| 基于logistic回归和随机森林的急性缺血性卒中3个月预后预测模型的构建 |
| |
| 引用本文： | 覃伟,吕芯芮,王子尧,刘爽,邓宇含,姜勇,,刘宝花.基于logistic回归和随机森林的急性缺血性卒中3个月预后预测模型的构建[J].现代预防医学,2021,0(2):193-197. |
| |
| 作者姓名： | 覃伟 吕芯芮 王子尧 刘爽 邓宇含 姜勇 刘宝花 |
| |
| 作者单位： | 1. 北京大学公共卫生学院社会医学与健康教育系， 北京 100191；2. 首都医科大学附属北京天坛医院；国家神经系统疾病临床医学研究中心；3. 北京大数据精准医疗高精尖创新中心（北京航空航天大学&首都医科大学） |
| |
| 摘 要： | 目的 基于logistic回归和随机森林构建急性缺血性卒中（acute ischemic stroke，AIS）3个月预后预测模型，并比较预测效果。方法 使用中国国家卒中登记Ⅱ（China National Stoke Registry Ⅱ，CNSRⅡ）数据库中的AIS数据，备选预测因子包括人口学特征、既往病史、用药史、临床检测指标、入院情况、院内情况、出院情况等不同时间点的变量。将数据按照8∶2随机分为训练集和测试集，在训练集中分别使用logistic回归和随机森林构建AIS患者3个月预后预测模型，在测试集中使用受试者工作特征曲线下面积（area under curve, AUC）评价区分度，使用Homser - Lemeshow检验和校准图来评价校准度。结果 最终纳入数据分析共9 847例AIS患者，其中61～80岁6 093例，男性6 477例，预后不良1 515例。在测试集中，logistic回归与随机森林的AUC差异无统计学意义（0.821,95%CI:0.815～0.827vs 0.825,95%CI:0.821～0.829,P = 0.268）,且两类模型的校准度均较好（χ2 = 5.67，P = 0.684 vs χ2 = 8.52，P = 0.385）。结论 基于logistic回归和随机森林建立的AIS患者3个月预后预测模型的区分度和校准度均较好。
|
| 关 键 词： | 急性缺血性卒中 预后预测 logistic回归 随机森林 |
Prediction model for 3-month prognosis in patients with acute ischemic stroke based on logistic regression and random forest methods |
| |
| QIN Wei,LV Xin-rui,WANG Zi-yao,LIU Shuang,DENG Yu-han,JIANG Yong,LIU Bao-hua.Prediction model for 3-month prognosis in patients with acute ischemic stroke based on logistic regression and random forest methods[J].Modern Preventive Medicine,2021,0(2):193-197. |
| |
| Authors: | QIN Wei LV Xin-rui WANG Zi-yao LIU Shuang DENG Yu-han JIANG Yong LIU Bao-hua |
| |
| Affiliation: | *Department of social medicine and health education, School of public health, Peking University, Beijing 100191, China |
| |
| Abstract: | Objective To construct and compare prediction models for 3-month prognosis in patients with acute ischemic stroke(AIS) based on logistic regression and random forest methods. Methods Data of AIS patients in the China National Stroke Registry Ⅱ(CNSR Ⅱ) were retrospectively analyzed. Candidate predictors included demographic characteristics,medical history, medication history, clinical indicators, admission, and hospitalization and discharge. The data were randomly divided into a training set and test set at a ratio of 8:2. In the training set, logistic regression and random forest were used to construct a 3-month prognosis prediction model. In the test set, the area under the receiver operating characteristic curve(AUC) was used to evaluate the discrimination, and the Homser-Lemeshow test and calibration chart were used to evaluate the model calibration. Results A total of 9 847 patients were included in the analysis, of which 6 093 patients were 61 to 80 years old, 6 477 were males, and 1515 had poor prognosis. In the test set, no significant difference was found in AUC between logistic regression and random forest model(OR=0.821, 95%CI: 0.815-0.827 vs OR=0.825, 95%CI: 0.821-0.829; P=0.268), and the calibration of two models were both good(χ |
| |
| Keywords: | Acute ischemic stroke Prognosis prediction Logistic regression Random forest |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《现代预防医学》浏览原始摘要信息 |
|
点击此处可从《现代预防医学》下载全文 |
|
