Yang Xing, Liu Jianyuan, Huang Xiaozhi, Liang Hao, Cui Ping, He Shiran, Zhang Heng, Liao Wenping, Zhang Guangkun, Huang Qianqian, Ning Huan, Luo Tingyan, Luo Yinghua, Li Wei, Huang Jiegang
Health Management Research Institute, People's Hospital of Guangxi Zhuang Autonomous Region and Guangxi Academy of Medical Sciences, Nanning, China.
School of Public Health, Guangxi Medical University, Nanning, China; Guangxi Key Laboratory of AIDS Prevention and Treatment, Guangxi Medical University, Nanning, China.
Bone. 2025 Jul 15;200:117592. doi: 10.1016/j.bone.2025.117592.
Low bone mineral density (LBMD), which includes osteopenia and osteoporosis, is associated with substantial health care costs. However, current diagnostic methods for LBMD are limited in terms of accuracy and accessibility. This study aims to develop an interpretable machine learning model for LBMD risk assessment and implement it as a web-based clinical decision support tool.
Data from subjects who underwent dual-energy X-ray absorptiometry (DXA) at the People's Hospital of Guangxi Zhuang Autonomous Region were collected and randomly divided into a training set (70 %) and an internal validation set (30 %). An external validation set was sourced from the National Health and Nutrition Examination Survey (NHANES) database. Least absolute shrinkage and selection operator (LASSO) regression and multiple logistic regression were used for feature selection. Ten common machine learning models were conducted based on the selected features. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), Matthews correlation coefficient (MCC), Brier score, and decision curve analysis (DCA). The decision mechanisms of the best-performing model were explained using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). The optimal model was deployed as a web application using Streamlit.
A total of 16,274 participants were included in this study. Age, body mass index (BMI), alkaline phosphatase, and total cholesterol were identified as key predictors of LBMD. The logistic regression (LR) model demonstrated superior prediction performance (internal validation set [AUC = 0.902, MCC = 0.684, Brier score = 0.123], external validation set [0.812, 0.358, 0.265]). DCA confirmed its clinical utility. Both SHAP and LIME showed consistent results in identifying predictive factors. The LR model was deployed as a web application to predict LBMD.
Our interpretable machine learning model and web-based implementation provide a free and reliable tool for predicting LBMD, which represents a significant advancement in making LBMD screening more accessible and cost-effective.
低骨矿物质密度（LBMD），包括骨量减少和骨质疏松症，与大量的医疗保健费用相关。然而，目前LBMD的诊断方法在准确性和可及性方面存在局限性。本研究旨在开发一种可解释的机器学习模型用于LBMD风险评估，并将其作为基于网络的临床决策支持工具来实施。
收集在广西壮族自治区人民医院接受双能X线吸收法（DXA）检查的受试者数据，并随机分为训练集（70%）和内部验证集（30%）。外部验证集来自国家健康与营养检查调查（NHANES）数据库。采用最小绝对收缩和选择算子（LASSO）回归和多重逻辑回归进行特征选择。基于所选特征构建了10种常见的机器学习模型。使用受试者工作特征曲线下面积（AUC）、马修斯相关系数（MCC）、布里尔评分和决策曲线分析（DCA）评估模型性能。使用夏普利值加法解释（SHAP）和局部可解释模型无关解释（LIME）来解释性能最佳模型的决策机制。使用Streamlit将最优模型部署为一个网络应用程序。
本研究共纳入16274名参与者。年龄、体重指数（BMI）、碱性磷酸酶和总胆固醇被确定为LBMD的关键预测因素。逻辑回归（LR）模型表现出卓越的预测性能（内部验证集[AUC = 0.902，MCC = 0.684，布里尔评分 = 0.123]，外部验证集[0.812，0.358，0.265]）。DCA证实了其临床实用性。SHAP和LIME在识别预测因素方面显示出一致的结果。LR模型被部署为一个网络应用程序以预测LBMD。
我们的可解释机器学习模型及其基于网络的实现为预测LBMD提供了一个免费且可靠的工具，这代表了在使LBMD筛查更易获得且更具成本效益方面的一项重大进展。
