基于多维动态临床特征的危重症患者死亡预测模型开发
该研究从中南大学湘雅三医院HIS系统提取2014年1月至2020年6月收治的10 925例>14岁危重症患者临床数据,以689例有APACHE II评分记录者作为测试集,其余10 236例用于建模(10%验证集、90%训练集),基于临终前3天一般信息、生命体征、生化检查及静脉用药剂量等动态特征构建随机森林死亡预测模型。测试集结果显示,随机森林模型AUROC为0.856(95%CI 0.812-0.896),高于APACHE II模型的0.783(95%CI 0.737-0.826);AUPRC为0.650(95%CI 0.604-0.762),高于APACHE II的0.524(95%CI 0.439-0.609);Brier评分0.104(95%CI 0.085-0.113),低于APACHE II的0.124(95%CI 0.107-0.141)。作者认为基于多维动态特征的随机森林模型对危重症患者住院死亡风险预测有较大应用价值,优于传统APACHE II评分系统。
要点
- 测试集随机森林模型AUROC 0.856(95%CI 0.812-0.896),高于APACHE II模型0.783(95%CI 0.737-0.826)。
- 测试集随机森林模型AUPRC 0.650(95%CI 0.604-0.762),高于APACHE II模型0.524(95%CI 0.439-0.609)。
- 测试集随机森林模型Brier评分0.104(95%CI 0.085-0.113),低于APACHE II模型0.124(95%CI 0.107-0.141)。
- 建模纳入临终前3天一般信息、生命体征、生化检查及静脉用药剂量等多维动态特征。
- 死亡组较生存组年龄更大(60.1±16.5岁 vs. 58.5±16.4岁,P<0.01),ICU入住比例更高(82.8% vs. 77.1%,P<0.01)。
适用人群与场景
- 2014年1月至2020年6月中南大学湘雅三医院收治的年龄>14岁危重症患者,共10 925例,其中78.2%(8 538例)入住ICU。
研究设计与关键结果
- 研究类型为基于医院信息系统的死亡预测模型开发与验证研究,样本量10 925例,来源为单家医院(中南大学湘雅三医院),人群为年龄>14岁危重症患者,干预/暴露为基于临终前3天多维动态临床特征构建的随机森林模型,对照为APACHE II模型。
- 共10 925例中男性7 797例(71.4%)、女性3 128例(28.6%),平均年龄(58.9±16.3)岁,住院时间中位数12(7,20)天,ICU住院时间中位数66(13,151)小时,住院死亡率19.0%(2 077/10 925)。
- 与生存组(8 848例)相比,死亡组(2 077例)年龄更大(60.1±16.5岁 vs. 58.5±16.4岁,P<0.01),ICU入住比例更高(82.8% vs. 77.1%,P<0.01),高血压病史比例更高(44.7% vs. 36.3%,P<0.01),糖尿病病史比例更高(20.0% vs. 16.9%,P<0.01),卒中病史比例更高(15.5% vs. 10.0%,P<0.01)。
- 测试集(689例有APACHE II评分记录者)中随机森林模型AUROC 0.856(95%CI 0.812-0.896),高于APACHE II模型0.783(95%CI 0.737-0.826)。
- 测试集中随机森林模型AUPRC 0.650(95%CI 0.604-0.762),高于APACHE II模型0.524(95%CI 0.439-0.609)。
- 测试集中随机森林模型Brier评分0.104(95%CI 0.085-0.113),低于APACHE II模型0.124(95%CI 0.107-0.141)。
证据类型、等级与局限
- 证据类型:基于医院信息系统的预测模型开发与验证研究(随机森林模型),以APACHE II模型为对照。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为基于多维动态特征的随机森林模型对危重症患者住院死亡风险预测有较大应用价值,优于传统APACHE II评分系统。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop a mortality prediction model for critically ill patients based on multidimensional and dynamic clinical data collected by the hospital information system (HIS) using random forest algorithm, and to compare the prediction efficiency of the model with acute physiology and chronic health evaluation II (APACHE II) model.
METHODS: The clinical data of 10 925 critically ill patients aged over 14 years old admitted to the Third Xiangya Hospital of Central South University from January 2014 to June 2020 were extracted from the HIS system, and APACHE II scores of the critically ill patients were extracted. Expected mortality of patients was calculated according to the death risk calculation formula of APACHE II scoring system. A total of 689 samples with APACHE II score records were used as the test set, and the other 10 236 samples were used to establish the random forest model, of which 10% (n = 1 024) were randomly selected as the validation set and 90% (n = 9 212) were selected as the training set. According to the time series of 3 days before the end of critical illness, the clinical characteristics of patients such as general information, vital signs data, biochemical test results and intravenous drug doses were selected to develope a random forest model for predicting the mortality of critically ill patients. Using the APACHE II model as a reference, receiver operator characteristic curve (ROC curve) was drawn, and the discrimination performance of the model was evaluated through the area under the ROC curve (AUROC). According to the precision and recall, Precision-Recall curve (PR curve) was drawn, and the calibration performance of the model was evaluated through the area under the PR curve (AUPRC). Calibration curve was drawn, and the consistency between the predicted event occurrence probability of the model and the actual occurrence probability was evaluated through the calibration index Brier score.
RESULTS: Among the 10 925 patients, there were 7 797 males (71.4%) and 3 128 females (28.6%). The average age was (58.9±16.3) years old. The median length of hospital stay was 12 (7, 20) days. Most patients (n = 8 538, 78.2%) were admitted to intensive care unit (ICU), and the median length of ICU stay was 66 (13, 151) hours. The hospitalized mortality was 19.0% (2 077/10 925). Compared with the survival group (n = 8 848), the patients in the death group (n = 2 077) were older (years old: 60.1±16.5 vs. 58.5±16.4, P < 0.01), the ratio of ICU admission was higher [82.8% (1 719/2 077) vs. 77.1% (6 819/8 848), P < 0.01], and the proportion of patients with hypertension, diabetes and stroke history was also higher [44.7% (928/2 077) vs. 36.3% (3 212/8 848), 20.0% (415/2 077) vs. 16.9% (1 495/8 848), 15.5% (322/2 077) vs. 10.0% (885/8 848), all P < 0.01]. In the test set data, the prediction value of random forest model for the risk of death during hospitalization of critically ill patients was greater than that of APACHE II model, which showed by that the AUROC and AUPRC of random forest model were higher than those of APACHE II model [AUROC: 0.856 (95% confidence interval was 0.812-0.896) vs. 0.783 (95% confidence interval was 0.737-0.826), AUPRC: 0.650 (95% confidence interval was 0.604-0.762) vs. 0.524 (95% confidence interval was 0.439-0.609)], and Brier score was lower than that of APACHE II model [0.104 (95% confidence interval was 0.085-0.113) vs. 0.124 (95% confidence interval was 0.107-0.141)].
CONCLUSIONS: The random forest model based on multidimensional dynamic characteristics has great application value in predicting hospital mortality risk for critically ill patients, and it is superior to the traditional APACHE II scoring system.
参考来源
- Zhao S, Tang G, Liu P, et al. [Development of mortality prediction model for critically ill patients based on multidimensional and dynamic clinical characteristics]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2023. PMID: 37308199. doi:10.3760/cma.j.cn121430-20220607-00550
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。