Machine learning approach to predict body weight in adults
BackgroundObesity is an established risk factor for non-communicable diseases such as type 2 diabetes mellitus, hypertension and cardiovascular disease. Thus, weight control is a key factor in the prevention of non-communicable diseases. A simple and quick method to predict weight change over a few...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1090146/full |
| _version_ | 1797803968481460224 |
|---|---|
| author | Kazuya Fujihara Mayuko Yamada Harada Chika Horikawa Midori Iwanaga Hirofumi Tanaka Hitoshi Nomura Yasuharu Sui Kyouhei Tanabe Takaho Yamada Satoru Kodama Kiminori Kato Hirohito Sone |
| author_facet | Kazuya Fujihara Mayuko Yamada Harada Chika Horikawa Midori Iwanaga Hirofumi Tanaka Hitoshi Nomura Yasuharu Sui Kyouhei Tanabe Takaho Yamada Satoru Kodama Kiminori Kato Hirohito Sone |
| author_sort | Kazuya Fujihara |
| collection | DOAJ |
| description | BackgroundObesity is an established risk factor for non-communicable diseases such as type 2 diabetes mellitus, hypertension and cardiovascular disease. Thus, weight control is a key factor in the prevention of non-communicable diseases. A simple and quick method to predict weight change over a few years could be helpful for weight management in clinical settings.MethodsWe examined the ability of a machine learning model that we constructed to predict changes in future body weight over 3 years using big data. Input in the machine learning model were three-year data on 50,000 Japanese persons (32,977 men) aged 19–91 years who underwent annual health examinations. The predictive formulas that used heterogeneous mixture learning technology (HMLT) to predict body weight in the subsequent 3 years were validated for 5,000 persons. The root mean square error (RMSE) was used to evaluate accuracy compared with multiple regression.ResultsThe machine learning model utilizing HMLT automatically generated five predictive formulas. The influence of lifestyle on body weight was found to be large in people with a high body mass index (BMI) at baseline (BMI ≥29.93 kg/m2) and in young people (<24 years) with a low BMI (BMI <23.44 kg/m2). The RMSE was 1.914 in the validation set which reflects ability comparable to that of the multiple regression model of 1.890 (p = 0.323).ConclusionThe HMLT-based machine learning model could successfully predict weight change over 3 years. Our model could automatically identify groups whose lifestyle profoundly impacted weight loss and factors the influenced body weight change in individuals. Although this model must be validated in other populations, including other ethnic groups, before being widely implemented in global clinical settings, results suggested that this machine learning model could contribute to individualized weight management. |
| first_indexed | 2024-03-13T05:30:04Z |
| format | Article |
| id | doaj.art-04ea4761289944afbddd1829006008e4 |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-03-13T05:30:04Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-04ea4761289944afbddd1829006008e42023-06-15T04:46:27ZengFrontiers Media S.A.Frontiers in Public Health2296-25652023-06-011110.3389/fpubh.2023.10901461090146Machine learning approach to predict body weight in adultsKazuya Fujihara0Mayuko Yamada Harada1Chika Horikawa2Midori Iwanaga3Hirofumi Tanaka4Hitoshi Nomura5Yasuharu Sui6Kyouhei Tanabe7Takaho Yamada8Satoru Kodama9Kiminori Kato10Hirohito Sone11Department of Endocrinology and Metabolism, Faculty of Medicine, Niigata University, Niigata, JapanDepartment of Endocrinology and Metabolism, Faculty of Medicine, Niigata University, Niigata, JapanDepartment of Health and Nutrition, Faculty of Human Life Studies, University of Niigata Prefecture, Niigata, JapanDepartment of Endocrinology and Metabolism, Faculty of Medicine, Niigata University, Niigata, JapanNEC Solution Innovators, Ltd., Tokyo, JapanNEC Solution Innovators, Ltd., Tokyo, JapanNEC Solution Innovators, Ltd., Tokyo, JapanNEC Solution Innovators, Ltd., Tokyo, JapanDepartment of Endocrinology and Metabolism, Faculty of Medicine, Niigata University, Niigata, JapanDepartment of Endocrinology and Metabolism, Faculty of Medicine, Niigata University, Niigata, JapanDepartment of Prevention of Noncommunicable Diseases and Promotion of Health Checkup, Niigata University, Niigata, JapanDepartment of Endocrinology and Metabolism, Faculty of Medicine, Niigata University, Niigata, JapanBackgroundObesity is an established risk factor for non-communicable diseases such as type 2 diabetes mellitus, hypertension and cardiovascular disease. Thus, weight control is a key factor in the prevention of non-communicable diseases. A simple and quick method to predict weight change over a few years could be helpful for weight management in clinical settings.MethodsWe examined the ability of a machine learning model that we constructed to predict changes in future body weight over 3 years using big data. Input in the machine learning model were three-year data on 50,000 Japanese persons (32,977 men) aged 19–91 years who underwent annual health examinations. The predictive formulas that used heterogeneous mixture learning technology (HMLT) to predict body weight in the subsequent 3 years were validated for 5,000 persons. The root mean square error (RMSE) was used to evaluate accuracy compared with multiple regression.ResultsThe machine learning model utilizing HMLT automatically generated five predictive formulas. The influence of lifestyle on body weight was found to be large in people with a high body mass index (BMI) at baseline (BMI ≥29.93 kg/m2) and in young people (<24 years) with a low BMI (BMI <23.44 kg/m2). The RMSE was 1.914 in the validation set which reflects ability comparable to that of the multiple regression model of 1.890 (p = 0.323).ConclusionThe HMLT-based machine learning model could successfully predict weight change over 3 years. Our model could automatically identify groups whose lifestyle profoundly impacted weight loss and factors the influenced body weight change in individuals. Although this model must be validated in other populations, including other ethnic groups, before being widely implemented in global clinical settings, results suggested that this machine learning model could contribute to individualized weight management.https://www.frontiersin.org/articles/10.3389/fpubh.2023.1090146/fullbody weightpredictionmachine learning modelheterogeneous mixture learning technologybody mass index |
| spellingShingle | Kazuya Fujihara Mayuko Yamada Harada Chika Horikawa Midori Iwanaga Hirofumi Tanaka Hitoshi Nomura Yasuharu Sui Kyouhei Tanabe Takaho Yamada Satoru Kodama Kiminori Kato Hirohito Sone Machine learning approach to predict body weight in adults Frontiers in Public Health body weight prediction machine learning model heterogeneous mixture learning technology body mass index |
| title | Machine learning approach to predict body weight in adults |
| title_full | Machine learning approach to predict body weight in adults |
| title_fullStr | Machine learning approach to predict body weight in adults |
| title_full_unstemmed | Machine learning approach to predict body weight in adults |
| title_short | Machine learning approach to predict body weight in adults |
| title_sort | machine learning approach to predict body weight in adults |
| topic | body weight prediction machine learning model heterogeneous mixture learning technology body mass index |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1090146/full |
| work_keys_str_mv | AT kazuyafujihara machinelearningapproachtopredictbodyweightinadults AT mayukoyamadaharada machinelearningapproachtopredictbodyweightinadults AT chikahorikawa machinelearningapproachtopredictbodyweightinadults AT midoriiwanaga machinelearningapproachtopredictbodyweightinadults AT hirofumitanaka machinelearningapproachtopredictbodyweightinadults AT hitoshinomura machinelearningapproachtopredictbodyweightinadults AT yasuharusui machinelearningapproachtopredictbodyweightinadults AT kyouheitanabe machinelearningapproachtopredictbodyweightinadults AT takahoyamada machinelearningapproachtopredictbodyweightinadults AT satorukodama machinelearningapproachtopredictbodyweightinadults AT kiminorikato machinelearningapproachtopredictbodyweightinadults AT hirohitosone machinelearningapproachtopredictbodyweightinadults |