随机森林与Logistic回归模型对子宫内膜癌患者加速康复外科术后早期出院预测的比较

doi:10.16460/j.issn1008-9969.2023.01.017

摘要/Abstract

摘要： 目的应用随机森林和Logistic回归分别构建子宫内膜癌患者加速康复外科术后早期出院预测模型,比较2种模型预测效果。方法采用便利抽样法,选取2019年1月-2021年12月在某三级甲等医院接受妇科加速康复外科手术并符合纳排标准的子宫内膜癌患者328例,按照7∶3的比例随机分配至建模组和验证组,运用随机森林和Logistic回归构建子宫内膜癌患者加速康复外科术后早期出院预测模型,采用准确度、灵敏度、特异度、阳性预测值、阴性预测值、约登指数和受试者工作特征曲线下面积对2种模型的性能进行比较。结果建模组中,随机森林与Logistic回归准确度为1.000,0.896、灵敏度为1.000,0.833、特异度为1.000,0.915、阳性预测值为1.000,0.750、阴性预测值为1.000,0.942、约登指数为1.000,0.729、AUC为1.000,0.950;验证组中,随机森林与Logistic回归准确度为0.969,0.888、灵敏度为0.960,0.750、特异度为0.973,0.943、阳性预测值为0.923,0.840、阴性预测值为0.986,0.904、约登指数为0.933,0.693、AUC为0.940,0.900。结论随机森林模型对子宫内膜癌患者加速康复外科术后早期出院的预测性能优于Logistic回归模型。

关键词: 随机森林, Logistic回归, 加速康复外科, 子宫内膜癌患者, 预测模型, 住院时间

Abstract: Objective To construct prediction models for early discharge of endometrial cancer patients after enhanced recovery after surgery (ERAS) with random forest and Logistic regression, respectively, and compare the prediction effects of the 2 models. Methods Using convenience sampling, 328 patients with endometrial cancer who underwent ERAS and met the inclusion and exclusion criteria in a tertiary grade-A hospital from January 2019 to December 2021 were randomly assigned to model group and validation group according to the ratio of 7∶3, and the random forest and Logistic regression were used to construct the prediction models of early discharge after ERAS for patients with endometrial cancer. The performance of the 2 models was compared in terms of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, Jorden index, and AUC of ROC. Results In the model group, the accuracy of random forest and Logistic regression was 1.000, and 0.896; sensitivity 1.000, and 0.833; specificity 1.000, and 0.915; positive predictive value 1.000, and 0.750; negative predictive value 1.000, and 0.942; Jorden index 1.000,and 0.729 and AUC 1.000, and 0.950 respectively; in the validation group, the accuracy of random forest and Logistic regression was 0.969, and 0.888; sensitivity 0.960, and 0.750; specificity 0.973, and 0.943; positive predictive value 0.923, and 0.840; negative predictive value 0.986, and 0.904; Jorden’s index 0.933, 0.693, and AUC 0.940, and 0.900, respectively. Conclusion Random forest model outperforms Logistic regression model in predicting early discharge after enhanced recovery after surgery for endometrial cancer patients.

Key words: random forest, Logistic regression, enhanced recovery after surgery, endometrial cancer patients, prediction model, length of stay

中图分类号:

R713

李梦娜, 刘晓夏, 陈美文, 赵蕊, 葛莉娜. 随机森林与Logistic回归模型对子宫内膜癌患者加速康复外科术后早期出院预测的比较[J]. 护理学报, 2023, 30(1): 17-21.

LI Meng-na, LIU Xiao-xia,CHEN Mei-wen, ZHAO Rui, GE Li-na. Comparison of random forest and Logistic regression models for predicting early discharge after enhanced recovery after surgery for patients with endometrial cancer[J]. Journal of Nursing, 2023, 30(1): 17-21.

参考文献

[1] 刘美玲,龚桂芳,肖玉梅,等. 日间病房妇科腹腔镜手术患者快速康复循证护理实践[J]. 护理学报, 2019,26(15):31-35. DOI:10.16460/j.issn1008-9969.2019.15.031.
[2] Crane EK, Brown J, Lehman A, et al.Perioperative recovery and narcotic use in laparoscopic versus robotic surgery for endometrial cancer[J]. J Minim Invasive Gynecol, 2021,28(11):1898-1902. DOI: 10.1016/j.jmig.2021.04.022.
[3] 中国抗癌协会妇科肿瘤专业委员会. 子宫内膜癌诊断与治疗指南(2021年版)[J]. 中国癌症杂志, 2021,31(6):501-512. DOI:10.19401/j.cnki.1007-3639.2021.06.08.
[4] Berian JR, Ban KA, Liu JB, et al.Adherence to enhanced recovery protocols in NSQIP and association with colectomy outcomes[J]. Ann Surg, 2019,269(3):486-493. DOI: 10.1097/SLA.0000000000002566.
[5] De Nonneville A, Jauffret C, Braticevic C, et al.Enhanced recovery after surgery program in older patients undergoing gynaecologic oncological surgery is feasible and safe[J]. Gynecol Oncol, 2018,151(3):471-476. DOI:10.1016/j.ygyno.2018.09.017.
[6] Smith CG, Davenport DL, Hoffman MR.Characteristics associated with prolonged length of stay after myomectomy for uterine myomas[J]. J Minim Invasive Gynecol, 2019,26(7):1303-1310. DOI: 10.1016/j.jmig.2018.12.015.
[7] Crane EK, Brown J, Lehman A, et al.Perioperative recovery and narcotic use in laparoscopic versus robotic surgery for endometrial cancer[J]. J Minim Invasive Gynecol, 2021,28(11):1898-1902. DOI: 10.1016/j.jmig.2021.04.022.
[8] Shao W, Zhang Z, Zhang J, et al.Charlson comorbidity index as a predictor of short-term outcomes after pulmonary resection[J]. J Thorac Dis, 2020,12(11):6670-6679. DOI:10.21037/jtd-20-2264.
[9] Datta A, Sebastian A, Chandy RG, et al.Complications and outcomes of diaphragm surgeries in epithelial ovarian malignancies[J]. Indian J Surg Oncol, 2021,12(4):822-829. DOI: 10.1007/s13193-021-01438-x.
[10] 马佳楚,商临萍,李淑花,等. 慢性阻塞性肺疾病患者住院时间延长危险因素的Meta分析[J].解放军护理杂志, 2022,39(2):60-63.
[11] Sánchez-Iglesias JL, Gómez-Hidalgo NR,Pérez-Benavente A, et al.Importance of enhanced recovery after surgery (ERAS) protocol compliance for length of stay in ovarian cancer surgery[J]. Ann Surg Oncol, 2021,28(13):8979-8986. DOI: 10.1245/s10434-021-10228-2.
[12] 刘娇. 快速康复外科护理在腹腔镜宫颈癌根治术患者中的应用[J]. 医疗装备, 2019,32(21):181-183.
[13] 轩俊娜. 快速康复外科理念对子宫内膜癌手术患者术前焦虑和术后疼痛的影响[J].中国民康医学,2018,30(10):112-114.
[14] 吴莹. 快速康复外科理念在达芬奇机器人子宫内膜腺癌手术患者中应用的随机对照研究[D].郑州:郑州大学, 2021. DOI:10.27466/d.cnki.gzzdu.2021.000531.
[15] Obermair A, Janda M, Baker J, et al.Improved surgical safety after laparoscopic compared to open surgery for apparent early stage endometrial cancer: results from a randomised controlled trial[J]. Eur J Cancer, 2012,48(8):1147-1153. DOI: 10.1016/j.ejca.2012.02.055.
[16] Laughlin-Tommaso S K, Lu D, Thomas L, et al. Short-term quality of life after myomectomy for uterine fibroids from the COMPARE-UF fibroid registry[J]. Am J Obstet Gynecol,2020,222(4):341-345.DOI:10.1016/j.ajog.2019.09.052.
[17] 中华医学会外科学分会,中华医学会麻醉学分会. 中国加速康复外科临床实践指南(2021)(三)[J]. 中华麻醉学杂志, 2021,41(9):1044-1052.
[18] Giglio MT, Marucci M, Testini M, et al.Goal-directed haemodynamic therapy and gastrointestinal complications in major surgery: a meta-analysis of randomized controlled trials[J]. Br J Anaesth, 2009,103(5):637-646. DOI:10.1093/bja/aep279.
[19] 吴可可,胡晓春,陈丹,等. 1例剖宫产后产褥期急性肺栓塞合并心脏骤停患者急救护理[J]. 护理学报, 2019,26(2):61-63. DOI:10.16460/j.issn1008-9969.2019.02.061.
[20] McKenny M, Conroy P, Wong A, et al. A randomised prospective trial of intra-operative oesophageal doppler-guided fluid administration in major gynaecological surgery[J]. Anaesthesia, 2013,68(12):1224-1231. DOI:10.1111/anae.12355.

相关文章 15

[1]	楚文强, 彭俊祥, 李丹玲. 基于Logistic回归分析颅脑手术后炎症指标动态变化及对颅内感染的诊断价值[J]. 护理学报, 2023, 30(1): 22-27.
[2]	许芳, 姚志清, 韩伟, 韩生伟. 口腔癌根治术患者术中低体温风险预测模型的构建及验证[J]. 护理学报, 2022, 29(7): 1-6.
[3]	杨洁, 谢小华, 连万成, 杨梅, 邓丽萍, 潘璐. 急性缺血性脑卒中静脉溶栓后出血预测模型的构建与验证[J]. 护理学报, 2022, 29(5): 10-14.
[4]	吴伟霞, 张一鸣, 何宗斌, 黄静文, 申海燕. 上尿路结石术后患者留置双J管出院风险预测模型的构建研究[J]. 护理学报, 2022, 29(4): 64-68.
[5]	赵晓蕊, 龙云, 陈思齐, 白洁, 肖霄, 朱社宁. 妇科恶性肿瘤患者术后胃肠功能紊乱风险预测模型的构建及验证[J]. 护理学报, 2022, 29(3): 72-78.
[6]	焦子珊, 张新月, 沙凯辉. 决策树C5.0与Logistic回归对产后压力性尿失禁预测性能的比较[J]. 护理学报, 2022, 29(3): 12-18.
[7]	陈静文, 徐林霞, 吴秀丽, 李显蓉. 基于Logistic回归与决策树模型的结直肠癌术后患者非计划性再入院影响因素分析[J]. 护理学报, 2022, 29(2): 1-6.
[8]	祁进芳, 董正惠, 李阳, 李振刚, 王志伟. ICU患者头面部器械相关性压力性损伤风险预测模型的构建[J]. 护理学报, 2022, 29(19): 11-15.
[9]	李蓉蓉, 张国娇, 王婷, 罗鸿萍, 范亚维. 基于精益质量管理模型的加速康复外科标准化全程管理方案的构建及在肝切除病人中的应用[J]. 护理学报, 2022, 29(18): 30-33.
[10]	苏小平, 徐静娟, 赵亚东, 张允, 陈建芬. 危重患者早期肠内营养喂养不耐受风险预测模型的构建[J]. 护理学报, 2022, 29(17): 47-51.
[11]	韩婷, 钱绪芬, 王庆芳, 程新春, 郭俊梅, 肖江琴. 基于Logistic回归和决策树模型的老年住院患者肌少症风险的影响因素分析[J]. 护理学报, 2022, 29(12): 56-62.
[12]	庞雪滢, 胡少华, 李慧, 尹丹乔, 张尚鑫, 杨晓东. 直肠癌患者保肛术1年后发生重度低位前切除综合征列线图预测模型的构建[J]. 护理学报, 2022, 29(11): 5-10.
[13]	石志宜, 刘玉凤, 王淑靖, 邢丽媛, 张红梅. 妊娠相关下腰痛风险预测模型的构建与验证[J]. 护理学报, 2022, 29(10): 67-72.
[14]	郭盛丽, 袁薇, 朱婷, 林威娜, 陈晓容, 夏美燕. 患者结肠镜检查前肠道准备失败风险预测模型的系统评价[J]. 护理学报, 2022, 29(1): 35-40.
[15]	周田田, 黄萍, 邹圣强. 急性缺血性脑卒中患者静脉溶栓后出血转化预测模型的研究进展[J]. 护理学报, 2021, 28(6): 17-21.

Metrics

Viewed

Full text

Abstract

Cited

Shared