[Machine Learning Model Based on Structured Injury Features for Knee Dysfunction after Traumatic Injury].

内容摘要

To extract structured injury features of knee trauma from forensic case files, and to assess knee functional impairment using a machine learning model combined with the voting method. A total of 490 forensic cases involving knee trauma were retrospectively collected and randomly divided into training and testing sets at an 8:2 ratio. Structured injury features were extracted and systematically organized and stored using a MySQL database. Six machine learning models, including support vector classification, random forest, logistic regression, gradient boosting, k-nearest neighbor, and extreme gradient boosting, were applied to select the optimal models. Using a 25% loss of joint range of motion as the threshold, a model for classifying the severity of knee functional impairment was established by combining the selected models with a voting method. The best models were first selected based on their average AUC values, and further validated using 5-fold cross-validation. The SHAP method was used to analyze and interpret the prediction results of the optimal model. In addition, 57 similar cases were collected as an external validation to evaluate the model's generalization ability. The average AUC values for support vector machine, random forest, and extreme gradient boosting all exceeded 0.9. In 5-fold cross-validation, each of the three individual models achieved an average AUC value of 0.89. After integrating these three models using the voting method, the average AUC of 5-fold cross-validation increased to 0.91. The model's performance, and the evaluation metrics on the external validation set were comparable to those from internal validation. The developed machine learning model based on structured injury features demonstrates good performance in classifying the severity of motor dysfunction following knee trauma, with high model interpretability and strong generalization capability. 目的: 基于鉴定案例档案提取结构化的膝关节外伤损伤特征，利用机器学习模型结合投票法，推断膝关节功能障碍。方法: 回顾性收集膝关节外伤行法医学鉴定案例490例，按照8∶2比例划分为训练集和测试集;提取结构化损伤特征并利用MySQL数据库进行数据的系统化组织与储存，采用支持向量分类、随机森林、逻辑回归、梯度提升、k-近邻法、极限梯度提升共6种机器学习模型筛选出的最佳模型，结合投票法，以关节活动度损失25％为界，建立膝关节功能障碍程度判别模型。根据初步筛选的平均AUC值挑选最佳模型，再采用5-折交叉验证进一步验证。采用SHAP方法分析并解释最佳模型的预测结果。另外收集57例同类案例作为外部验证集检验模型的泛化能力。结果: 支持向量分类、随机森林、极限梯度提升3种模型的平均AUC值较高，均超过0.9。在5-折交叉验证中，三个模型的平均AUC值均为0.89。使用投票法集成这3种模型后，5-折交叉验证平均AUC值提升至0.91。模型的外部验证集各项评估指标与内部测试结果相近。结论: 建立的基于结构化膝关节外伤损伤特征机器学习模型，在膝关节外伤后运动功能障碍程度判别任务中效果较好，具有良好的可解释性与较高的泛化能力。.