Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning
Abstract Background Diabetic peripheral neuropathy (DPN) is a common complication of diabetes. Predicting the risk of developing DPN is important for clinical decision-making and designing clinical trials. Methods We retrospectively reviewed the data of 1278 patients with diabetes treated in two cen...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-08-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-023-02232-1 |
| _version_ | 1797752680590868480 |
|---|---|
| author | Xiaoyang Lian Juanzhi Qi Mengqian Yuan Xiaojie Li Ming Wang Gang Li Tao Yang Jingchen Zhong |
| author_facet | Xiaoyang Lian Juanzhi Qi Mengqian Yuan Xiaojie Li Ming Wang Gang Li Tao Yang Jingchen Zhong |
| author_sort | Xiaoyang Lian |
| collection | DOAJ |
| description | Abstract Background Diabetic peripheral neuropathy (DPN) is a common complication of diabetes. Predicting the risk of developing DPN is important for clinical decision-making and designing clinical trials. Methods We retrospectively reviewed the data of 1278 patients with diabetes treated in two central hospitals from 2020 to 2022. The data included medical history, physical examination, and biochemical index test results. After feature selection and data balancing, the cohort was divided into training and internal validation datasets at a 7:3 ratio. Training was made in logistic regression, k-nearest neighbor, decision tree, naive bayes, random forest, and extreme gradient boosting (XGBoost) based on machine learning. The k-fold cross-validation was used for model assessment, and the accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC) were adopted to validate the models’ discrimination and clinical practicality. The SHapley Additive exPlanation (SHAP) was used to interpret the best-performing model. Results The XGBoost model outperformed other models, which had an accuracy of 0·746, precision of 0·765, recall of 0·711, F1-score of 0·736, and AUC of 0·813. The SHAP results indicated that age, disease duration, glycated hemoglobin, insulin resistance index, 24-h urine protein quantification, and urine protein concentration were risk factors for DPN, while the ratio between 2-h postprandial C-peptide and fasting C-peptide(C2/C0), total cholesterol, activated partial thromboplastin time, and creatinine were protective factors. Conclusions The machine learning approach helped established a DPN risk prediction model with good performance. The model identified the factors most closely related to DPN. |
| first_indexed | 2024-03-12T17:08:02Z |
| format | Article |
| id | doaj.art-34065995f567463da74982005307aab8 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-03-12T17:08:02Z |
| publishDate | 2023-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-34065995f567463da74982005307aab82023-08-06T11:16:37ZengBMCBMC Medical Informatics and Decision Making1472-69472023-08-0123111210.1186/s12911-023-02232-1Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learningXiaoyang Lian0Juanzhi Qi1Mengqian Yuan2Xiaojie Li3Ming Wang4Gang Li5Tao Yang6Jingchen Zhong7Affiliated Hospital of Nanjing University of Chinese Medicine，Jiangsu Province Hospital of Chinese MedicineSchool of Artificial Intelligence and Information Technology, Nanjing University of Chinese MedicineAffiliated Hospital of Nanjing University of Chinese Medicine，Jiangsu Province Hospital of Chinese MedicineJiangsu Health Vocational CollegeGeriatric Hospital of Nanjing Medical University, Jiangsu Province Official HospitalSchool of Artificial Intelligence and Information Technology, Nanjing University of Chinese MedicineSchool of Artificial Intelligence and Information Technology, Nanjing University of Chinese MedicineAffiliated Hospital of Nanjing University of Chinese Medicine，Jiangsu Province Hospital of Chinese MedicineAbstract Background Diabetic peripheral neuropathy (DPN) is a common complication of diabetes. Predicting the risk of developing DPN is important for clinical decision-making and designing clinical trials. Methods We retrospectively reviewed the data of 1278 patients with diabetes treated in two central hospitals from 2020 to 2022. The data included medical history, physical examination, and biochemical index test results. After feature selection and data balancing, the cohort was divided into training and internal validation datasets at a 7:3 ratio. Training was made in logistic regression, k-nearest neighbor, decision tree, naive bayes, random forest, and extreme gradient boosting (XGBoost) based on machine learning. The k-fold cross-validation was used for model assessment, and the accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC) were adopted to validate the models’ discrimination and clinical practicality. The SHapley Additive exPlanation (SHAP) was used to interpret the best-performing model. Results The XGBoost model outperformed other models, which had an accuracy of 0·746, precision of 0·765, recall of 0·711, F1-score of 0·736, and AUC of 0·813. The SHAP results indicated that age, disease duration, glycated hemoglobin, insulin resistance index, 24-h urine protein quantification, and urine protein concentration were risk factors for DPN, while the ratio between 2-h postprandial C-peptide and fasting C-peptide(C2/C0), total cholesterol, activated partial thromboplastin time, and creatinine were protective factors. Conclusions The machine learning approach helped established a DPN risk prediction model with good performance. The model identified the factors most closely related to DPN.https://doi.org/10.1186/s12911-023-02232-1Machine learningData analysisDiabetesDiabetic peripheral neuropathy |
| spellingShingle | Xiaoyang Lian Juanzhi Qi Mengqian Yuan Xiaojie Li Ming Wang Gang Li Tao Yang Jingchen Zhong Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning BMC Medical Informatics and Decision Making Machine learning Data analysis Diabetes Diabetic peripheral neuropathy |
| title | Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning |
| title_full | Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning |
| title_fullStr | Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning |
| title_full_unstemmed | Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning |
| title_short | Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning |
| title_sort | study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning |
| topic | Machine learning Data analysis Diabetes Diabetic peripheral neuropathy |
| url | https://doi.org/10.1186/s12911-023-02232-1 |
| work_keys_str_mv | AT xiaoyanglian studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT juanzhiqi studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT mengqianyuan studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT xiaojieli studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT mingwang studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT gangli studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT taoyang studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning AT jingchenzhong studyonriskfactorsofdiabeticperipheralneuropathyandestablishmentofapredictionmodelbymachinelearning |