Related Experiment Video
Updated: Sep 20, 2025

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Reintubation After Lung Cancer Resection: Development and External Validation of a Predictive Score
Felix C Linhardt1, Peter Santer2, Xinling Xu2
1Department of Anaesthesia, Critical Care and Pain Medicine, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts; Department of Anaesthesiology, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, New York.
Background:
Reintubation after lung cancer resection is an important quality metric because of increased disability, mortality and cost. However, no validated predictive instrument is in use to reduce reintubation after lung resection. This study aimed to create and validate the PRediction Of REintubation After Lung cancer resection (PROREAL) score.
Methods:
The study analyzed lung resection cases from 2 university hospitals. The primary end point was reintubation within 7 days after surgery. Predictors were selected through backward stepwise logistic regression and bootstrap resampling. The investigators used reclassification and receiver-operating characteristic (ROC) curve analyses to assess score performance and compare it with an established score for all surgical patients (Score for Prediction of Postoperative Respiratory Complications [SPORC]).
Results:
The study included 2672 patients who underwent resection for lung cancer (1754, development cohort; 918, validation cohort) between 2008 and 2020, of whom 71 (2.7%) were reintubated within 7 days after surgery. Identified score variables were surgical extent and approach, American Society of Anesthesiologists physical status, heart failure, renal disease, and diffusing capacity of the lung for carbon monoxide. The score achieved excellent discrimination in the development cohort (ROC AUC, 0.90; 95% CI, 0.87-0.94) and good discrimination in the validation cohort (ROC AUC, 0.74, 95% CI; 0.66-0.82), thus outperforming the SPORC in both cohorts (P < .001 and P = .018, respectively; validation cohort net reclassification improvement, 0.39; 95% CI, 0.18-0.60; P = .001). The score cutoff of ≥5 yielded a sensitivity of 88% (95% CI, 72-95) and a specificity of 81% (95% CI,79-83) in the development cohort.
Conclusions:
A simple score (PROREAL) specific to lung cancer predicts postoperative reintubation more accurately than the nonspecific SPORC score. Operative candidates at risk may be identified for preventive intervention or alternative oncologic therapy.
More Related Videos
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
06:46Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024