Dynamic and interpretable deep learning model for predicting respiratory failure following cardiac surgery

作者：Man Xu, Hao Liu, Anran Dai, Qilian Tan, Xinlong Zhang, Rui Ding, Chen Chen, Jianjun Zou, Yongjun Li, Yanna Si · 发表于：BMC Anesthesiology · 年份：2025 · DOI：10.1186/s12871-025-03239-z · 被引用次数：4 · 研究领域：Cardiac, Anesthesia and Surgical Outcomes、Hemodynamic Monitoring and Therapy、Artificial Intelligence in Healthcare and Education

BACKGROUND: Postoperative respiratory failure following cardiac surgery (CS-PRF) remains a critical complication with substantial morbidity and mortality. Current risk prediction models are limited by static assessments and suboptimal accuracy. This study aimed to develop and validate a dynamic, machine learning–based model to enhance perioperative risk stratification for CS-PRF. METHODS: We retrospectively analyzed 1,016 adult patients who underwent cardiac surgery. Feature selection was conducted via the Least Absolute Shrinkage and Selection Operator (LASSO) and Boruta algorithms. Five machine learning models, including logistic regression, multilayer perceptron, extreme gradient boosting, categorical boosting, and deep neural network (DNN), were trained using preoperative and intraoperative variables. Model performance was evaluated by the area under the receiver operating characteristic curve (AUROC), area under the precision–recall curve (AUPRC), and calibration metrics. Model interpretability was evaluated via SHapley additive exPlanation (SHAP), and restricted cubic spline (RCS) analyses were used to explore nonlinear associations. RESULTS: The incidence of CS-PRF was 16.3%. In the validation cohort, the DNN model achieved superior performance, with an AUROC of 0.782 (95% CI 0.703–0.852) and an AUPRC of 0.496 based on preoperative variables, which improved to an AUROC of 0.855 (95% CI 0.796–0.906) and an AUPRC of 0.549 with the addition of intraoperative data. Calibra...