Open AccessAutomated machine learning‐based model predicts postoperative delirium using readily extractable perioperative collected electronic data
Author(s) -
Hu XiaoYi,
Liu He,
Zhao Xue,
Sun Xun,
Zhou Jian,
Gao Xing,
Guan HuiLian,
Zhou Yang,
Zhao Qiu,
Han Yuan,
Cao JunLi
Publication year - 2022
Publication title -
cns neuroscience and therapeutics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.403
H-Index - 69
eISSN - 1755-5949
pISSN - 1755-5930
DOI - 10.1111/cns.13758
Subject(s) - logistic regression , medicine , confidence interval , perioperative , brier score , delirium , receiver operating characteristic , intensive care unit , random forest , emergency medicine , machine learning , surgery , intensive care medicine , computer science
Objective Postoperative delirium (POD) is a common postoperative complication that is relevant to poor outcomes. Therefore, it is critical to find effective methods to identify patients with high risk of POD rapidly. Creating a fully automated score based on an automated machine‐learning algorithm may be a method to predict the incidence of POD quickly. Materials and methods This is the secondary analysis of an observational study, including 531 surgical patients who underwent general anesthesia. The least absolute shrinkage and selection operator (LASSO) was used to screen essential features associated with POD. Finally, eight features (age, intraoperative blood loss, anesthesia duration, extubation time, intensive care unit [ICU] admission, mini‐mental state examination score [MMSE], Charlson comorbidity index [CCI], postoperative neutrophil‐to‐lymphocyte ratio [NLR]) were used to established models. Four models, logistic regression, random forest, extreme gradient boosted trees, and support vector machines, were built in a training set (70% of participants) and evaluated in the remaining testing sample (30% of participants). Multivariate logistic regression analysis was used to explore independent risk factors for POD further. Results Model 1 (logistic regression model) was found to outperform other classifier models in testing data (area under the curve [AUC] of 80.44%, 95% confidence interval [CI] 72.24%–88.64%) and achieve the lowest Brier Score as well. These variables including age (OR = 1.054, 95%CI: 1.017~1.093), extubation time (OR = 1.027, 95%CI: 1.012~1.044), ICU admission (OR = 2.238, 95%CI: 1.313~3.793), MMSE (OR = 0.929, 95%CI: 0.876~0.984), CCI (OR = 1.197, 95%CI: 1.038~1.384), and postoperative NLR (OR = 1.029, 95%CI: 1.002~1.057) were independent risk factors for POD in this study. Conclusions We have built and validated a high‐performing algorithm to demonstrate the extent to which patient risk changes of POD during the perioperative period, thus leading to a rational therapeutic choice.