Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study
Junli Zhang,1,* Zhenghui Xu,1,* Yu Fu,2,* Lu Chen1,2 1Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Soochow University, Changzhou, People’s Republic of China; 2Department of Clinical Nutrition, The Third Affiliated Hospital of Soochow University...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2023-09-01
|
| Series: | Diabetes, Metabolic Syndrome and Obesity |
| Subjects: | |
| Online Access: | https://www.dovepress.com/prediction-of-the-risk-of-bone-mineral-density-decrease-in-type-2-diab-peer-reviewed-fulltext-article-DMSO |
| _version_ | 1797678117477679104 |
|---|---|
| author | Zhang J Xu Z Fu Y Chen L |
| author_facet | Zhang J Xu Z Fu Y Chen L |
| author_sort | Zhang J |
| collection | DOAJ |
| description | Junli Zhang,1,* Zhenghui Xu,1,* Yu Fu,2,* Lu Chen1,2 1Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Soochow University, Changzhou, People’s Republic of China; 2Department of Clinical Nutrition, The Third Affiliated Hospital of Soochow University, Changzhou, People’s Republic of China*These authors contributed equally to this workCorrespondence: Lu Chen, Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Soochow University, Changzhou, 213003, People’s Republic of China, Tel +86 0519-68870424, Email chenluforever@163.comPurpose: There remains a lack of a machine learning (ML) model incorporating body composition to assess the risk of bone mineral density (BMD) decreases in type 2 diabetes mellitus (T2DM) patients. We aimed to use ML algorithms and the traditional multivariate logistic regression to establish prediction models for BMD decreases in T2DM patients over 50 years of age, and compare the performance of the two methods.Patients and Methods: This cross-sectional study was conducted among 450 patients with T2DM from 1 August 2016 to 31 December 2022. The participants were divided into a normal BMD group and a decreased BMD group. Traditional multivariate logistic regression and six ML algorithms were selected to construct male and female models. Two nomograms were constructed to evaluate the risk of BMD decreases in the male and female T2DM patients, respectively. The ML models with the highest area under the curve (AUC) were compared with the traditional multivariate logistic regression models in terms of discriminant ability and clinical applicability.Results: The optimal ML model was the extreme gradient boost (XGBoost) model. The AUCs of the traditional multivariate logistic regression and the XGBoost models were 0.722 and 0.800 in the male testing dataset, respectively, and 0.876 and 0.880 in the female testing dataset, respectively. The decision curve analysis results suggested that using the XGBoost models to predict the risk of BMD decreases obtained more net benefits compared with the traditional models in both sexes.Conclusion: We preliminarily proved that the XGBoost models outperformed most other ML models in both sexes and achieved higher accuracy than traditional analyses. Due to the limited sample size in the study, it is necessary to validate our findings in larger prospective cohort studies.Keywords: type 2 diabetes mellitus, bone mineral density decrease, prediction model, machine learning, nomogram |
| first_indexed | 2024-03-11T22:55:01Z |
| format | Article |
| id | doaj.art-d04dc54688264c1ca031105ba942e761 |
| institution | Directory Open Access Journal |
| issn | 1178-7007 |
| language | English |
| last_indexed | 2024-03-11T22:55:01Z |
| publishDate | 2023-09-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Diabetes, Metabolic Syndrome and Obesity |
| spelling | doaj.art-d04dc54688264c1ca031105ba942e7612023-09-21T19:08:59ZengDove Medical PressDiabetes, Metabolic Syndrome and Obesity1178-70072023-09-01Volume 162885289886799Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary StudyZhang JXu ZFu YChen LJunli Zhang,1,* Zhenghui Xu,1,* Yu Fu,2,* Lu Chen1,2 1Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Soochow University, Changzhou, People’s Republic of China; 2Department of Clinical Nutrition, The Third Affiliated Hospital of Soochow University, Changzhou, People’s Republic of China*These authors contributed equally to this workCorrespondence: Lu Chen, Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Soochow University, Changzhou, 213003, People’s Republic of China, Tel +86 0519-68870424, Email chenluforever@163.comPurpose: There remains a lack of a machine learning (ML) model incorporating body composition to assess the risk of bone mineral density (BMD) decreases in type 2 diabetes mellitus (T2DM) patients. We aimed to use ML algorithms and the traditional multivariate logistic regression to establish prediction models for BMD decreases in T2DM patients over 50 years of age, and compare the performance of the two methods.Patients and Methods: This cross-sectional study was conducted among 450 patients with T2DM from 1 August 2016 to 31 December 2022. The participants were divided into a normal BMD group and a decreased BMD group. Traditional multivariate logistic regression and six ML algorithms were selected to construct male and female models. Two nomograms were constructed to evaluate the risk of BMD decreases in the male and female T2DM patients, respectively. The ML models with the highest area under the curve (AUC) were compared with the traditional multivariate logistic regression models in terms of discriminant ability and clinical applicability.Results: The optimal ML model was the extreme gradient boost (XGBoost) model. The AUCs of the traditional multivariate logistic regression and the XGBoost models were 0.722 and 0.800 in the male testing dataset, respectively, and 0.876 and 0.880 in the female testing dataset, respectively. The decision curve analysis results suggested that using the XGBoost models to predict the risk of BMD decreases obtained more net benefits compared with the traditional models in both sexes.Conclusion: We preliminarily proved that the XGBoost models outperformed most other ML models in both sexes and achieved higher accuracy than traditional analyses. Due to the limited sample size in the study, it is necessary to validate our findings in larger prospective cohort studies.Keywords: type 2 diabetes mellitus, bone mineral density decrease, prediction model, machine learning, nomogramhttps://www.dovepress.com/prediction-of-the-risk-of-bone-mineral-density-decrease-in-type-2-diab-peer-reviewed-fulltext-article-DMSOtype 2 diabetes mellitusbone mineral density decreaseprediction modelmachine learningnomogram |
| spellingShingle | Zhang J Xu Z Fu Y Chen L Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study Diabetes, Metabolic Syndrome and Obesity type 2 diabetes mellitus bone mineral density decrease prediction model machine learning nomogram |
| title | Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study |
| title_full | Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study |
| title_fullStr | Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study |
| title_full_unstemmed | Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study |
| title_short | Prediction of the Risk of Bone Mineral Density Decrease in Type 2 Diabetes Mellitus Patients Based on Traditional Multivariate Logistic Regression and Machine Learning: A Preliminary Study |
| title_sort | prediction of the risk of bone mineral density decrease in type 2 diabetes mellitus patients based on traditional multivariate logistic regression and machine learning a preliminary study |
| topic | type 2 diabetes mellitus bone mineral density decrease prediction model machine learning nomogram |
| url | https://www.dovepress.com/prediction-of-the-risk-of-bone-mineral-density-decrease-in-type-2-diab-peer-reviewed-fulltext-article-DMSO |
| work_keys_str_mv | AT zhangj predictionoftheriskofbonemineraldensitydecreaseintype2diabetesmellituspatientsbasedontraditionalmultivariatelogisticregressionandmachinelearningapreliminarystudy AT xuz predictionoftheriskofbonemineraldensitydecreaseintype2diabetesmellituspatientsbasedontraditionalmultivariatelogisticregressionandmachinelearningapreliminarystudy AT fuy predictionoftheriskofbonemineraldensitydecreaseintype2diabetesmellituspatientsbasedontraditionalmultivariatelogisticregressionandmachinelearningapreliminarystudy AT chenl predictionoftheriskofbonemineraldensitydecreaseintype2diabetesmellituspatientsbasedontraditionalmultivariatelogisticregressionandmachinelearningapreliminarystudy |