Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study
Objectives Sufficient attention has not been given to machine learning (ML) models using longitudinal data for investigating important predictors of new onset of hypertension. We investigated the predictive ability of several ML models for the development of hypertension.Methods A total of 15 965 Ja...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Clinical and Experimental Hypertension |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10641963.2025.2449613 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554161398710272 |
|---|---|
| author | Marenao Tanaka Yukinori Akiyama Kazuma Mori Itaru Hosaka Keisuke Endo Toshifumi Ogawa Tatsuya Sato Toru Suzuki Toshiyuki Yano Hirofumi Ohnishi Nagisa Hanawa Masato Furuhashi |
| author_facet | Marenao Tanaka Yukinori Akiyama Kazuma Mori Itaru Hosaka Keisuke Endo Toshifumi Ogawa Tatsuya Sato Toru Suzuki Toshiyuki Yano Hirofumi Ohnishi Nagisa Hanawa Masato Furuhashi |
| author_sort | Marenao Tanaka |
| collection | DOAJ |
| description | Objectives Sufficient attention has not been given to machine learning (ML) models using longitudinal data for investigating important predictors of new onset of hypertension. We investigated the predictive ability of several ML models for the development of hypertension.Methods A total of 15 965 Japanese participants (men/women: 9,466/6,499, mean age: 45 years) who received annual health examinations were randomly divided into a training group (70%, n = 11,175) and a test group (30%, n = 4,790). The predictive abilities of 58 candidates including fatty liver index (FLI), which is calculated by using body mass index, waist circumference and levels of γ-glutamyl transferase and triglycerides, were investigated by statistics analogous to the area under the curve (AUC) in receiver operating characteristic curve analyses using ML models including logistic regression, random forest, naïve Bayes, extreme gradient boosting and artificial neural network.Results During a 10-year period (mean period: 6.1 years), 2,132 subjects (19.1%) in the training group and 917 subjects (19.1%) in the test group had new onset of hypertension. Among the 58 parameters, systolic blood pressure, age and FLI were identified as important candidates by random forest feature selection with 10-fold cross-validation. The AUCs of ML models were 0.765–0.825, and discriminatory capacity was significantly improved in the artificial neural network model compared to that in the logistic regression model.Conclusions The development of hypertension can be simply and accurately predicted by each ML model using systolic blood pressure, age and FLI as selected features. By building multiple ML models, more practical prediction might be possible. |
| format | Article |
| id | doaj-art-1cb7488dfcb94d0683bbe775fd4e049c |
| institution | Kabale University |
| issn | 1064-1963 1525-6006 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Clinical and Experimental Hypertension |
| spelling | doaj-art-1cb7488dfcb94d0683bbe775fd4e049c2025-01-08T17:11:17ZengTaylor & Francis GroupClinical and Experimental Hypertension1064-19631525-60062025-12-0147110.1080/10641963.2025.2449613Machine learning-based analyses of contributing factors for the development of hypertension: a comparative studyMarenao Tanaka0Yukinori Akiyama1Kazuma Mori2Itaru Hosaka3Keisuke Endo4Toshifumi Ogawa5Tatsuya Sato6Toru Suzuki7Toshiyuki Yano8Hirofumi Ohnishi9Nagisa Hanawa10Masato Furuhashi11Department of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Neurosurgery, Sapporo Medical University, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Cardiovascular Surgery, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Public Health, Sapporo Medical University School of Medicine, Sapporo, JapanDepartment of Health Checkup and Promotion, Keijinkai Maruyama Clinic, Sapporo, JapanDepartment of Cardiovascular, Renal and Metabolic Medicine, Sapporo Medical University School of Medicine, Sapporo, JapanObjectives Sufficient attention has not been given to machine learning (ML) models using longitudinal data for investigating important predictors of new onset of hypertension. We investigated the predictive ability of several ML models for the development of hypertension.Methods A total of 15 965 Japanese participants (men/women: 9,466/6,499, mean age: 45 years) who received annual health examinations were randomly divided into a training group (70%, n = 11,175) and a test group (30%, n = 4,790). The predictive abilities of 58 candidates including fatty liver index (FLI), which is calculated by using body mass index, waist circumference and levels of γ-glutamyl transferase and triglycerides, were investigated by statistics analogous to the area under the curve (AUC) in receiver operating characteristic curve analyses using ML models including logistic regression, random forest, naïve Bayes, extreme gradient boosting and artificial neural network.Results During a 10-year period (mean period: 6.1 years), 2,132 subjects (19.1%) in the training group and 917 subjects (19.1%) in the test group had new onset of hypertension. Among the 58 parameters, systolic blood pressure, age and FLI were identified as important candidates by random forest feature selection with 10-fold cross-validation. The AUCs of ML models were 0.765–0.825, and discriminatory capacity was significantly improved in the artificial neural network model compared to that in the logistic regression model.Conclusions The development of hypertension can be simply and accurately predicted by each ML model using systolic blood pressure, age and FLI as selected features. By building multiple ML models, more practical prediction might be possible.https://www.tandfonline.com/doi/10.1080/10641963.2025.2449613Artificial intelligencemachine learninghypertensionfatty liver index |
| spellingShingle | Marenao Tanaka Yukinori Akiyama Kazuma Mori Itaru Hosaka Keisuke Endo Toshifumi Ogawa Tatsuya Sato Toru Suzuki Toshiyuki Yano Hirofumi Ohnishi Nagisa Hanawa Masato Furuhashi Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study Clinical and Experimental Hypertension Artificial intelligence machine learning hypertension fatty liver index |
| title | Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study |
| title_full | Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study |
| title_fullStr | Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study |
| title_full_unstemmed | Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study |
| title_short | Machine learning-based analyses of contributing factors for the development of hypertension: a comparative study |
| title_sort | machine learning based analyses of contributing factors for the development of hypertension a comparative study |
| topic | Artificial intelligence machine learning hypertension fatty liver index |
| url | https://www.tandfonline.com/doi/10.1080/10641963.2025.2449613 |
| work_keys_str_mv | AT marenaotanaka machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT yukinoriakiyama machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT kazumamori machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT itaruhosaka machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT keisukeendo machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT toshifumiogawa machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT tatsuyasato machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT torusuzuki machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT toshiyukiyano machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT hirofumiohnishi machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT nagisahanawa machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy AT masatofuruhashi machinelearningbasedanalysesofcontributingfactorsforthedevelopmentofhypertensionacomparativestudy |