Predictive model for acute respiratory distress syndrome events in ICU patients in China using machine learning algorithms: a secondary analysis of a cohort study

• Published in: Journal of translational medicine Vol. 17; no. 1; p. 326
• Main Authors: Ding, Xian-Fei, Li, Jin-Bo, Liang, Huo-Yan, Wang, Zong-Yu, Jiao, Ting-Ting, Liu, Zhuang, Yi, Liang, Bian, Wei-Shuai, Wang, Shu-Peng, Zhu, Xi, Sun, Tong-Wen
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 01.10.2019; BioMed Central; BMC
• Subjects: Accuracy; Acute respiratory distress syndrome; Artificial intelligence; Bioindicators; Biological markers; Biomarkers; Bone marrow; Cohort analysis; Critical care; Health aspects; Hematocrit; Hospitals; Identification and classification; Intensive care; Intensive care units; Learning algorithms; Machine learning; Patients; Prediction models; Predictive model; Respiratory distress syndrome; Risk factors; Secondary analysis; Sodium; Transplants & implants; Tumor necrosis factor-TNF; China; Beijing China; United States > US; Japan; Acute respiratory distress syndrome; Machine learning; Predictive model
• ISSN: 1479-5876; 1479-5876
• DOI: 10.1186/s12967-019-2075-0

To develop a machine learning model for predicting acute respiratory distress syndrome (ARDS) events through commonly available parameters, including baseline characteristics and clinical and laboratory parameters. A secondary analysis of a multi-centre prospective observational cohort study from five hospitals in Beijing, China, was conducted from January 1, 2011, to August 31, 2014. A total of 296 patients at risk for developing ARDS admitted to medical intensive care units (ICUs) were included. We applied a random forest approach to identify the best set of predictors out of 42 variables measured on day 1 of admission. All patients were randomly divided into training (80%) and testing (20%) sets. Additionally, these patients were followed daily and assessed according to the Berlin definition. The model obtained an average area under the receiver operating characteristic (ROC) curve (AUC) of 0.82 and yielded a predictive accuracy of 83%. For the first time, four new biomarkers were included in the model: decreased minimum haematocrit, glucose, and sodium and increased minimum white blood cell (WBC) count. This newly established machine learning-based model shows good predictive ability in Chinese patients with ARDS. External validation studies are necessary to confirm the generalisability of our approach across populations and treatment practices.