Development of machine learning models for predicting delirium in elderly patients after thoracic surgeries
- 1Department of Anesthesiology, Affiliated Hospital of Nantong University, Medical School of Nantong University, Nantong, 226001 China
- 2Department of Anesthesiology, Beijing Tongren Hospital, Beijing, 100730 China
- 3Department of Information, Affiliated Hospital of Nantong University, Nantong, 226001 China
Abstract
Background: Postoperative delirium (POD) is a frequent neurological complication following anesthesia and surgery, which is associated with increased comorbidities and mortality. The current study developed and internally validated a machine learning model for predicting POD in elderly patients undergoing thoracic surgeries based on machine learning (ML) algorithms.
Methods: Elderly patients who underwent elective segmentectomy, lobectomy, or esophagectomy with general anesthesia from January 2015 to December 2022 were electronically retrieved. Clinical features, preoperative laboratory values, and intraoperative parameters were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to screen critical features associated with POD. Nine ML algorithms were used to construct prediction models in the training dataset (80% of participants), and model performances were evaluated in the validation dataset (20% of participants). Prediction performances of the nine ML models were also compared using the area under the receiver operating characteristic curve (AUC). Model calibration was assessed using the Brier scores. Finally, the best model was determined and was interpreted using the Shapley Additive exPlanations (SHAP).
Results: Three thousand nine hundred sixty-seven elderly patients were enrolled, and 277 of them developed POD. Preoperative white blood cell (WBC), preoperative fasting plasma glucose (FPG), intraoperative hypotension, arrhythmia, combined nerve block anesthesia, hypertension, intraoperative vasoactive drugs, current smoker, blood transfusion, glucocorticoids usage, ASA classification, and video-assisted thoracoscopy were identified as prediction variables. The XGBoost model exhibited the best predictive performance (AUC: 0.936, 95% confidence interval (CI): 0.932–0.941). The XGBoost model also presented the lowest Brier scores (0.110) in terms of model calibration. The three predictive variables with the most influence on the model were preoperative WBC, preoperative FPG and intra-operative hypotension.
Conclusions: The current study developed a ML model for POD prediction for elderly patients undergoing thoracic surgeries. If validated, the model could potentially serve as a complementary tool to aid POD risk stratification.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12871-026-04152-9.
Related
- Predicting delirium in critically Ill patients with cancer using interpretable machine learning
- Development and external validation of machine learning models for early prediction of delirium risk in patients with severe pneumonia
- Development and internal validation of a clinical risk score for early delirium detection in older emergency department patients
- Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
- Development and Validation of a Perioperative Risk Update Model for Postoperative Delirium in Patients Aged ≥ 80 Years Undergoing Hip Fracture Surgery: A Retrospective Cohort Study
BibTeX
@article{li2026development,
title = {{Development of machine learning models for predicting delirium in elderly patients after thoracic surgeries}},
author = {Yanhao Li and Min Liu and Yu’e Sun and Tingting Zhang and Yongtao Gao and Dongchen Qian and Yongji Xu and Yunyue Wu and Jia Liu and Yibin Qin and Binbin Wang and Siyuan Liu},
journal = {BMC Anesthesiology},
year = {2026},
month = aug,
doi = {10.1186/s12871-026-04152-9},
url = {https://doi.org/10.1186/s12871-026-04152-9},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Development of machine learning models for predicting delirium in elderly patients after thoracic surgeries
AU - Yanhao Li
AU - Min Liu
AU - Yu’e Sun
AU - Tingting Zhang
AU - Yongtao Gao
AU - Dongchen Qian
AU - Yongji Xu
AU - Yunyue Wu
AU - Jia Liu
AU - Yibin Qin
AU - Binbin Wang
AU - Siyuan Liu
PY - 2026
DA - 2026/08/10
JO - BMC Anesthesiology
DO - 10.1186/s12871-026-04152-9
UR - https://doi.org/10.1186/s12871-026-04152-9
AB - Background: Postoperative delirium (POD) is a frequent neurological complication following anesthesia and surgery, which is associated with increased comorbidities and mortality. The current study developed and internally validated a machine learning model for predicting POD in elderly patients undergoing thoracic surgeries based on machine learning (ML) algorithms. Methods: Elderly patients who underwent elective segmentectomy, lobectomy, or esophagectomy with general anesthesia from January 2015 to December 2022 were electronically retrieved. Clinical features, preoperative laboratory values, and intraoperative parameters were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to screen critical features associated with POD. Nine ML algorithms were used to construct prediction models in the training dataset (80% of participants), and model performances were evaluated in the validation dataset (20% of participants). Prediction performances of the nine ML models were also compared using the area under the receiver operating characteristic curve (AUC). Model calibration was assessed using the Brier scores. Finally, the best model was determined and was interpreted using the Shapley Additive exPlanations (SHAP). Results: Three thousand nine hundred sixty-seven elderly patients were enrolled, and 277 of them developed POD. Preoperative white blood cell (WBC), preoperative fasting plasma glucose (FPG), intraoperative hypotension, arrhythmia, combined nerve block anesthesia, hypertension, intraoperative vasoactive drugs, current smoker, blood transfusion, glucocorticoids usage, ASA classification, and video-assisted thoracoscopy were identified as prediction variables. The XGBoost model exhibited the best predictive performance (AUC: 0.936, 95% confidence interval (CI): 0.932–0.941). The XGBoost model also presented the lowest Brier scores (0.110) in terms of model calibration. The three predictive variables with the most influence on the model were preoperative WBC, preoperative FPG and intra-operative hypotension. Conclusions: The current study developed a ML model for POD prediction for elderly patients undergoing thoracic surgeries. If validated, the model could potentially serve as a complementary tool to aid POD risk stratification. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12871-026-04152-9.
SN - 1471-2253
ER -