干旱区生态环境知识资源中心(Arid): Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database

Arid

DOI	10.3389/fmed.2021.662340
	Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database
	Zhu, Yibing; Zhang, Jin; Wang, Guowei; Yao, Renqi; Ren, Chao; Chen, Ge; Jin, Xin; Guo, Junyang; Liu, Shi; Zheng, Hua; Chen, Yan; Guo, Qianqian; Li, Lin; Du, Bin; Xi, Xiuming; Li, Wei; Huang, Huibin; Li, Yang; Yu, Qian
通讯作者	Li, W (corresponding author), Chinese Acad Med Sci & Peking Union Med Coll, Fuwai Hosp, Natl Ctr Cardiovasc Dis, Med Res & Biometr Ctr, Beijing, Peoples R China. ; Huang, HB (corresponding author), Tsinghua Univ, Sch Clin Med, Beijing Tsinghua Changgung Hosp, Dept Crit Care Med, Beijing, Peoples R China. ; Li, Y ; Yu, Q (corresponding author), Peking Univ, Acad Adv Interdisciplinary Studies, Beijing, Peoples R China.
来源期刊	FRONTIERS IN MEDICINE
EISSN	2296-858X
出版年	2021
卷号	8
英文摘要	Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission. Methods: A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of k-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported. Results: A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate. Conclusion: The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models.
英文关键词	prediction model machine learning mechanical ventilation intensive care unit death
类型	Article
语种	英语
开放获取类型	Green Published, gold
收录类别	SCI-E
WOS记录号	WOS:000673699100001
WOS关键词	SURVIVAL
WOS类目	Medicine, General & Internal
WOS研究方向	General & Internal Medicine
来源机构	北京大学 ; 清华大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/363319
作者单位	[Zhu, Yibing; Chen, Ge; Li, Wei] Chinese Acad Med Sci & Peking Union Med Coll, Fuwai Hosp, Natl Ctr Cardiovasc Dis, Med Res & Biometr Ctr, Beijing, Peoples R China; [Zhu, Yibing] China Acad Chinese Med Sci, Guanganmen Hosp, Dept Emergency, Beijing, Peoples R China; [Zhang, Jin] Beijing Inst Technol, Sch Econ & Management, Beijing, Peoples R China; [Wang, Guowei; Li, Lin] Wuhan Univ Technol, Sch Comp Sci & Technol, Wuhan, Peoples R China; [Yao, Renqi] Naval Med Univ, Affiliated Hosp 1, Dept Burn Surg, Shanghai, Peoples R China; [Yao, Renqi; Ren, Chao] Chinese Peoples Liberat Army PLA Gen Hosp, Translat Med Res Ctr, Med Ctr 4, Beijing, Peoples R China; [Yao, Renqi; Ren, Chao] Chinese Peoples Liberat Army PLA Gen Hosp, Med Innovat Res Div, Beijing, Peoples R China; [Jin, Xin] Yidu Cloud Technol Inc, Beijing, Peoples R China; [Guo, Junyang] Beijing Big Eye Xing Tu Culture Media Co Ltd, Beijing, Peoples R China; [Liu, Shi] Hebei North Univ, Sch Informat Sci & Engn, Shijiazhuang, Hebei, Peoples R China; [Zheng,...
推荐引用方式 GB/T 7714	Zhu, Yibing,Zhang, Jin,Wang, Guowei,et al. Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database[J]. 北京大学, 清华大学,2021,8.
APA	Zhu, Yibing.,Zhang, Jin.,Wang, Guowei.,Yao, Renqi.,Ren, Chao.,...&Yu, Qian.(2021).Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database.FRONTIERS IN MEDICINE,8.
MLA	Zhu, Yibing,et al."Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database".FRONTIERS IN MEDICINE 8(2021).