Construction of risk prediction model for intraoperative hypothermia in patients undergoing off - pump coronary artery bypass grafting based on machine learning algorithms

ZHANG Mengran; LI Yan; ZHANG Menghan; ZHENG Zengmei; ZHANG Juan

doi:10.16460/j.issn2097-6569.2025.09.064

PDF(1034 KB)

Journal of Nursing ›› 2025, Vol. 32 ›› Issue (9) : 64-68. DOI: 10.16460/j.issn2097-6569.2025.09.064

Construction of risk prediction model for intraoperative hypothermia in patients undergoing off - pump coronary artery bypass grafting based on machine learning algorithms

ZHANG Mengran^a, LI Yan^a, ZHANG Menghan^a, ZHENG Zengmei^b, ZHANG Juan^a

Author information +

History +

Abstract

Objective To construct a risk prediction model of intraoperative hypothermia in patients undergoing off-pump coronary artery bypass grafting (OPCABG) using four kinds of machine learning algorithms including back propagation neural network (BPNN), support vector machine (SVM), random forest (RF) and logistic regression (LR), and to provide reference for evaluating and preventing intraoperative hypothermia. Methods A total of 1,065 patients with OPCABG in one hospital in Henan Province from January 2021 to July 2024 were selected as research objects. Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to screen the predictors. Four kinds of machine learning algorithms were used to construct the risk prediction model of intraoperative hypothermia, and the receiver operating characteristic curve area (AUC) was used to evaluate the performance of the model, and SHAP for explanatory analysis. Results The AUC values of the BPNN, SVM, RF, and LR models were 0.821,0.822, 0.978, and 0.730, respectively, with the model constructed by RF performing the best. Conclusion The RF-based risk prediction model of intraoperative hypothermia in OPCABG patients has the best performance, which is helpful for early evaluation and prevention of intraoperative hypothermia.

Key words

machine learning / random forest / off-pump coronary artery bypass graft / inadventent intraoperative hypothermia / prediction model

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

ZHANG Mengran, LI Yan, ZHANG Menghan, ZHENG Zengmei, ZHANG Juan. Construction of risk prediction model for intraoperative hypothermia in patients undergoing off - pump coronary artery bypass grafting based on machine learning algorithms[J]. Journal of Nursing. 2025, 32(9): 64-68 https://doi.org/10.16460/j.issn2097-6569.2025.09.064

References

[1] Farina P, Gaudino M, Angelini GD.Off-pump coronary artery bypass surgery: the long and winding road[J]. International journal of cardiology,2019,279:51-55.DOI:10.1016/j.ijcard.2018.09.101.
[2] 刘佳佳, 邱晨, 赵晶. 全维保温预防老年男性非体外循环下冠状动脉旁路移植术围术期低体温的效果观察[J]. 中华老年心脑血管病杂志, 2021,23(2):164-167.
[3] Jin L, Han X, Yu Y, et al.Intraoperative thermal insulation in off-pump coronary artery bypass grafting surgery: a prospective, double blind, randomized controlled, single-center study[J]. Ann Transl Med, 2020,8(19):1220.DOI:10.21037/atm-19-4571.
[4] 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.
[5] Sari S, Aksoy SM, But A.The incidence of inadvertent perioperative hypothermia in patients undergoing general anesthesia and an examination of risk factors[J].Int J Clin Pract(Esher), 2021,75(6):e14103.DOI:10.1111/ijcp.14103.
[6] Akers JL, Dupnick AC, Hillman EL, et al.Inadvertent Perioperative Hypothermia Risks and Postoperative Complications: A Retrospective Study[J]. AORN J, 2019,109(6):741-747.DOI:10.1002/aorn.12696.
[7] Nam K, Jo WY, Kwon SM, et al.Association between postoperative body temperature and all-cause mortality after off-pump coronary artery bypass graft surgery: a retrospective observational study[J]. Anesth Analg, 2020, 130(5):1381-1388.DOI:10.1213/ANE.0000000000004416.
[8] 章明阳, 刘京辉, 金雁, 等. 围手术期低体温风险预测模型的系统评价[J].护理学报, 2024, 31(22):54-60.DOI:10.16460/j.issn1008-9969.2024.22.054.
[9] Handelman GS, Kok HK, Chandra RV, et al.eDoctor: machine learning and the future of medicine[J]. J Intern Med, 2018,284(6):603-619.DOI:10.1111/joim.12822.
[10] Dai Z, Zhang Y, Yi J, et al.Validation of a prediction model for intraoperative hypothermia in patients receiving general anesthesia[J]. Int J Clin Pract, 2022,2022:6806225.DOI:10.1155/2022/6806225.
[11] Hu Z, Li W, Liang C, et al.Risk factors and prediction model for inadvertent intraoperative hypothermia in patients undergoing robotic surgery: a retrospective analysis[J]. Sci Rep, 2023,13(1):3687.DOI:10.1038/s41598-023-30819-1.
[12] Yan L, Yao L, Zhao Q, et al.Risk prediction models for inadvertent intraoperative hypothermia: a systematic review[J]. J Perianesth Nurs, 2021,36(6):724-729.DOI:10.1016/j.jopan.2021.02.011.
[13] Riley RD, Ensor J, Snell KIE, et al.Calculating the sample size required for developing a clinical prediction model[J]. BMJ (Online), 2020,368:m441.DOI:10.1136/bmj.m441.
[14] Langham GE, Maheshwari A, Contrera K, et al.Noninvasive temperature monitoring in postanesthesia care units[J]. Anesthesiology,2009,111(1):90-96.DOI:10.1097/ALN.0b013e3181a864ca.
[15] Hu J, Sheng Y, Ma J, et al.Construction and validation of a progression prediction model for locally advanced rectal cancer patients received neoadjuvant chemoradiotherapy followed by total mesorectal excision based on machine learning[J]. Front Oncol, 2023,13:1231508.DOI:10.3389/fonc.2023.1231508.
[16] Yesilyaprak A, Kumar AK, Agrawal A, et al.Predicting long-term clinical outcomes of patients with recurrent pericarditis[J]. J Am Coll Cardiol, 2024, 84(13):1193-1204.DOI:10.1016/j.jacc.2024.05.072.
[17] Forrest IS, Petrazzini BO, Duffy A, et al.Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts[J]. Lancet, 2023,401(10372):215-225.DOI:10.1016/S0140-6736(22)02079-7.
[18] Wang F, Wang Y, Ji X, et al.Effective macrosomia prediction using random forest algorithm[J]. Int J Environ Res Public Health, 2022,19(6):3245.DOI:10.3390/ijerph19063245.
[19] 黄光成, 周良, 石建伟, 等. 机器学习算法在疾病风险预测中的应用与比较[J]. 中国卫生资源, 2020,23(4):432-436.DOI:10.13688/j.cnki.chr.2020.19608.
[20] 张妮潇. 肥厚型心肌病患者的临床预后及其预测因素[D]. 北京:北京协和医学院, 2021.DOI:10.27648/d.cnki.gzxhu.2021.000210.
[21] Hannan E L, Samadashvili Z, Wechsler A, et al.The relationship between perioperative temperature and adverse outcomes after off-pump coronary artery bypass graft surgery[J]. J Thorac Cardiovasc Surg, 2010,139(6):1568-1575.DOI:10.1016/j.jtcvs.2009.11.057.
[22] Wallisch C, Zeiner S, Scholten P, et al.Development and internal validation of an algorithm to predict intraoperative risk of inadvertent hypothermia based on preoperative data[J]. Sci Rep, 2021,11(1):22296.DOI:10.1038/s41598-021-01743-z.
[23] 国家麻醉专业质量控制中心. 围术期患者低体温防治专家共识(2023版)[J]. 协和医学杂志, 2023,14(4):734-743.
[24] Zhao B, Zhu Z, Qi W, et al.Construction and validation of a risk prediction model for intraoperative hypothermia in elderly patients undergoing total hip arthroplasty[J]. Aging Clin Exp Res,2023,35(10):2127-2136.DOI:10.1007/s40520-023-02500-0.
[25] Kasai T, Hirose M, Matsukawa T, et al.The vasoconstriction threshold is increased in obese patients during general anaesthesia[J]. Acta Anaesthesiol Scand, 2003,47(5):588-592.DOI:10.1034/j.1399-6576.2003.00097.x.
[26] Li L, Lu Y, Yang L L, et al.Construction and validation of postoperative hypothermia prediction model for patients undergoing joint replacement surgery[J]. J Clin Nurs, 2023,32(13-14):3831-3839.DOI:10.1111/jocn.16503.
[27] Alshammari N A, Alodhayani A A, Joy S S, et al.Evaluation of risk factors for diabetic peripheral neuropathy among saudi type 2 diabetic patients with longer duration of diabetes[J]. Diabetes Metab Syndr Obes,2022,15:3007-3014.DOI:10.2147/DMSO.S364933.
[28] Kenny G P, Sigal R J, McGinn R. Body temperature regulation in diabetes[J]. Temperature (Austin), 2016,3(1):119-145.DOI:10.1080/23328940.2015.1131506.
[29] 李恒, 付秀荣, 郭栋. 腹腔镜手术病人术中低体温影响因素和预测模型的研究进展[J].护理研究, 2024,38(5):874-878.