An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China
PurposeThis study aimed to develop and validate a novel web-based calculator using machine learning algorithms to predict fragility fracture risk in People living with HIV (PLWH), who face increased morbidity and mortality from such fractures.MethodWe retrospectively analyzed clinical data from Beij...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-03-01
|
| Series: | Frontiers in Cellular and Infection Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcimb.2025.1461740/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850053732893458432 |
|---|---|
| author | Bo Liu Bo Liu Qiang Zhang Qiang Zhang Xin Li Xin Li |
| author_facet | Bo Liu Bo Liu Qiang Zhang Qiang Zhang Xin Li Xin Li |
| author_sort | Bo Liu |
| collection | DOAJ |
| description | PurposeThis study aimed to develop and validate a novel web-based calculator using machine learning algorithms to predict fragility fracture risk in People living with HIV (PLWH), who face increased morbidity and mortality from such fractures.MethodWe retrospectively analyzed clinical data from Beijing Ditan Hospital orthopedic department between 2015 and September 2023. The dataset included 1045 patients (2015-2021) for training and 450 patients (2021-September 2023) for external testing. Feature selection was performed using multivariable logistic regression, LASSO, Boruta, and RFE-RF. Six machine learning models (logistic regression, decision trees, SVM, KNN, random forest, and XGBoost) were trained with 10-fold cross-validation and hyperparameter tuning. Model performance was assessed with ROC curves, Decision Curve Analysis, and other metrics. The optimal model was integrated into an online risk assessment calculator.ResultsThe XGBoost model showed the highest predictive performance, with key features including age, smoking, fall history, TDF use, HIV viral load, vitamin D, hemoglobin, albumin, CD4 count, and lumbar spine BMD. It achieved an ROC-AUC of 0.984 (95% CI: 0.977-0.99) in the training set and 0.979 (95% CI: 0.965-0.992) in the external test set. Decision Curve Analysis indicated clinical utility across various threshold probabilities, with calibration curves showing high concordance between predicted and observed risks. SHAP values explained individual risk profiles. The XGBoostpowered web calculator (https://sydtliubo.shinyapps.io/cls2shiny/) enables clinicians and patients to assess fragility fracture risk in PLWH.ConclusionWe developed a web-based risk assessment tool using the XGBoost algorithm for predicting fragility fractures in HIV-positive patients. This tool, with its high accuracy and interpretability, aids in fracture risk stratification and management, potentially reducing the burden of fragility fractures in the HIV population. |
| format | Article |
| id | doaj-art-0ef1faa5c6484b3ea480d72cdb4f6122 |
| institution | DOAJ |
| issn | 2235-2988 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cellular and Infection Microbiology |
| spelling | doaj-art-0ef1faa5c6484b3ea480d72cdb4f61222025-08-20T02:52:27ZengFrontiers Media S.A.Frontiers in Cellular and Infection Microbiology2235-29882025-03-011510.3389/fcimb.2025.14617401461740An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, ChinaBo Liu0Bo Liu1Qiang Zhang2Qiang Zhang3Xin Li4Xin Li5Department of Orthopaedics, Beijing Ditan Hospital, Capital Medical University, Beijing, ChinaNational Center for Infectious Diseases, Beijing, ChinaDepartment of Orthopaedics, Beijing Ditan Hospital, Capital Medical University, Beijing, ChinaNational Center for Infectious Diseases, Beijing, ChinaDepartment of Orthopaedics, Beijing Ditan Hospital, Capital Medical University, Beijing, ChinaNational Center for Infectious Diseases, Beijing, ChinaPurposeThis study aimed to develop and validate a novel web-based calculator using machine learning algorithms to predict fragility fracture risk in People living with HIV (PLWH), who face increased morbidity and mortality from such fractures.MethodWe retrospectively analyzed clinical data from Beijing Ditan Hospital orthopedic department between 2015 and September 2023. The dataset included 1045 patients (2015-2021) for training and 450 patients (2021-September 2023) for external testing. Feature selection was performed using multivariable logistic regression, LASSO, Boruta, and RFE-RF. Six machine learning models (logistic regression, decision trees, SVM, KNN, random forest, and XGBoost) were trained with 10-fold cross-validation and hyperparameter tuning. Model performance was assessed with ROC curves, Decision Curve Analysis, and other metrics. The optimal model was integrated into an online risk assessment calculator.ResultsThe XGBoost model showed the highest predictive performance, with key features including age, smoking, fall history, TDF use, HIV viral load, vitamin D, hemoglobin, albumin, CD4 count, and lumbar spine BMD. It achieved an ROC-AUC of 0.984 (95% CI: 0.977-0.99) in the training set and 0.979 (95% CI: 0.965-0.992) in the external test set. Decision Curve Analysis indicated clinical utility across various threshold probabilities, with calibration curves showing high concordance between predicted and observed risks. SHAP values explained individual risk profiles. The XGBoostpowered web calculator (https://sydtliubo.shinyapps.io/cls2shiny/) enables clinicians and patients to assess fragility fracture risk in PLWH.ConclusionWe developed a web-based risk assessment tool using the XGBoost algorithm for predicting fragility fractures in HIV-positive patients. This tool, with its high accuracy and interpretability, aids in fracture risk stratification and management, potentially reducing the burden of fragility fractures in the HIV population.https://www.frontiersin.org/articles/10.3389/fcimb.2025.1461740/fullfragility fracturePLWHweb calculatormachine learningXGBoostSHAP |
| spellingShingle | Bo Liu Bo Liu Qiang Zhang Qiang Zhang Xin Li Xin Li An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China Frontiers in Cellular and Infection Microbiology fragility fracture PLWH web calculator machine learning XGBoost SHAP |
| title | An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China |
| title_full | An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China |
| title_fullStr | An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China |
| title_full_unstemmed | An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China |
| title_short | An explainable web application based on machine learning for predicting fragility fracture in people living with HIV: data from Beijing Ditan Hospital, China |
| title_sort | explainable web application based on machine learning for predicting fragility fracture in people living with hiv data from beijing ditan hospital china |
| topic | fragility fracture PLWH web calculator machine learning XGBoost SHAP |
| url | https://www.frontiersin.org/articles/10.3389/fcimb.2025.1461740/full |
| work_keys_str_mv | AT boliu anexplainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT boliu anexplainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT qiangzhang anexplainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT qiangzhang anexplainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT xinli anexplainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT xinli anexplainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT boliu explainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT boliu explainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT qiangzhang explainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT qiangzhang explainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT xinli explainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina AT xinli explainablewebapplicationbasedonmachinelearningforpredictingfragilityfractureinpeoplelivingwithhivdatafrombeijingditanhospitalchina |