利用决策树算法建立严重脓毒症院内死亡的风险预测模型及其效能验证-东南大学学报医学版

利用决策树算法建立严重脓毒症院内死亡的风险预测模型及其效能验证

单位：中国人民解放军海军第九七一医院急诊医学科, 山东青岛 266071

分类号：R631.2

出版年·卷·期（页码）：2025·44·第一期（90-98）

摘要：

目的:探讨严重脓毒症患者院内死亡的风险因素,并利用决策树算法建立院内死亡风险预测模型且验证模型效能,以指导临床工作。方法:回顾性选取本院243例严重脓毒症患者,根据院内死亡情况将其分为死亡组(n=98)与存活组(n=145)。比较两组临床资料,通过多因素Logistic回归分析影响患者院内死亡的相关因素。另根据2 : 1比例,将243例严重脓毒症患者随机分为模型组(n=162)与验证组(n=81),基于模型组数据利用决策树算法建立严重脓毒症患者院内死亡的风险预测模型,利用验证组数据对该模型进行验证。结果:经多因素Logistic回归分析,年龄≥60岁、入院时心率＞100次·min^-1、入院时平均动脉压＜70 mmHg、入院时氧合指数＜300 mmHg、急性生理学与慢性健康状况评分系统Ⅱ(APACHE Ⅱ)评分≥30分、序贯器官衰竭评分(SOFA)≥8分、中性粒细胞计数与淋巴细胞计数比值(NLR)＞3、红细胞压积(HCT)＜0.3、 ρ(白蛋白)＜35 g·L^-1、c(血肌酐)＞176.8 μmol·L^-1、活化部分凝血活酶时间(APTT)＞45 s、 ρ[B型脑钠肽前体(NT-proBNP)]≥2 000 pg·mL^-1、c(血乳酸)＞4.0 mmol·L^-1、 ρ[C反应蛋白(CRP)]＞50 mg·L^-1、 ρ[降钙素原(PCT)]＞2 ng·mL^-1均是严重脓毒症患者院内死亡的危险因素(P＜0.05);基于模型组数据,建立含SOFA、APACHE Ⅱ评分、血乳酸、白蛋白、NT-proBNP、NLR、CRP、PCT共8个解释变量在内的严重脓毒症患者院内死亡的风险预测决策树模型,其中SOFA最为重要。基于验证组数据对风险预测决策树模型进行验证,结果显示该风险预测决策树模型预测严重脓毒症患者院内死亡的灵敏度、特异度、准确度分别为87.10%、84.00%、85.19%。结论:利用决策树算法建立的严重脓毒症院内死亡风险预测模型包含SOFA、APACHE Ⅱ评分、血乳酸、白蛋白、NT-proBNP、NLR、CRP、PCT共8个变量,其中SOFA是最重要影响因素,该决策树模型对严重脓毒症院内死亡风险具有良好的预测效能,可用于指导临床防治。

Objective: To explore the risk factors of in-hospital mortality in patients with severe sepsis, and establishing an in-hospital mortality risk prediction model using decision tree algorithm and validating its effectiveness, to guide clinical work. Methods: 243 patients with severe sepsis were retrospectively selected and divided into a death group(n=98) and a survival group(n=145) based on in-hospital mortality. The clinical data between the two groups was compared, and the relevant factors affecting in-hospital mortality of patients was screened using multivariate Logistic regression analysis. In addition, 243 patients with severe sepsis were randomly divided into a model group(n=162) and a validation group(n=81) in 2 : 1 ratio, and a risk prediction model for in-hospital mortality in severe sepsis patients was established using decision tree algorithm based on model group data, and the model was validated using validation group data. Results:According to multiple Logistic regression analysis, age ≥60 years old, heart rate>100 beats·min^-1 at admission, mean arterial pressure<70 mmHg at admission, oxygenation index<300 mmHg at admission, acute physiology and chronic health score system Ⅱ(APACHEⅡ) score ≥30 points, sequential organ failure assessment(SOFA) score ≥8 points, ratio of neutrophil count to lymphocyte count(NLR)>3, hematocrit(HCT)<0.3, ρ(albumin)<35 g·L^-1,c(blood creatinine)>176.8 μmol·L^-1, activated partial thromboplastin time(APTT)>45 s, ρ[N terminal pro B type natriuretic peptide(NT-proBNP)] ≥2 000 pg·mL^-1,c(blood lactate)>4.0 mmol·L^-1,ρ[ C-reactive protein(CRP)]>50 mg·L^-1 and ρ[procalcitonin(PCT)]>2 ng·mL^-1 were all risk factors for in-hospital mortality in patients with severe sepsis(P<0.05). Based on model group data, a risk prediction decision tree model for in-hospital mortality in severe sepsis patients was established, and it included eight explanatory variables of SOFA score, APACHE Ⅱscore, blood lactate, albumin, NT proBNP, NLR, CRP and PCT, among which SOFA score was the most important. Decision tree model for risk prediction was validated based on validation group data, and the results showed that the sensitivity, specificity and accuracy of the risk prediction decision tree model in predicting in-hospital mortality of severe sepsis patients were 87.10%, 84.00% and 85.19% respectively. Conclusion:The in-hospital mortality risk prediction model for severe sepsis established using decision tree algorithm includes 8 variables of SOFA score, APACHE Ⅱscore, blood lactate, albumin, NT-proBNP, NLR, CRP and PCT, among which SOFA score is the most important influencing factor. This decision tree model has good predictive efficacy for the risk of in-hospital mortality in severe sepsis, and it can be used to guide clinical prevention and treatment.

参考文献：

[1] CHANDRA J, ARMENGOL DE LA HOZ M A, LEE G, et al.A novel vascular leak index identifies sepsis patients with a higher risk for in-hospital death and fluid accumulation[J]. Crit Care, 2022, 26(1):103.
[2] HAGIWARA A, TANAKA N, INABA Y, et al.Predictors of severe sepsis-related in-hospital mortality based on a multicenter cohort study:the focused outcomes research in emergency care in acute respiratory distress syndrome, sepsis, and trauma study[J]. Medicine(Baltimore), 2021, 100(8):e24844.
[3] 简万均, 蒋昌华, 符宜龙, 等.老年脓毒症病人28 d死亡的危险因素及预测模型建立[J]. 实用老年医学, 2022, 36(9):892-896.
[4] 汪德聪, 高见, 张华, 等.血清NGAL与Fetuin A对脓毒症患者28天死亡的预测价值[J]. 中国急救医学, 2022, 42(3):240-245.
[5] ELHAZMI A, AL-OMARI A, SALLAM H, et al.Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU[J]. J Infect Public Health, 2022, 15(7):826-834.
[6] 中华医学会重症医学分会, 严静.中国严重脓毒症/脓毒性休克治疗指南(2014)[J]. 中华内科杂志, 2015, 54(6):557-581.
[7] BAHTOUEE M, EGHBALI S S, MALEKI N, et al.Acute Physiology and Chronic Health Evaluation II score for the assessment of mortality prediction in the intensive care unit:a single-centre study from Iran[J]. Nurs Crit Care, 2019, 24(6):375-380.
[8] GUPTA T, PUSKARICH M A, DEVOS E, et al.Sequential Organ Failure Assessment Component score prediction of in-hospital mortality from sepsis[J]. J Intensive Care Med, 2020, 35(8):810-817.
[9] 向弘利, 刘玉新.基于ICU严重脓毒症患者死亡危险因素的系统回顾和Meta分析[J]. 创伤外科杂志, 2022, 24(8):580-588.
[10] 李俊玉, 王雅慧, 刘慧珍, 等.红细胞分布宽度与血小板计数比值对急诊脓毒症患者预后的预测价值[J]. 临床急诊杂志, 2022, 23(2):132-137.
[11] 王斌, 陈剑平, 欧阳建.脓毒症患者30天死亡风险预测模型的建立[J]. 中华急诊医学杂志, 2021, 30(10):1240-1247.
[12] 陆金帅, 姜媛, 王丽慧, 等.中心静脉-动脉血二氧化碳分压差联合中心静脉血氧饱和度指导感染性休克患者液体复苏的应用效果及预后的危险因素分析[J]. 现代生物医学进展, 2022, 22(18):3463-3468.
[13] 吕慧, 陈道南, 田锐, 等.红细胞压积和抗凝血酶Ⅲ联合APACHEⅡ评分在老年脓毒症患者90天预后中的评估价值[J]. 老年医学与保健, 2022, 28(6):1181-1186.
[14] 封慧, 李琴, 李思睿.脓毒症休克患者动脉血乳酸, 血清白蛋白比值在预测病情评估及转归的临床价值[J]. 中国实验诊断学, 2023, 27(1):37-40.
[15] LESTARI M I, SEDONO R, ZULKIF L I.Initial lactate levels versus lactate clearance for predicting mortality in sepsis:a prospective observational analytical study[J]. J Pak Med Assoc, 2021, 71(Suppl 2):S25-S29.
[16] 刘雪媛, 杨梁, 刘朝发.脓毒症患者预后相关危险因素的综合分析[J]. 现代医学, 2023, 51(3):294-298.
[17] 刘振国, 白惠惠, 王顺达.脓毒症患者SAA, PCT, ALB水平及SII, APACHEⅡ, SOFA评分与预后的相关性研究[J]. 海南医学, 2023, 34(17):2523-2526.
[18] ZHOU S, WEI J, TANG L, et al.A prognostic model for interventional thrombectomy in patients with acute ischemic stroke based on a BP neural network, random forest model and decision tree model[J]. Am J Transl Res, 2023, 15(5):3290-3299.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录