Using Machine Learning Algorithms to Predict High-Risk Factors for Postoperative Delirium in Elderly Patients

Abstract

Purpose Postoperative delirium (POD) is a common postoperative complication in elderly patients, and it greatly affects the short-term and long-term prognosis of patients. The purpose of this study was to develop a machine learning model to identify preoperative, intraoperative and postoperative high-risk factors and predict the occurrence of delirium after nonbrain surgery in elderly patients. Patients and Methods A total of 950 elderly patients were included in the study, including 132 patients with POD. We collected 30 characteristic variables, including patient demographic characteristics, basic medical history, preoperative examination characteristics, type of surgery, and intraoperative information. Three machine learning algorithms, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), and k-nearest neighbor algorithm (KNN), were applied to construct the model, and the k-fold cross-validation method, ROC curve, calibration curve, decision curve analysis (DCA) and external validation were used for model evaluation. Results XGBoost showed the best performance among the three prediction models. The ROC curve results showed that XGBoost had a high area under the curve (AUC) value of 0.982 in the training set; the AUC value in the validation set was 0.924, and the prediction model was highly accurate. The k-fold cross-validation method was used for internal validation, and the XGBoost model was stable The calibration curve showed high predictive power of the XGBoost model. The DCA curve showed a higher benefit rate for patients who received interventional treatment under the XGBoost model. The AUC value for the external validation set was 0.88, indicating that the predictive model was extrapolative. Conclusion The prediction model of POD derived from the machine learning algorithm in this study has high prediction accuracy and clinical utility, which is beneficial for clinicians to diagnose and treat patients in a timely manner.

Can admission Braden skin score predict delirium in older adults in the intensive care unit? Results from a multicenter study

“…The advent of artificial intelligence has introduced innovative machine learning algorithms that have enormous potential for predicting delirium. By simulating human learning processes to analyse data patterns, these algorithms have tremendous potential to uncover intricate relationships between variables and improve predictive accuracy (Liu et al., 2023). However, a recent systematic review and meta‐analysis found that while machine learning models perform well in predicting delirium, most of the studies associated with them have a high risk of bias (Xie et al., 2022).…”

“…The advent of artificial intelligence has introduced innovative machine learning algorithms that have enormous potential for predicting delirium. By simulating human learning processes to analyse data patterns, these algorithms have tremendous potential to uncover intricate relationships between variables and improve predictive accuracy (Liu et al, 2023).…”

Nomogram for predicting of postoperative delirium in elderly patients undergoing radical esophagectomy

“…In this study, age was strongly independently associated with the development of POD. An advanced age has been widely accepted as a major demography-related preoperative risk factor affecting the onset of POD in several studies [41][42][43][44]. As the increase of age, degeneration of compensatory physiological mechanisms and organ function, remarkably reduced body adaptability to drastic alterations during the surgical period leaded to a signi cantly increased risk of POD [29].…”

Evaluating the performance of machine learning methods for risk estimation of delirium in patients hospitalized from the emergency department

“…There is a need to identify an optimal screening strategy for delirium beyond cognitive assessment because, until we have it, delirium will likely remain an elusive diagnosis. In recent years, numerous studies have developed models in the hospital setting for estimating the risk of delirium in postoperative patients 13–22 and ICU patients, 23–28 but limited work has focused on the ED patient population 3,29,30 …”

“…[10][11][12] There is a need to identify an optimal screening strategy for delirium beyond cognitive assessment because, until we have it, delirium will likely remain an elusive diagnosis. In recent years, numerous studies have developed models in the hospital setting for estimating the risk of delirium in postoperative patients [13][14][15][16][17][18][19][20][21][22] and ICU patients, [23][24][25][26][27][28] but limited work has focused on the ED patient population. 3,29,30 Our objective was to leverage electronic health records to identify a clinically valuable risk estimation model for positive delirium screens in patients admitted from the ED to inpatient units.…”