Establishment and validation of a risk prediction model for intraoperative hypothermia in patients undergoing laparoscopic surgery

doi:10.3761/j.issn.0254-1769.2022.04.012

Abstract

Abstract:

Objective To construct a risk predictive model of intraoperative hypothermia for patients undergoing laparoscopic surgery and to verify the predictive effect of the model. Methods 1043 patients who underwent laparoscopic surgery and met the inclusion and exclusion criteria were selected in our hospital from June to October 2020,using the convenience sampling method. They were randomly assigned to a modeling group and a verification group at a ratio of 7 ∶ 3. The influencing factors of patients with intraoperative hypothermia（n=407） and patients without intraoperative hypothermia（n=323） in the modeling group were compared,which is conducive to the random forest algorithm to sort the influencing factors and build the prediction model. Results The incidence of intraoperative hypothermia was 55.75% in the modeling group and 54.95% in the validation group. In the importance score of random forest algorithm variables,basic body temperature,operating room temperature,BMI,operation time and other indicators have a high contribution to the model classification,with clinical significance. The area under the receiver operating characteristic curve of the predictive model is 0.797;the sensitivity is 78.74%;the specificity is 64.03%;the accuracy is 72.20%. Conclusion The prediction model based on random forest algorithm is effective,which is of great significance to identify the key factors of intraoperative hypothermia in patients undergoing laparoscopic surgery and intervene timely and effectively.

Key words: Intraoperative Hypothermia, Correlative Factor, Risk Prediction, Random Forest Algorithm, Nursing Care

摘要：

目的构建腹腔镜手术患者术中低体温风险预测模型并验证模型的预测效果。方法采用便利抽样法,选取2020年6月—10月在山东省某三级甲等医院接受腹腔镜手术并符合纳入标准的患者1 043例,按照7 ∶ 3的比例随机分配至建模组和验证组。将建模组发生术中低体温患者（407例）和未发生术中低体温患者（323例）的各项影响因素进行对比,利用随机森林算法对各项影响因素进行排序并构建预测模型。利用验证组数据绘制受试者操作特征曲线,并以曲线下面积检验模型的预测效果。结果患者术中低体温发生率建模组为55.75%,验证组为54.95%。随机森林算法变量重要性评分中,基础体温、手术间温度、BMI、手术时长等指标对模型分类的贡献度较高,且具有临床意义。预测模型的受试者操作特征曲线下面积为0.797,灵敏度为78.74%,特异度为64.03%,准确率为72.20%。结论该研究基于随机森林算法构建的预测模型具有良好的预测效能,对识别腹腔镜手术患者术中低体温的关键因素具有重要意义。

关键词: 术中低体温, 相关因素, 风险预测, 随机森林算法, 护理

LI Li, YAN Yan, FANG Xin, ZHAI Yonghua. Establishment and validation of a risk prediction model for intraoperative hypothermia in patients undergoing laparoscopic surgery[J]. Chinese Journal of Nursing, 2022, 57(4): 463-468.

李丽, 颜艳, 房馨, 翟永华. 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.

Figures/Tables 5

Table 1 The result of single factor analysis of hypothermia in patients undergoing laparoscopic surgery

Table 2 The optimal range and optimal value of random forest model parameter tuning

Table 3 Importance score of variables in random forest model

Figure 1 Receiver operating characteristic curve of modeling group

Figure 2 Receiver operating characteristic curve of validation group

References 22

[1]	Sessler DI. Mild perioperative hypothermia[J]. N Engl J Med, 1997, 336(24):1730-1737. DOI URL
[2]	Li Y, Liang H, Feng Y. Prevalence and multivariable factors associated with inadvertent intraoperative hypothermia in video-assisted thoracoscopic surgery:a single-center retrospective study[J]. BMC Anesthesiol, 2020, 20(1):25. DOI URL
[3]	Yi J, Lei Y, Xu S, et al. Intraoperative hypothermia and its clinical outcomes in patients undergoing general anesthesia:national study in China[J]. PLoS One, 2017, 12(6):e177221.
[4]	Staikou C, Paraskeva A, Drakos E, et al. Impact of graded hypothermia on coagulation and fibrinolysis[J]. J Surg Res, 2011, 167(1):125-130. DOI URL
[5]	Rajagopalan S, Mascha E, Na J, et al. The effects of mild perioperative hypothermia on blood loss and transfusion requirement[J]. Anesthesiology, 2008, 108(1):71-77. PMID
[6]	Frank SM, Fleisher LA, Breslow MJ, et al. Perioperative maintenance of normothermia reduces the incidence of morbid cardiac events.A randomized clinical trial[J]. JAMA, 1997, 277(14):1127-1134. DOI URL
[7]	Hart SR, Bordes B, Hart J, et al. Unintended perioperative hypothermia[J]. Ochsner J, 2011, 11(3):259-270.
[8]	Torossian A, Bräuer A, Höcker J, et al. Preventing inadvertent perioperative hypothermia[J]. Dtsch Arztebl Int, 2015, 112(10):166-172.
[9]	Shenoy L, Krishna HM, Kalyan N, et al. A prospective comparative study between prewarming and cowarming to prevent intraoperative hypothermia[J]. J Anaesthesiol Clin Pharmacol, 2019, 35(2):231-235. DOI URL
[10]	Xu H, Wang Z, Guan X, et al. Safety of intraoperative hypo-thermia for patients:meta-analyses of randomized controlled trials and observational studies[J]. BMC Anesthesiol, 2020, 20(1):202. DOI URL
[11]	Sumida H, Sugino S, Kuratani N, et al. Effect of forced-air warming by an underbody blanket on end-of-surgery hypothermia:a propensity score-matched analysis of 5063 patients[J]. BMC Anesthesiol, 2019, 19(1):50. DOI URL
[12]	国家麻醉专业质量控制中心, 中华医学会麻醉学分会. 围手术期患者低体温防治专家共识(2017)[J]. 协和医学杂志, 2017, 8(6):352-358.
	National Anesthesia Quality Control Center, Chinese Medical Association on Anesthesiology. Expert consensus on prevention and treatment of hypothermia in perioperative patients (2017)[J]. Med J Peking Union Med Coll Hosp, 2017, 8(6):352-358.
[13]	Bindu B, Bindra A, Rath G. Temperature management under general anesthesia:compulsion or option[J]. J Anaesthesiol Clin Pharmacol, 2017, 33(3):306-316. DOI URL
[14]	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.
	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.
[15]	普鹰, 张莹, 汤佳骏, 等. 腹腔镜手术患者术中低体温预测模型的构建及应用[J]. 中华护理杂志, 2019, 54(9):1308.
	Pu Y, Zhang Y, Tang JJ, et al. Establishment and validation of a risk prediction model for intraoperative hypothermia in patients undergoing laparoscopic surgery[J]. Chin J Nurs, 2019, 54(9):1308.
[16]	Xiao Y, Zhang R, Lü N, et al. Effects of a preoperative forced-air warming system for patients undergoing video-assisted tho-racic surgery:a randomized controlled trial[J]. Medicine(Baltimore), 2020, 99(48):e23424.
[17]	Yoo JH, Ok SY, Kim SH, et al. Effects of 10-min of pre-warm-ing on inadvertent perioperative hypothermia in intraoperative warming patients:a randomized controlled trial[J]. Anesth Pain Med(Seoul), 2020, 15(3):356-364.
[18]	国家卫生和计划生育委员会. 医院洁净手术部建筑技术规范[S]. 北京: 中国建筑工业出版社, 2013.
	National Health and Family Planning Commission. Architectural technical code for hospital clean operating department[S]. Beijing: China Architecture & Building Press, 2013.
[19]	Yi J, Xiang Z, Deng X, et al. Incidence of inadvertent intra-operative hypothermia and its risk factors in patients undergoing general anesthesia in Beijing[J]. PLoS One, 2015, 10(9):e136136.
[20]	Yi J, Zhan L, Lei Y, et al. Establishment and validation of a prediction equation to estimate risk of intraoperative hypo-thermia in patients receiving general anesthesia[J]. Sci Rep, 2017, 7(1):13927. DOI URL
[21]	Forbes SS, Eskicioglu C, Nathens AB, et al. Evidence-based guidelines for prevention of perioperative hypothermia[J]. J Am Col Surg, 2009, 209(4):492-503. DOI URL
[22]	杜晓菊, 张海林, 尹丽霞, 等. 维持性血液透析患者骨骼肌质量下降预测模型的构建及对护理工作的启示[J]. 中华护理杂志, 2021, 56(4):496-501.
	Du XJ, Zhang HL, Yin LX, et al. Establishment and enlightenment of a predictive model for decreased skeletal muscle mass in maintenance hemodialysis patients[J]. Chin J Nurs, 2021, 56(4):496-501.