基于机器学习算法的成人术中低体温预测模型的范围综述

doi:10.3761/j.issn.0254-1769.2026.06.017

摘要/Abstract

摘要：

目的对基于机器学习算法构建成人术中低体温预测模型的相关研究进行范围综述，为优化术中低体温管理提供参考。方法依据范围界定审查指南，系统检索Embase、Web of Science、CINAHL、Cochrane Library、Elsevier ScienceDirect、Scopus、PubMed、IEEE Electronic Library、中国知网、中国生物医学文献数据库、万方数据库、维普数据库中的相关研究，检索时限为建库至2025年9月26日，对纳入文献进行归纳和分析。结果共纳入15篇文献，共42个预测模型，模型受试者工作特征曲线下面积为0.717~0.974，平均值为0.830。数据的质量有待提高。常用机器学习算法包括随机森林、XGBoost、Logistic回归、决策树及支持向量机等。常见预测因子为麻醉时间、手术时间、术中输液量、BMI、基础体温、手术室温度和年龄。研究仅进行内部验证，缺乏外部验证；仅少数研究进行了超参数优化或可解释性分析。结论近5年来基于机器学习算法成人术中低体温预测模型数量快速增长，机器学习在术中低体温预测中展现出良好潜力，尤其以树模型（如随机森林、XGBoost）性能较优。未来，应提高数据质量、推进多中心、前瞻性研究，采用超参数调优方法，加强外部验证，引入可解释人工智能技术，促进模型解释及临床转化，并评估其成本效益与临床效用，以实现精准的体温管理。

关键词: 机器学习算法, 术中低体温, 护理, 预测模型, 范围综述

Abstract:

Objective To conduct a scoping review of studies on machine learning-based prediction models for intraoperative hypothermia in adults，in order to provide a reference for optimizing the management of intraoperative hypothermia. Methods Following scoping review guidelines，we systematically searched original studies in databases including Embase，Web of Science，CINAHL，Cochrane Library，Elsevier ScienceDirect，Scopus，PubMed，IEEE Electronic Library Electronic Library，CNKI，CBM，Wanfang Database，and VIP Database from their inception to September 26th，2025. The included literature was summarized and analyzed. Results A total of 15 articles were included，encompassing 42 prediction models. The area under the receiver operating characteristic curve（AUC） of the models ranged from 0.717 to 0.974，with an average value of 0.830. The quality of data requires improvement. Commonly used machine learning algorithms included Random Forest，XGBoost，Logistic Regression，Decision Tree，and Support Vector Machine. Frequent predictive factors were anesthesia duration，surgery duration，intraoperative fluid volume，BMI，baseline body temperature，operating room temperature，and age. The studies only conducted internal validation，lacking external validation；only a few studies performed hyperparameter optimization or interpretability analysis. Conclusion In the past 5 years，the number of machine learning-based prediction models for intraoperative hypothermia in adults has grown rapidly. Machine learning demonstrates significant potential in predicting intraoperative hypothermia，with tree-based models（e.g.，Random Forest，XGBoost） showing particularly optimal performance. Future efforts should focus on improving data quality，promoting multi-center prospective studies，employing hyperparameter tuning methods，strengthening external validation，incorporating explainable artificial intelligence techniques to enhance model interpretability and clinical translation，and evaluating their cost-effectiveness and clinical utility to achieve precise temperature management.

Key words: Machine Learning Algorithms, Intraoperative Hypothermia, Nursing Care, Prediction Model, Scoping Review

武玲, 吴波, 陈红, 古晨茜, 刘洋, 张春谨, 陈梦琪, 章青. 基于机器学习算法的成人术中低体温预测模型的范围综述[J]. 中华护理杂志, 2026, 61(6): 844-851.

WU Ling, WU Bo, CHEN Hong, GU Chenxi, LIU Yang, ZHANG Chunjin, CHEN Mengqi, ZHANG Qing. Machine learning-based prediction models for intraoperative hypothermia risk in adults：a scoping review[J]. Chinese Journal of Nursing, 2026, 61(6): 844-851.

图/表 3

参考文献 33

[1]	中华护理学会.成人术中非计划低体温预防与护理 T/CNAS 44—2024[S]. 北京: 中华护理学会,2024:1.
	Chinese Nursing Association.Prevention and care of unplanned perioperative hypothermia in adults:standard T/CNAS 44—2024[S]. Beijing: Chinese Nursing Association,2024:1.
[2]	Wongyingsinn M, Pookprayoon V. Incidence and associated fac-tors of perioperative hypothermia in adult patients at a univer-sity-based,tertiary care hospital in Thailand[J]. BMC Anesthe-siol, 2023, 23(1):137.
[3]	周羽, 朱琳, 柳露, 等. 术中低体温护理质量指标体系的构建[J]. 中国护理管理, 2024, 24(4):571-576.
	Zhou Y, Zhu L, Liu L, et al. Construction of evidence-based index system of intraoperative hypothermia nursing quality[J]. Chin Nurs Manag, 2024, 24(4):571-576.
[4]	黄立峰, 钱维明, 徐琴, 等. 胸腔镜下肺癌根治患者术中体温变化曲线及对护理的启示[J]. 中华护理杂志, 2022, 57(20):2481-2486. DOI
	Huang LF, Qian WM, Xu Q, et al. Enlightenment of tempera-ture change curve on temperature management and nursing care of patients undergoing video-assisted thoracic surgery of lung cancer[J]. Chin J Nurs, 2022, 57(20):2481-2486.
[5]	孔珊珊, 邓露, 申海艳, 等. 剖宫产产妇术中低体温风险预测模型的构建及应用效果研究[J]. 中华护理杂志, 2021, 56(2):165-171. DOI
	Kong SS, Deng L, Shen HY, et al. Establishment of a risk predictive model of maternal hypothermia during caesarean section and its application effect test[J]. Chin J Nurs, 2021, 56(2):165-171. DOI
[6]	刘婷, 王林, 郝艳丽, 等. 不停跳冠状动脉旁路移植患者术中低体温风险预测模型的构建[J]. 中华护理杂志, 2023, 58(20):2481-2487. DOI
	Liu T, Wang L, Hao YL, et al. Construction of a preoperative risk prediction nomogram model for hypothermia during off-pump coronary artery bypass grafting[J]. Chin J Nurs, 2023, 58(20):2481-2487. DOI
[7]	Julkunen H, Rousu J. Comprehensive interaction modeling with machine learning improves prediction of disease risk in the UK Biobank[J]. Nat Commun, 2025,16:6620.
[8]	周晓芸, 何敏芝, 周宁宁, 等. 胸腔镜肺癌根治术患者苏醒期躁动风险预测模型的构建与验证[J]. 中华护理杂志, 2025, 60(16):1989-1995. DOI
	Zhou XY, He MZ, Zhou NN, et al. Construction and validation of a risk prediction model for emergence agitation in patients undergoing thoracoscopic radical resection of lung cancer[J]. Chin J Nurs, 2025, 60(16):1989-1995. DOI
[9]	李丽, 颜艳, 房馨, 等. 腹腔镜手术患者术中低体温风险预测模型的构建及验证[J]. 中华护理杂志, 2022, 57(4):463-468. DOI
	Li L, Yan Y, Fang X, et al. Establishment and validation of a risk prediction model for intraoperative hypothermia in patients undergoing laparoscopic surgery[J]. Chin J Nurs, 2022, 57(4):463-468. DOI
[10]	曹立源, 范勤勤, 黄敬英. 基于特征选择和XGBoost优化的术中低体温预测[J]. 数据采集与处理, 2022, 37(1):134-146.
	Cao LY, Fan QQ, Huang JY. Intraoperative hypothermia predi-ction model based on feature selection and XGBoost optimi-zation[J]. J Data Acquis Process, 2022, 37(1):134-146.
[11]	任远雯. 基于机器学习算法的OPCAB患者术中低体温预测模型构建研究[D]. 南京: 东南大学, 2023.
	Ren YW. Study on the construction of predictive model of intraoperative hypothermia in OPCAB patients based on ma-chine learning algorithm[D]. Nanjing: Southeast University, 2023.
[12]	曾昕, 卢秀英, 周羽, 等. 肺癌患者术中低体温风险预测模型的构建及验证[J]. 中国护理管理, 2023, 23(10):1500-1506.
	Zeng X, Lu XY, Zhou Y, et al. Construction and validation of intraoperative hypothermia risk prediction model in lung can-cer patients[J]. Chin Nurs Manag, 2023, 23(10):1500-1506.
[13]	梁晓霜, 彭边, 裴娟, 等. 基于决策树法构建后路腰椎椎间融合术患者术中低体温发生风险的预测模型[J]. 军事护理, 2024, 41(11):70-73.
	Liang XS, Peng B, Pei J, et al. Risk prediction model of intraoperative hypothermia in patients with posterior lumbar interbody fusion based on decision tree method[J]. Mil Nurs, 2024, 41(11):70-73.
[14]	张梦冉, 李妍, 张梦晗, 等. 基于机器学习算法的非体外循环冠状动脉旁路移植术患者术中低体温风险预测模型的构建[J]. 护理学报, 2025, 32(9):64-68.
	Zhang MR, Li Y, Zhang MH, et al. Construction of risk prediction model for intraoperative hypothermia in patients undergoing off-pump coronary artery bypass grafting based on machine learning algorithms[J]. J Nurs(China), 2025, 32(9):64-68.
[15]	刘鲁华, 邹晓银, 章芬. 3种机器学习算法对剖宫产产妇术中低体温风险预测性能比较[J]. 全科护理, 2025, 23(5):923-927.
	Liu LH, Zou XY, Zhang F. Comparison of three machine learning algorithms in predicting the risk of hypothermia dur-ing cesarean section[J]. Chin Gen Pract Nurs, 2025, 23(5):923-927.
[16]	冯敏, 马文涓, 加依娜尔·木哈台勒, 等. 非体外循环冠状动脉旁路移植术患者非计划性术中低体温风险预测模型的构建[J]. 中国体外循环杂志, 2025, 23(1):11-16.
	Feng M, Ma WJ, Jiayinaer M, et al. Construction of a risk prediction model for unplanned intraoperative hypothermia in patients undergoing off-pump coronary artery bypass grafting[J]. Chin J Extracorpor Circ, 2025, 23(1):11-16.
[17]	Dibiasi C, Agibetov A, Kapral L, et al. Predicting intraopera-tive hypothermia burden during non-cardiac surgery:a retros-pective study comparing regression to six machine learning algorithms[J]. J Clin Med, 2023, 12(13):4434. DOI URL
[18]	Zhu K, Zhang ZX, Zhang M. Application value of machine learn-ing models in predicting intraoperative hypothermia in lapa-roscopic surgery for polytrauma patients[J]. World J Clin Cases, 2024, 12(24):5513-5522. DOI URL
[19]	Lu ZY, Chen X. Early prediction of intraoperative hypothermia in patients undergoing gynecological laparoscopic surgery:a retrospective cohort study[J]. Medicine, 2024, 103(40):e39038. DOI URL
[20]	Long KY, Guo DH, Deng L, et al. Cross-combination analyses of random forest feature selection and decision tree model for predicting intraoperative hypothermia in total joint arthro-plasty[J]. J Arthroplasty, 2025, 40(1):61-69. DOI URL
[21]	Cao XS, Wen XJ, Tang H, et al. Predictive tool for the risk of hypothermia during laparoscopic gynecologic tumor resection[J]. Eur J Obstet Gynecol Reprod Biol, 2025,306:147-153.
[22]	Chen R, Ma XM, Liu M, et al. Machine learning-based predic-tion model for intraoperative hypothermia risk in thoracos-copic lobectomy patients:a SHAP analysis[J]. Medicine, 2025, 104(35):e44202. DOI URL
[23]	Duan H. Development of a machine learning-based predictive model for intraoperative hypothermia risk during radical sur-gery for oral cancer[J]. Am J Transl Res, 2025, 17(8):6303-6319. DOI PMID
[24]	Naik A, Tejani GG, Mousavirad SJ. SGO enhanced random forest and extreme gradient boosting framework for heart disease prediction[J]. Sci Rep, 2025,15:18145.
[25]	Yan LH, Ye QL, Shi BL, et al. Random forest-based model for the recurrence prediction of borderline ovarian tumor:clinical development and validation[J]. J Cancer Res Clin Oncol, 2025, 151(5):160. DOI
[26]	Zhang Z, Shao BB, Liu HZ, et al. Construction and validation of a predictive model for coronary artery disease using extre-me gradient boosting[J]. J Inflamm Res, 2024,17:4163-4174.
[27]	Li XY, Dong SH, Guo SY, et al. Applying support vector ma-chines to a diagnostic classification model for polytomous attributes in small-sample contexts[J]. Br J Math Stat Psychol, 2025, 78(1):167-189. DOI URL
[28]	Song YX, Yang XD, Luo YG, et al. Comparison of logistic re-gression and machine learning methods for predicting posto-perative delirium in elderly patients:a retrospective study[J]. CNS Neurosci Ther, 2023, 29(1):158-167. DOI URL
[29]	Yang HQ, Gu S, Fan J, et al. Factors influencing the occur-rence of intraoperative hypothermia in patients undergoing general anesthesia intervention:a study in a tertiary care hospital[J]. Med Sci Monit, 2024,30:e943463.
[30]	Li YN, Liang HS, Feng Y. Prevalence and multivariable factors associated with inadvertent intraoperative hypothermia in video-assisted thoracoscopic surgery:a single-center retrospec-tive study[J]. BMC Anesthesiol, 2020, 20(1):25. DOI
[31]	Shen CY, He YQ. Intraoperative hypothermia in patients with laparoscopic surgery:influencing factors and prevention strate-gies[J]. Heliyon, 2024, 10(10):e31479. DOI URL
[32]	Le NQK, Xu L. Optimizing hyperparameter tuning in machine learning to improve the predictive performance of cross-species N6-methyladenosine sites[J]. ACS Omega, 2023, 8(42):39420-39426. DOI PMID
[33]	Bradshaw TJ, Huemann Z, Hu JJ, et al. A guide to cross-vali-dation for artificial intelligence in medical imaging[J]. Radiol Artif Intell, 2023, 5(4):e220232.