A Preoperative Risk-Prediction Model (SSPAL) for Prolonged Air Leak After Lobectomy for Lung Cancer: Development and Internal Validation
- 1Department of Thoracic Surgery, Dr. Suat Seren Chest Diseases and Surgery Training and Research Hospital, Izmir 35110, Turkey
Abstract
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.
Related
- Development and validation of machine learning models for preoperative prediction of perioperative outcomes in patients with thymic epithelial tumors
- Development and validation of a machine learning model for preoperative prediction of intraoperative hypothermia in gynecological laparoscopic surgery: a two-center cohort study
- Development and Patient-Level Internal Validation of an MRI-Based Radiomics Machine Learning Model for Preoperative Prediction of Cervical Lymph Node Metastasis in Oral Squamous Cell Carcinoma: A Pilot Study.
- Development and external validation of a preoperative prediction model for in-hospital major adverse cardiovascular events after hip fracture surgery in older adults: a retrospective two-center study.
- Preoperative prediction of microvascular invasion in hepatocellular carcinoma using routine clinical variables: development and temporal validation of an interpretable random forest model in a single-center retrospective cohort study.
BibTeX
@article{turk2026preoperative,
title = {{A Preoperative Risk-Prediction Model (SSPAL) for Prolonged Air Leak After Lobectomy for Lung Cancer: Development and Internal Validation}},
author = {Yunus Türk and Necati Çitak and Esra Yamansavcı Şirzai and Ahmet Üçvet},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15218367},
url = {https://www.mdpi.com/2077-0383/15/21/8367},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A Preoperative Risk-Prediction Model (SSPAL) for Prolonged Air Leak After Lobectomy for Lung Cancer: Development and Internal Validation
AU - Yunus Türk
AU - Necati Çitak
AU - Esra Yamansavcı Şirzai
AU - Ahmet Üçvet
PY - 2026
DA - 2026/10/27
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15218367
UR - https://www.mdpi.com/2077-0383/15/21/8367
AB - 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.
SN - 2077-0383
ER -