基于随机森林算法的全麻食管癌根治术老年患者术后 苏醒延迟的预警模型构建.
Saved in:
| Title: | 基于随机森林算法的全麻食管癌根治术老年患者术后 苏醒延迟的预警模型构建. (Chinese) |
|---|---|
| Alternate Title: | Construction of An Warning Model for Postoperative Delayed Awakening in Elderly Patients Underwent Radical Esophagectomy under General Anesthesia Based on Random Forest Algorithm. (English) |
| Authors: | 卢敏萍, 李清连, 叶梦媛 |
| Source: | Progress in Modern Biomedicine; 2025, Vol. 25 Issue 22, p3590-3597, 8p |
| Subject Terms: | OLDER patients, ESOPHAGECTOMY, PREDICTION models, POSTOPERATIVE care, RANDOM forest algorithms, GENERAL anesthesia, TREATMENT effectiveness |
| Abstract (English): | Objective: To construct an warning model for postoperative delayed awakening in elderly patients underwent radical esophagectomy under general anesthesia based on random forest algorithm, and to provided a reference for the early clinical identification of high-risk patients and the adoption of intervention measures. Methods: This study adopts a retrospective research approach, 162 elderly patients who underwent radical esophagectomy under general anesthesia from January 2020 to January 2022 at the Longyan Second Hospital were selected as the study subjects. The patients were divided into delayed awakening group and non-delayed awakening group based on whether there were delayed awakening after the operation. General information of patients was collected, Univariate and multivariate Logistic regression analyses were conducted to investigate the influencing factors of delayed awakening in elderly patients underwent radical esophagectomy under general anesthesia. The results of multivariate logistic analysis were used to construct an warning model used the random forest algorithm, the receiver operating characteristic (ROC) curve was used to evaluate the predictive efficacy of the warning model for delayed awakening in elderly patients underwent radical esophagectomy under general anesthesia. Results: Among the 162 patients who underwent radical esophagectomy under general anesthesia, the incidence of postoperative delayed awakening was 14.81% (24/162). There were significant differences between non-delayed awakening group and delayed awakening group in terms of age, american society of anesthesiologists (ASA) classification, preoperative albumin, operation time, anesthesia time, total dose of propofol, total dose of remifentanil and intraoperative infusion volume (P﹤0.05). Multivariate logistic regression model showed that older age, long operation time, high intraoperative infusion volume and high total dose of propofol were independent risk factors for delayed awakening in elderly patients underwent radical esophagectomy under general anesthesia, elevated preoperative albumin was a protective factor (P﹤0.05). The random forest plot importance score shows that, the total dose of propofol, operation time and age were of relatively high importance. The area under curve (AUC) of the random forest model for predicting delayed awakening in elderly patients underwent radical esophagectomy under general anesthesia was 0.865, and the AUC of the multivariate logistic regression model was 0.782. The predictive efficacy of the random forest model was superior to that of the multivariate logistic regression model (P < 0.05) Conclusion: The warning model based on the random forest algorithm can effectively predict the risk of postoperative delayed awakening in elderly patients underwent radical esophagectomy under general anesthesia, and has high clinical application value. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): | 目的: 构建基于随机森林算法的全麻食管癌根治术老年患者术后苏醒延迟预警模型, 为临床早期识别高风险患者并采取干预措施提供参考。方法: 本研究采用回顾性研究, 选取 2020 年 1 月至 2022 年 1 月在龙岩市第二医院行全麻食管癌根治术的 162 例老年患者作为研究对象。根据术后是否苏醒延迟分为苏醒延迟组和非苏醒延迟组收集患者的一般资料, 通过单因素和多因素 Logistic 回归分析行全麻食管癌根治术老年患者术后苏醒延迟的影响因素, 将多因素 Logistic 分析结果利用随机森林算法构建预警模型, 采用受试者工作特征 receiver operating characteristic, ROC) 曲线评估预警模型对全麻食管癌根治术老年患者术后苏醒延迟的预测效能。结果: 162 例行全麻食管癌根治术老年患者中, 发生术后苏醒延迟 24 例, 发生率为 14.81% (24/162)。非苏醒延迟组和苏醒延迟组在年龄、美国麻醉医师协会 (american society of anesthesiologists, ASA) 分级、术前白蛋白、手术时间、麻醉时间、丙泊酚总剂量、瑞芬太尼总剂量、术中输液量存在显著差异 P <0.05) 多因素 Logistic 回归模型, 结果显示: 年龄、手术时间偏长、术中输液量偏高、丙泊酚总剂量偏高是全麻食管癌根治术老年患者术后苏醒延迟的独立危险因素, 术前白蛋白偏高是保护因素 p <0.05) 随机森林图重要性得分显示, 丙泊酚总剂量、手术时间、年龄的重要性较高。随机森林模型预测全麻食管癌根治术老年患者术后苏醒延迟的曲线下面积 (area under the curve, AUC) 为 0.865, 多因素 Logistic 回归模型的 AUC 为 0.782。随机森林模型的预测效能优于多因素 Logistic 回归模型 ( P <0.05)。结论: 基于随机森林算法构建的预警模型可有效预测行全麻 食管癌根治术老年患者术后苏醒延迟发生风险, 具有较高的临床应用价值。 [ABSTRACT FROM AUTHOR] |
| Copyright of Progress in Modern Biomedicine is the property of Publishing House of Progress in Modern Biomedicine and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Biomedical Index |
Nájsť tento článok vo Web of Science Be the first to leave a comment!