Temporal Validation and Extension of a Risk Prediction Model for Postoperative Pulmonary Complications in Head and Neck Surgery Patients

Background: : Postoperative pulmonary complications (PPCs) are common following head and neck surgeries (HNS) leading to longer hospital stays and significant morbidity and mortality. Current PPC risk prediction models developed for general surgery patients underperform for HNS. This study validates an existing model and extends it for HNS patients. Methods: : Using the NSQIP-ACS database (2018-19), we validated the Gupta model, developed on the same database (2007-08). Later, we recalibrated and updated the model with additional predictors relevant for HNS, followed by internal-external validation. The model performance was evaluated by scaled Brier score and Nagelkerke’s R 2 . The discrimination ability was measured by C-statistic (AUC) and calibration was assessed by calibration slope. Results: : After extension and validation, the updated model achieved improved performance, with a Brier score of 0.0234 and R 2 of 0.1435. C-statistic rose to 0.822 (95% CI: 0.785–0.858), and the calibration slope increased to 0.979. Conclusion: : The updated model showed better performance, discrimination, and calibration in predicting PPC in HNS patients compared to the original model.