预测对抗骨质疏松症治疗的不良反应：整合临床和新型生物标志物数据的机器学习模型
Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data.
摘要(中文译文)
本研究旨在开发并验证一个整合临床特征与新型生物标志物的预测模型，以期在治疗开始前识别标准抗骨质疏松治疗反应不佳的高危患者，从而支持个体化治疗决策。本研究对2021年1月至2024年12月期间收治的543例原发性骨质疏松症患者进行了回顾性分析。所有患者均接受12个月的标准治疗。参与者按7：3的比例随机分配至训练集（n=380）和验证集（n=163）。在训练集中，采用单因素分析、最小绝对收缩和选择算子（LASSO）回归及多因素logistic回归确定独立预测因子。随后构建了三种机器学习模型——随机森林（RF）、支持向量机（SVM）和K近邻（KNN）。采用受试者工作特征曲线下面积（AUC）、校准曲线和决策曲线分析（DCA）评估模型性能。使用SHapley加法解释（SHAP）值对最优模型进行解释。训练集与验证集的基线特征具有可比性（P>0.05）。共识别出8个治疗反应不佳的独立预测因子：合并糖尿病、脆性骨折史、糖皮质激素使用≥6个月、股骨颈骨密度T值，以及血清骨钙素、I型前胶原N端前肽、I型胶原β-降解产物（β-CTX）和25-羟基维生素D水平。在各模型中，RF算法表现出更优的性能，训练集AUC为0.856（95% CI：0.808-0.905），验证集AUC为0.825（95% CI：0.718-0.933）。该模型校准良好，DCA显示具有较高的净获益。SHAP分析证实血清β-CTX是最重要的预测变量。本研究成功开发并验证了一个整合多维度因素的预测模型，用于评估骨质疏松症的治疗疗效。基于RF的模型表现出稳健的预测性能和临床实用性，有望在治疗前识别高危患者，促进骨质疏松症的精准管理。
Abstract
This study was conducted to develop and validate a prediction model integrating clinical characteristics and novel biomarkers. The goal was to identify patients at high risk for a poor response to standard anti-osteoporosis therapy prior to treatment initiation, thereby supporting personalized therapeutic decision-making. A retrospective analysis was performed on 543 patients with primary osteoporosis admitted between January 2021 and December 2024. All patients received 12 months of standard treatment. Participants were randomly allocated to a training set ( = 380) and a validation set ( = 163) in a 7:3 ratio. In the training set, univariate analysis, Least Absolute Shrinkage and Selection Operator (LASSO) regression, and multivariate logistic regression were used to determine independent predictors. Three machine learning models-Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)-were then constructed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) values were used to interpret the optimal model. Baseline characteristics were comparable between the training and validation sets ( > 0.05). Eight independent predictors of poor treatment response were identified: comorbid diabetes, history of fragility fracture, glucocorticoid use for ≥ 6 months, femoral neck bone mineral density T-score, and serum levels of osteocalcin, procollagen type I N-terminal propeptide, β-CrossLaps of type I collagen (β-CTX), and 25-Hydroxyvitamin D. Among the models, the RF algorithm demonstrated superior performance, with an AUC of 0.856 (95% CI: 0.808-0.905) in the training set and 0.825 (95% CI: 0.718-0.933) in the validation set. The model was well-calibrated, and DCA indicated a high net benefit. SHAP analysis confirmed serum β-CTX as the most significant predictive variable. A predictive model integrating multi-dimensional factors was successfully developed and validated for assessing osteoporosis treatment efficacy. The RF-based model exhibited robust predictive performance and clinical utility. It shows potential for pre-therapeutic identification of high-risk patients, facilitating precision management in osteoporosis.
如何引用
AMA
Yannan Bi, Maolin Zhang, Weiqiong Zhang, Jiahong Li. Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data.. Frontiers in medicine. 2026; doi:10.3389/fmed.2026.1786209.
APA
Yannan Bi, Maolin Zhang, Weiqiong Zhang, Jiahong Li (2026). Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data.. Frontiers in medicine. https://doi.org/10.3389/fmed.2026.1786209
GB/T 7714
Yannan Bi, Maolin Zhang, Weiqiong Zhang, Jiahong Li. Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data.[J]. Frontiers in medicine, 2026 doi:10.3389/fmed.2026.1786209.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出