Xiao Lishan, Zhao Yizhe, Li Yuchen, Yan Mengmeng, Liu Yongming, Liu Manhua, Ning Chunping
Department of Ultrasound, the Affiliated Hospital of Qingdao University, Qingdao, China.
The School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China; MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China.
Eur J Radiol. 2025 Mar;184:111959. doi: 10.1016/j.ejrad.2025.111959. Epub 2025 Jan 31.
To develop a machine learning (ML) model using clinical data and ultrasound features for gout prediction, and apply SHapley Additive exPlanations (SHAP) for model interpretation.
This study analyzed 609 patients' first metatarsophalangeal (MTP1) joint ultrasound data from two institutions. Institution 1 data (n = 571) were split into training cohort (TC) and internal testing cohort (ITC) (8:2 ratio), while Institution 2 data (n = 92) served as external testing cohort (ETC). Key predictors were selected using Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Extreme Gradient Boosting (XGBoost) algorithms. Six ML models were evaluated using standard performance metrics, with SHAP analysis for model interpretation.
Five key predictors were identified: serum uric acid (SUA), deep learning (DL) model predictions, tophus, bone erosion, and double contour sign (DCs). The logistic regression (LR) model demonstrated optimal performance, achieving Area Under the Curve (AUC) values of 0.870 (95% CI: 0.820-0.920) in ITC and 0.854 (95% CI: 0.804-0.904) in ETC. The model showed good calibration with Brier scores of 0.138 and 0.159 in ITC and ETC, respectively.
This study developed an interpretable ML model for gout prediction and utilized SHAP to elucidate feature contributions, establishing a foundation for future applications in clinical decision support for gout diagnosis.
利用临床数据和超声特征开发一种用于痛风预测的机器学习（ML）模型，并应用夏普利值加法解释（SHAP）进行模型解释。
本研究分析了来自两个机构的609例患者的第一跖趾关节（MTP1）超声数据。机构1的数据（n = 571）被分为训练队列（TC）和内部测试队列（ITC）（比例为8:2），而机构2的数据（n = 92）用作外部测试队列（ETC）。使用随机森林（RF）、最小绝对收缩和选择算子（LASSO）以及极端梯度提升（XGBoost）算法选择关键预测因子。使用标准性能指标评估六个ML模型，并进行SHAP分析以解释模型。
确定了五个关键预测因子：血清尿酸（SUA）、深度学习（DL）模型预测、痛风石、骨质侵蚀和双轨征（DCs）。逻辑回归（LR）模型表现出最佳性能，在ITC中的曲线下面积（AUC）值为0.870（95%置信区间：0.820 - 0.920），在ETC中的AUC值为0.854（95%置信区间：0.804 - 0.904）。该模型在ITC和ETC中的Brier分数分别为0.138和0.159，显示出良好的校准。
本研究开发了一种可解释的用于痛风预测的ML模型，并利用SHAP阐明特征贡献，为痛风诊断的临床决策支持的未来应用奠定了基础。
