机构：[1]Institute of Neuroscience, Kunming Medical University, Kunming, Yunnan,China[2]Department of Neurology, Nanbu People's Hospital, Nanbu, Sichuan, China[3]Department of Neurology, The Third People’s Hospital of Chengdu & TheAffiliated Hospital of Southwest Jiaotong University, Chengdu, Sichuan, China[4]Department of Neurology, The Second Affiliated Hospital of Kunming MedicalUniversity, Kunming, Yunnan, China[5]Second Department of General Surgery, First People’s Hospital of YunnanProvince, Kunming, Yunnan, China
Embolic stroke (ES) is characterized by high morbidity and mortality. Its mortality predictors remain unclear. This study aimed to use machine learning (ML) to identify the key predictors of mortality for ES patients in the intensive care unit (ICU). Data were extracted from two large ICU databases: MIMIC-IV for training and internal validation, and eICU-CRD for external validation. We developed predictive models of ES mortality based on 15 ML algorithms. We relied on the synthetic minority oversampling technique (SMOTE) to address class imbalance. Our main performance metric was area under the ROC (AUROC). We adopted recursive feature elimination (RFE) for feature selection. We assessed model performance using three disease-severity scoring systems as benchmarks. Of the 1,566 and 207 ES patients enrolled in the two databases, there were 173 (15.70%), 73 (15.57%), and 36 (17.39%) hospital mortality in the training, internal validation, and external validation cohort, respectively. The random forest (RF) model had the largest AUROC (0.806) in the internal validation phase and was chosen as the best model. The AUROC of the RF compact (RF-COM) model containing the top six features identified by RFE was 0.795. In the external validation phase, the AUROC of the RF model was 0.838, and the RF-COM model was 0.830, outperforming other models. Our findings suggest that the RF model was the best model and the top six predictors of ES hospital mortality were Glasgow Coma Scale, white blood cell, blood urea nitrogen, bicarbonate, age, and mechanical ventilation.Copyright 2022 The Author(s).
基金：
This work was supported by the National Natural Science Foundation of China, China
[82160263, funder: Liyan Li], the Research Innovation Team of Yunnan Province,
China [2019HC022, funder: Liyan Li], the Ten Thousand Person Plan for Famous .
Doctors of Yunnan Province ( YNWR-MY-2018-015)，the Yunnan Applied Basic
Research Projects [202101 AY070001-253, funder: Jinwei Yang; 2019FE001(-175) ]and the Foundation of Yunnan Provincial Education Department [2019J1257, funder:
Chunyan Li].
第一作者机构：[1]Institute of Neuroscience, Kunming Medical University, Kunming, Yunnan,China[2]Department of Neurology, Nanbu People's Hospital, Nanbu, Sichuan, China
共同第一作者：
通讯作者：
通讯机构：[1]Institute of Neuroscience, Kunming Medical University, Kunming, Yunnan,China[5]Second Department of General Surgery, First People’s Hospital of YunnanProvince, Kunming, Yunnan, China[*1]Institute of Neuroscience, Kunming Medical University, No. 1168, Chunrong West Road, Yuhua Street Office, Chenggong District, Kunming, Yunnan,650500, People’s Republic of China[*2]Second Department of 20 General Surgery, First People’s Hospital of Yunnan Province, No. 157, Jinbi Road, Xishan District, Kunming, Yunnan, 650034, People’s Republic of China,
推荐引用方式(GB/T 7714)：
Wei Liu,Wei Ma,Na Bai,et al.Identification of key predictors of hospital mortality in critically ill patients with embolic stroke using machine learning[J].BIOSCIENCE REPORTS.2022,42(9):doi:10.1042/BSR20220995.
APA：
Wei Liu,Wei Ma,Na Bai,Chunyan Li,Kuangpin Liu...&Liyan Li.(2022).Identification of key predictors of hospital mortality in critically ill patients with embolic stroke using machine learning.BIOSCIENCE REPORTS,42,(9)
MLA：
Wei Liu,et al."Identification of key predictors of hospital mortality in critically ill patients with embolic stroke using machine learning".BIOSCIENCE REPORTS 42..9(2022)
