The Society of Thoracic Surgeons 2024 Risk Models for Lung Cancer Resection: Continued Refinement and Improved Outcomes

BACKGROUND The Society of Thoracic Surgeons (STS) General Thoracic Surgery Database (GTSD) has been used to develop risk models for patients undergoing pulmonary resection for cancer. Leveraging a contemporary and more inclusive cohort, this study sought to refine these models. METHODS The study population consisted of adult patients in the STS GTSD who underwent pulmonary resection for cancer between 2015 and 2022. Unlike in previous models, nonelective operations were included. Separate risk models were derived for operative mortality, major morbidity, and composite morbidity or mortality. Logistic regression with backward selection was used with predictors retained in models if P < .10. All derived models were validated using 9-fold cross- validation. Model discrimination and calibration were assessed for the overall cohort and for surgical procedure, demographic, and risk factor subgroups. RESULTS Data from 140,927 patients at 337 participating centers were included in the study. Overall operative mortality rate was 1.1%, major morbidity was 7.3%, and composite morbidity or mortality was 7.6%. Novel predictors of short-term outcomes included interstitial lung disease, diffusing capacity of lung for carbon monoxide, and payer status. Overall discrimination was superior to previous STS pulmonary resection models for operative mortality (C-statistic = 0.80) and for composite morbidity or mortality (C-statistic = 0.70). Model discrimination was comparable and model calibration was excellent across all procedure- and demographic-specific subcohorts. CONCLUSIONS Among STS GTSD participants, major morbidity and operative mortality rates remained low after pulmonary resection. The newly derived pulmonary resection risk models demonstrate superior performance compared with previous models, with broader real-life applicability and clinical face validity.