Abstract
In December 2017, our group published the results of a retrospective study evaluating the prognostic factors in completely resected node-negative lung adenocarcinomas 3 cm or smaller.1Hung J.J. Yeh Y.C. Wu Y.C. Chou T.Y. Hsu W.H. Prognostic factors in completely resected node-negative lung adenocarcinoma of 3 cm or smaller.J Thorac Oncol. 2017; 12: 1824-1833Abstract Full Text Full Text PDF PubMed Scopus (24) Google Scholar Subsequently, a letter to the editor by Safiri and Ashrafi-Asgarabad 2Safiri S. Ashrafi-Asgarabad A. Prognostic factors in completely resected node-negative lung adenocarcinoma of 3 cm or smaller: methodological issues.J Thorac Oncol. 2018; 13: e186-e187Google Scholar expressed their concern regarding some statistical and methodological issues. We have checked the proportional hazard assumption of our Cox proportional hazard regression model. The proportional hazard assumption was satisfied. We have also checked whether multicollinearity between the independent variables in the multivariable model existed. The results showed that our model was not affected by this phenomenon. To validate our prediction model, bootstrap analyses of 1000 samples were used to assess the stability of the predictors in the multivariable analysis. In the bootstrap procedure, 1000 samples were selected with replacements from the original data set. The bootstrap analysis showed that larger tumor size (p = 0.002) and the predominant pattern group (micropapillary/solid predominant versus lepidic/acinar/papillary predominant) (p = 0.037) were significant prognostic factors for probability of freedom from recurrence (FFR) in patients with N0 lung adenocarcinoma 3 cm or smaller in multivariable analysis. For patients with N0 lung adenocarcinoma 2 cm or smaller, bootstrap analysis showed that larger tumor size (p = 0.001) and greater smoking exposure (p = 0.004) were significant prognostic factors for lower probability of FFR in multivariable analysis. Predominant pattern group (micropapillary/solid predominant versus lepidic/acinar/papillary predominant) was not a significant prognostic factor of probability of FFR (p = 0.056). If histologic type was entered as present versus absent, bootstrap analysis showed that larger tumor size (p = 0.004) and presence of the solid pattern (p = 0.004) were significant prognostic factors for a lower probability of FFR in multivariable analysis. The results of the bootstrap analysis were similar to our previous data regarding Cox proportional hazard model. Prognostic Factors in Completely Resected Node-Negative Lung Adenocarcinoma of 3 cm or Smaller: Methodological IssuesJournal of Thoracic OncologyVol. 13Issue 9PreviewWe read the paper by Hung et al. enthusiastically and meticulously.1 They aimed to determine the prognostic value of the new classification in completely resected node-negative lung adenocarcinoma of 3 cm or smaller. They concluded that the new adenocarcinoma classification has significant impact in these patients. Also, the risk of recurrence was higher among patients with a micropapillary/solid predominant pattern. It is obvious that valuable research has been conducted, but some statistical and methodological issues seem to be important. Full-Text PDF Open Archive
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
