumference, smoking status, low-density lipoprotein cholesterol level, high-density lipoprotein cholesterol level, frequency of drinking, glucose level, urea nitrogen level, total cholesterol level, diastolic blood pressure measured on the upper right arm, exercise frequency, time spent engaged in exercise, high salt consumption, and triglyceride level.ConclusionsXGBoost outperformed random forest and logistic regression in predicting the risk of hypertension in primary care. The integration of this risk assessment model into primary care facilities may improve the prevention and management of hypertension in residents.https://www.frontiersin.org/articles/10.3389/fpubh.2022.984621/fullhypertensionrisk assessment modelrisk of hypertensionmachine learning algorithmsprimary care |
| spellingShingle | Ning Chen Feng Fan Jinsong Geng Yan Yang Ya Gao Hua Jin Hua Jin Hua Jin Hua Jin Qiao Chu Dehua Yu Dehua Yu Dehua Yu Dehua Yu Zhaoxin Wang Zhaoxin Wang Zhaoxin Wang Jianwei Shi Jianwei Shi Jianwei Shi Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms Frontiers in Public Health hypertension risk assessment model risk of hypertension machine learning algorithms primary care |
| title | Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms |
| title_full | Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms |
| title_fullStr | Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms |
| title_full_unstemmed | Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms |
| title_short | Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms |
| title_sort | evaluating the risk of hypertension in residents in primary care in shanghai china with machine learning algorithms |
| topic | hypertension risk assessment model risk of hypertension machine learning algorithms primary care |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2022.984621/full |
| work_keys_str_mv | AT ningchen evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT fengfan evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT jinsonggeng evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT yanyang evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT yagao evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT huajin evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT huajin evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT huajin evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT huajin evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT qiaochu evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT dehuayu evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT dehuayu evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT dehuayu evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT dehuayu evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT zhaoxinwang evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT zhaoxinwang evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT zhaoxinwang evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT jianweishi evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT jianweishi evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms AT jianweishi evaluatingtheriskofhypertensioninresidentsinprimarycareinshanghaichinawithmachinelearningalgorithms |