A Preoperative Risk-Prediction Model (SSPAL) for Prolonged Air Leak After Lobectomy for Lung Cancer: Development and Internal Validation

Background: Prolonged air leak (PAL) remains one of the most common complications following lobectomy for non-small-cell lung cancer (NSCLC), leading to prolonged hospitalization, increased healthcare costs, and delayed recovery. We aimed to develop and internally validate a practical model for predicting PAL after lobectomy. Methods: This retrospective single-center cohort study included 905 consecutive patients who underwent lobectomy for NSCLC between 2017 and 2024. Patients were randomly allocated to derivation (n = 680) and internal validation (n = 225) cohorts (3:1). Candidate clinical, operative, and pathological variables were evaluated to identify predictors of PAL, and multivariable logistic regression was used to develop the Suat Seren Prolonged Air Leak (SSPAL) model. Model performance was assessed by discrimination (AUC) and calibration. Results: The overall incidence of PAL was 20.8%. Multivariable logistic regression identified lower body mass index (OR, 0.915; 95% CI, 0.871–0.961; p < 0.001), current smoking (OR, 4.096; 95% CI, 1.359–12.350; p = 0.01), and left-sided lobectomy (OR, 0.637; 95% CI, 0.424–0.956; p = 0.03) as independent predictors of PAL. Sex (p = 0.07) and upper lobectomy (p = 0.08) were retained in the final model. The SSPAL model demonstrated acceptable discrimination in the derivation cohort (AUC, 0.723; 95% CI, 0.675–0.771) and the internal validation cohort (AUC, 0.728; 95% CI, 0.649–0.807). Conclusions: The SSPAL model is a simple candidate risk-prediction model for estimating PAL risk after lobectomy for NSCLC. Prospective multicenter external validation is required before its clinical utility and potential role in decision-making can be established.