Integrating intraoperative data with preoperative baseline characteristics in a multi-output LSTM model increased the overall AUC for predicting postoperative delirium dimensions from 0.76 to 0.81.
Observational (n=536)
No
Does a multi-output LSTM model integrating baseline and intraoperative data accurately predict multiple dimensions of postoperative delirium in older spine surgery patients?
Integrating acute perioperative data with baseline assessments in a multi-output LSTM model significantly improves the prediction of postoperative delirium occurrence, subtype, duration, severity, and onset timing in older spine surgery patients.
Absolute Event Rate: 0.81% vs 0.76%
Postoperative delirium (POD) adversely affects clinical outcomes among older adults undergoing spine surgery. However, existing predictive models often neglect multidimensional nature of delirium, including its clinical subtype, duration, severity, and timing. This study developed a multi-output Long Short-Term Memory (LSTM) neural network that integrates preoperative baseline characteristics and intraoperative acute stressors to predict multiple clinical dimensions of POD in elderly patients undergoing spinal surgery. This prospective observational study included 536 patients aged 70 or older who underwent elective spine surgery between November 2019 and May 2023. Comprehensive assessments were conducted during both the preoperative and intraoperative phases. The multi-output LSTM model incorporated preoperative baseline variables (demographic, frailty scores, cognitive function, medication count, and laboratory parameters) and intraoperative data (surgical invasiveness, duration of surgery and anesthesia, intraoperative fluid management, immediate postoperative medication use). Outcomes comprised delirium occurrence, subtype, duration, severity, and onset timing. Model performance was evaluated via accuracy, precision, recall, F1-score, and ROC curve analyses. SHapley Additive exPlanations (SHAP) analysis enhanced clinical interpretability. Using solely preoperative baseline data, the model demonstrated strong predictive performance with an overall AUC of 0.76, particularly for delirium occurrence (AUC = 0.68), the duration (AUC = 0.80), and severity (AUC = 0.79). Incorporating intraoperative data substantially enhanced model performance, increasing the overall AUC to 0.81, notably improving predictions for delirium subtype (AUC up to 0.84), duration (AUC = 0.81), and onset timing (AUC up to 0.87). SHAP analysis consistently identified frailty, polypharmacy, cognitive impairment, nutritional deficiencies, and acute perioperative factors—such as surgical invasiveness, pain management—as pivotal predictors across delirium dimensions. The proposed multi-output LSTM model predicted multiple clinical dimensions of postoperative delirium, highlighting baseline health status as a primary determinant. Strategic integration of comprehensive baseline assessments with acute perioperative data substantially enhances predictive accuracy, informing personalized delirium prevention and management strategies for improved perioperative outcomes in older spine surgery patients.
You et al. (2026) conducted an observational in Postoperative delirium (n=536). Multi-output LSTM model integrating preoperative and intraoperative data vs. LSTM model using solely preoperative baseline data was evaluated on Overall Area Under the Curve (AUC) for predicting multiple dimensions of postoperative delirium. Integrating intraoperative data with preoperative baseline characteristics in a multi-output LSTM model increased the overall AUC for predicting postoperative delirium dimensions from 0.76 to 0.81.