Duan Hao, Liu Haoling, Liu Weiwei, Zhang Yuan, Yan Pengying, Wu Baolei, Ma Yiwei
Department of Medical Engineering, The 987 Hospital, Joint Logistic Support Force, Chinese People's Liberation Army No. 45 Dongfeng Road, Jintai District, Baoji 721004, Shaanxi, China.
Department of Pathology, The 987 Hospital, Joint Logistic Support Force, Chinese People's Liberation Army No. 45 Dongfeng Road, Jintai District, Baoji 721004, Shaanxi, China.
Am J Transl Res. 2025 Aug 15;17(8):6303-6319. doi: 10.62347/RIGS6581. eCollection 2025.
To develop and validate a machine learning (ML)-based model for predicting the risk of intraoperative hypothermia in patients undergoing radical oral cancer surgery and to identify key contributing risk factors for clinical reference.
This retrospective study included 402 patients who underwent radical oral cancer resection, divided into training (n = 281) and validation (n = 121) cohorts. Demographic data, physiologic indicators, and intraoperative variables were collected. Predictive models were constructed using Least Absolute Shrinkage and Selection Operator (LASSO) regression, eXtreme Gradient Boosting (XGBoost), and Random Forest (RF) algorithms. Model performance was evaluated using receiver operating characteristic curves, calibration plots, and Shapley Additive Explanations (SHAP) analysis.
The RF model demonstrated superior performance, achieving an area under the curve (AUC) of 0.821 (95% confidence interval [CI]: 0.783-0.856) in the training cohort and 0.807 (95% CI: 0.742-0.865) in the validation cohort, with 64.6% sensitivity. It outperformed both the XGBoost model (validation AUC = 0.721) and LASSO model (validation AUC = 0.738). SHAP analysis identified surgical duration > 441 minutes (odds ratio [OR] = 2.31), baseline temperature ≤ 36.5°C (OR = 3.12), and intraoperative fluid volume ≥ 4.6 liters (OR = 1.89) as the most important predictors. Calibration curves showed strong agreement between predicted and actual outcomes (mean absolute error = 0.17).
The ML-based RF model provides reliable prediction of intraoperative hypothermia risk in oral cancer surgery. Surgical duration and baseline temperature emerged as key risk factors, offering targets for perioperative risk stratification and intervention.
开发并验证一种基于机器学习（ML）的模型，用于预测口腔癌根治性手术患者术中低体温的风险，并识别关键的风险因素，以供临床参考。
这项回顾性研究纳入了402例行口腔癌根治性切除术的患者，分为训练组（n = 281）和验证组（n = 121）。收集人口统计学数据、生理指标和术中变量。使用最小绝对收缩和选择算子（LASSO）回归、极端梯度提升（XGBoost）和随机森林（RF）算法构建预测模型。使用受试者工作特征曲线、校准图和夏普利值附加解释（SHAP）分析评估模型性能。
RF模型表现出卓越的性能，在训练组中曲线下面积（AUC）为0.821（95%置信区间[CI]：0.783 - 0.856），在验证组中为0.807（95%CI：0.742 - 0.865），灵敏度为64.6%。它优于XGBoost模型（验证组AUC = 0.721）和LASSO模型（验证组AUC = 0.738）。SHAP分析确定手术时间>441分钟（优势比[OR]=2.31）、基线体温≤36.5°C（OR = 3.12）和术中液体量≥4.6升（OR = 1.89）是最重要的预测因素。校准曲线显示预测结果与实际结果之间具有高度一致性（平均绝对误差 = 0.17）。
基于ML的RF模型为口腔癌手术中术中低体温风险提供了可靠的预测。手术时间和基线体温是关键风险因素，为围手术期风险分层和干预提供了目标。
