Xiangya School of Nursing, Central South University, Changsha, Hunan, China.
Operation Department, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China.
J Arthroplasty. 2025 Jan;40(1):61-69.e2. doi: 10.1016/j.arth.2024.07.007. Epub 2024 Jul 14.
In total joint arthroplasty patients, intraoperative hypothermia (IOH) is associated with perioperative complications and an increased economic burden. Previous models have some limitations and mainly focus on regression modeling. Random forest (RF) algorithms and decision tree modeling are effective for eliminating irrelevant features and making predictions that aid in accelerating modeling and reducing application difficulty.
We conducted this prospective observational study using convenience sampling and collected data from 327 total joint arthroplasty patients in a tertiary hospital from March 4, 2023, to September 11, 2023. Of those, 229 patients were assigned to the training and 98 to the testing sets. The Chi-square, Mann-Whitney U, and t-tests were used for baseline analyses. The feature variables selection used the RF algorithms, and the decision tree model was trained on 299 examples and validated on 98. The sensitivity, specificity, recall, F1 score, and area under the curve were used to test the model's performance.
The RF algorithms identified the preheating time, the volume of flushing fluids, the intraoperative infusion volume, the anesthesia time, the surgical time, and the core temperature after intubation as risk factors for IOH. The decision tree was grown to 5 levels with 9 terminal nodes. The overall incidence of IOH was 42.13%. The sensitivity, specificity, recall, F1 score, and area under the curve were 0.651, 0.907, 0.916, 0.761, and 0.810, respectively. The model indicated strong internal consistency and predictive ability.
The preheating time, the volume of flushing fluids, the intraoperative infusion volume, the anesthesia time, the surgical time, and the core temperature after intubation could accurately predict IOH in total joint arthroplasty patients. By monitoring these factors, the clinical staff could achieve early detection and intervention of IOH in total joint arthroplasty patients.
在全关节置换术患者中，术中低体温（IOH）与围手术期并发症和经济负担增加有关。以前的模型存在一些局限性，主要集中在回归建模上。随机森林（RF）算法和决策树建模对于消除不相关特征和进行预测很有效，有助于加速建模和降低应用难度。
我们采用便利抽样法进行了这项前瞻性观察研究，于 2023 年 3 月 4 日至 9 月 11 日期间从一家三级医院的 327 例全关节置换术患者中收集数据。其中，229 例患者被分配到训练组，98 例患者被分配到测试组。使用卡方检验、Mann-Whitney U 检验和 t 检验进行基线分析。特征变量选择使用 RF 算法，决策树模型在 299 个示例上进行训练，并在 98 个示例上进行验证。使用灵敏度、特异性、召回率、F1 评分和曲线下面积来测试模型的性能。
RF 算法确定了预热时间、冲洗液量、术中输液量、麻醉时间、手术时间和插管后核心体温作为 IOH 的危险因素。决策树生长到 5 级，有 9 个终端节点。总的 IOH 发生率为 42.13%。灵敏度、特异性、召回率、F1 评分和曲线下面积分别为 0.651、0.907、0.916、0.761 和 0.810。该模型显示出较强的内部一致性和预测能力。
预热时间、冲洗液量、术中输液量、麻醉时间、手术时间和插管后核心体温可以准确预测全关节置换术患者的 IOH。通过监测这些因素，临床工作人员可以实现全关节置换术患者 IOH 的早期检测和干预。
