ICU患者肠内营养相关性腹泻风险预测模型的构建及验证

doi:10.3761/j.issn.0254-1769.2022.19.003

摘要/Abstract

摘要：

目的探讨ICU患者肠内营养相关性腹泻（enteral nutrition-associated diarrhea,ENAD）的危险因素,基于随机森林算法,构建并验证风险预测模型。方法回顾性收集2017年8月—2021年5月在天津市某三级甲等医院ICU住院且行肠内营养的537例患者的资料,采用单因素分析、多重共线性分析、Logistic回归分析筛选ENAD的危险因素。再将数据按6：4的比例随机分为训练组和验证组。基于训练组数据,利用随机森林算法,建立ENAD风险预测模型,对危险因素的重要性进行排序,并绘制部分依赖图,分析危险因素的变化对ENAD发生风险的影响。对验证组数据进行混淆矩阵分析,采用准确率、灵敏度、特异度和受试者操作特征曲线下面积评价模型的预测效果。结果 ENAD发生率为38.73%,经单因素分析、多重共线性分析、Logistic回归分析后初步确定9个危险因素,其中重要性排序前5位的危险因素为口服钾制剂天数、急性生理与慢性健康状况Ⅱ评分、平均每日肠内营养量、禁食天数、白蛋白浓度≤35 g/L。验证组中,风险预测模型的准确率76.27%,灵敏度70.73%,特异度79.70%,受试者操作特征曲线下面积为0.810（95%CI：0.638~0.827）。结论该风险预测模型的预测效能良好,可为护理人员制订个性化预防措施提供参考。

关键词: 重症监护病房, 肠内营养, 腹泻, 随机森林算法, 护理

Abstract:

Objective To explore the risk factors of enteral nutrition-associated diarrhea（ENAD）,and to construct a risk prediction model based on random forest. Methods This study adopted a retrospective data collection method. A total of 537 ICU patients who received enteral nutrition in a tertiary hospital in Tianjin from August 2017 to May 2021 were enrolled. Based on univariate analysis and multivariate logistic regression analysis and VIF,the variables of the risk prediction model for enteral nutrition-associated diarrhea were determined. All data are randomly divided into a training set and a validation set by 6：4. Based on the training set data,the random forest model of ENAD is established,and the importance of ENAD risk factors was ranked by variable importance score using a random forest model. Confusion matrix analysis,accuracy,sensitivity,specificity,and area under the ROC curve were used to evaluate the predictive effect of the model on the validation dataset. Results The incidence of ENAD in this study was 38.73%. After univariate analysis,multivariate Logistic regression analysis and VIF,9 variables were determined to be included in the prediction model. The top 5 variable importance scores of the random forest prediction model include days of taking potassium preparations,APACHE Ⅱ score,daily doses of enteral nutrition,fasting days before enteral nutrition and hypoproteinemia. The accuracy of the random forest model on the validation set is 76.27%;the sensitivity is 70.73%;the specificity is 79.70%;the area under the ROC curve is 0.810（95%CI：0.638~0.827）. Conclusion The predictive model has good predictive performance,which provides a reference for the precise prevention of clinical nurses with certain practical significance.

Key words: Intensive Care Units, Enteral Nutrition, Diarrhea, Random Forest Algorithm, Nursing Care

谢文亮, 王淑芳, 李旭光, 张清. ICU患者肠内营养相关性腹泻风险预测模型的构建及验证[J]. 中华护理杂志, 2022, 57(19): 2324-2331.

XIE Wenliang, WANG Shufang, LI Xuguang, ZHANG Qing. Establishment and validation of a risk prediction model for enteral nutrition-associated diarrhea in ICU patients[J]. Chinese Journal of Nursing, 2022, 57(19): 2324-2331.

图/表 6

表1 ICU患者肠内营养相关性腹泻风险预测模型训练组和验证组一般资料比较

Table 1 Comparison of general data between training group and validation group of enteral nutrition-associated diarrhea risk prediction model in ICU patients

表2 ICU患者肠内营养相关性腹泻危险因素的单因素分析结果

Table 2 Univariate analysis of risk factors for enteral nutrition-associated diarrhea in ICU patients

表3 ICU患者肠内营养相关性腹泻Logistic回归分析结果

Table 3 Multivariate Logistic regression analysis of enteral nutrition-associated diarrhea in ICU patients

表4 ICU患者肠内营养相关性腹泻危险因素的重要性分析结果

Table 4 Importance analysis results of risk factors for enteral nutrition-associated diarrhea in ICU patients

图1 口服钾制剂天数、急性生理与慢性健康状况Ⅱ评分、平均每日肠内营养量、禁食天数与ICU患者肠内营养相关性腹泻发生风险的部分依赖图注：APACHE为急性生理与慢性健康状况;A为口服钾制剂天数与ICU患者肠内营养相关性腹泻发生风险的关系;B为APACHE Ⅱ与ICU患者肠内营养相关性腹泻发生风险的关系;C为平均每日肠内营养量与ICU患者肠内营养相关性腹泻发生风险的关系;D为禁食天数与ICU患者肠内营养相关性腹泻发生风险的关系。

Figure 1 Partial dependence plots of days of taking potassium preparations, APACHE Ⅱ score, daily doses of enteral nutrition, fasting days before enteral nutrition on the risk of enteral nutrition-associated diarrhea in ICU patients

图2 验证组中ICU患者肠内营养相关性腹泻风险预测模型的受试者操作特征曲线

Figure 2 The ROC curve of predictive models for enteral nutrition-associated diarrhea in ICU patients

参考文献 27

[1]	McClave SA, Taylor BE, Martindale RG, et al. Guidelines for the provision and assessment of nutrition support therapy in the adult critically ill patient:Society of Critical Care Medicine(SCCM) and American Society for Parenteral and Enteral Nutrition(A.S.P.E.N.)[J]. JPEN J Parenter Enter Nutr, 2016, 40(2):159-211. DOI URL
[2]	Reintam Blaser A, Deane AM, Fruhwald S. Diarrhoea in the critically ill[J]. Curr Opin Crit Care, 2015, 21(2):142-153. DOI PMID
[3]	远庚. 综合ICU患者腹泻相关因素分析及中医证型回顾性研究[D]. 北京: 中国中医科学院, 2012.
	Yuan G. Diarrhea related factors analysis and TCM syndrome retrospective study in general ICU patients[D]. Beijing: China Academy of Chinese Medical Sciences, 2012.
[4]	Fabiani A, Sanson G, Bottigliengo D, et al. Impact of a natural versus commercial enteral-feeding on the occurrence of diarrhea in critically ill cardiac surgery patients. A retrospective cohort study[J]. Int J Nurs Stud, 2020, 108:103605. DOI URL
[5]	Pitta MR, Campos FM, Monteiro AG, et al. Tutorial on diarrhea and enteral nutrition:a comprehensive step-by-step approach[J]. JPEN J Parenter Enteral Nutr, 2019, 43(8):1008-1019. DOI URL
[6]	危娟, 林凤英, 莫红平, 等. ICU患者肠内营养期间腹泻的相关因素分析[J]. 中华护理杂志, 2015, 50(8):954-959.
	Wei J, Lin FY, Mo HP, et al. A retrospective analysis of factors related to diarrhea during enteral nutrition in ICU patients[J]. Chin J Nurs, 2015, 50(8):954-959.
[7]	王先美, 陈卫挺, 叶立刚, 等. 浙江省ICU危重症患者肠内营养早期腹泻的调查研究[J]. 中华急诊医学杂志, 2018, 27(10):1142-1147.
	Wang XM, Chen WT, Ye LG, et al. Investigation on early diarrhea during enteral nutrition in critically ill patients admitted to ICU in Zhejiang Province[J]. Chin J Emerg Med, 2018, 27(10):1142-1147.
[8]	米元元, 沈月, 郝彬, 等. ICU患者肠内营养支持并发腹泻的循证护理实践[J]. 中华护理杂志, 2017, 52(11):1291-1298.
	Mi YY, Shen Y, Hao B, et al. Evidence-based nursing practice of enteral nutrition support among ICU patients with diarrhea[J]. Chin J Nurs, 2017, 52(11):1291-1298.
[9]	Chang SJ, Huang HH. Diarrhea in enterally fed patients:blame the diet?[J]. Curr Opin Clin Nutr Metab Care, 2013, 16(5):588-594. DOI URL
[10]	Xie Y, Tian R, Wang T, et al. A prediction model of enteral nutrition complicated with severe diarrhea in ICU patients based on CD55[J]. Ann Palliat Med, 2021, 10(2):1610-1619. DOI PMID
[11]	Wu XY, Li XZ, Yu DL, et al. Construction of a model predicting the risk of tube feeding intolerance after gastrectomy for gastric cancer based on 225 cases from a single Chinese center[J]. Oncotarget, 2017, 8(59):99940-99949. DOI PMID
[12]	郭长满, 郭敏, 刘媛媛, 等. 机器学习算法在预测男男性行为人群中HIV感染的应用[J]. 中国卫生统计, 2019, 36(1):28-31,35.
	Guo CM, Guo M, Liu YY, et al. Application of machine-learning algorithms in predicting HIV infection among men who have sex with men[J]. Chin J Heal Stat, 2019, 36(1):28-31,35.
[13]	刘沛, 郭威, 王中亮, 等. 基于logistic回归和随机森林的慢性肾脏病危险程度预测模型[J]. 中国卫生统计, 2020, 37(4):514-518.
	Liu P, Guo W, Wang ZL, et al. Multi-classification logistic regression and random forest model on the risk of CKD prediction[J]. Chin J Heal Stat, 2020, 37(4):514-518.
[14]	吴鸟青, 赵莉莉. ICU肠内营养相关性腹泻的危险因素分析[J]. 中国卫生标准管理, 2021, 12(18):78-81.
	Wu NQ, Zhao LL. Risk factors of enteral nutrition related diarr-hea in ICU[J]. China Heal Stand Manag, 2021, 12(18):78-81.
[15]	Kurisu K, Yoshiuchi K, Ogino K, et al. Machine learning analysis to identify the association between risk factors and onset of nosocomial diarrhea:a retrospective cohort study[J]. Peer J, 2019, 7:e7969. DOI URL
[16]	Chen WT, Wang HH, Chen YZ, et al. The independent risk factors of early diarrhoea in enteral nutrition for ICU patients[J]. J Int Med Res, 2019, 47(10):4929-4939. DOI PMID
[17]	王斌会. 计量经济学模型及R语言应用[M]. 广州: 暨南大学出版社, 2015.
	Wang BH. Econometric models and the application of R language[M]. Guangzhou: Jinan University Press, 2015.
[18]	Zaman MK, Noor Azman RSR. Diarrhoea risk factors in critically ill patients receiving enteral nutrition[J]. Malaysian J Med Health Sci, 2021, 17(6):140-145.
[19]	陈卫挺. ICU危重症患者肠内营养早期的腹泻调查研究[D]. 杭州: 浙江大学, 2017.
	Chen WT. Investigation on early diarrhea during enteral nutrition in critically ill patients admitted to ICU[D]. Hangzhou: Zhejiang University, 2017.
[20]	莫雪秋, 滕海英, 黄琼兰, 等. 护理改善专案在降低肠内营养患者腹泻发生率中的应用[J]. 中国临床护理, 2019, 11(2):147-149.
	Mo XQ, Teng HY, Huang QL, et al. Application of nursing improvement project in reducing the incidence of diarrhea of enteral nutrition patients[J]. Chin Clin Nurs, 2019, 11(2):147-149.
[21]	封宇飞. 氯化钾片说明书[EB/OL]. [2022-05-18]. https://www.dayi.org.cn/drug/1146026.
	Feng YF. Potassium chloride tablets instructions[EB/OL]. [2022-05-18]. https://www.dayi.org.cn/drug/1146026.
[22]	Yahyapoor F, Dehnavi Z, Askari G, et al. The prevalence and possible causes of enteral tube feeding intolerance in critically ill patients:a cross-sectional study[J]. J Res Med Sci, 2021, 26:60. DOI PMID
[23]	Deane AM, Rayner CK, Keeshan A, et al. The effects of critical illness on intestinal glucose sensing,transporters,and absorption[J]. Crit Care Med, 2014, 42(1):57-65. DOI PMID
[24]	邱远, 杨桦. 营养支持治疗在肠功能障碍中的作用及意义[J]. 肠外与肠内营养, 2016, 23(5):260-262,269.
	Qiu Y, Yang H. Role and significance of nutritional support therapy in intestinal dysfunction[J]. Parenter Enter Nutr, 23(5):260-262,269.
[25]	郑菁, 陈刚, 陈鑫鑫. 老年重症患者肠内营养相关性腹泻的原因分析与护理对策[J]. 护理实践与研究, 2019, 16(9):24-26.
	Zheng J, Chen G, Chen XX. Analysis of causes of enteral nutrition-related diarrhea in elderly patients with severe disease and its nursing strategies[J]. Nurs Pract Res, 2019, 16(9):24-26.
[26]	Vieira LV, Pedrosa LAC, Souza VS, et al. Incidence of diarrhea and associated risk factors in patients with traumatic brain injury and enteral nutrition[J]. Metab Brain Dis, 2018, 33(5):1755-1760. DOI PMID
[27]	荆晨晨, 孙淑青, 秦德春. 急性呼吸窘迫综合征患者早期风险预测模型的建立[J]. 中华护理杂志, 2020, 55(9):1285-1291. DOI URL
	Jing CC, Sun SQ, Qin DC. Establishment of an early risk prediction model for patients with acute respiratory distress syndrome in ICU[J]. Chin J Nurs, 2020, 55(9):1285-1291. DOI URL