Combining statistical techniques to predict postsurgical risk of 1-year mortality for patients with colon cancer
Received 18 July 2017
Accepted for publication 14 January 2018
Published 6 March 2018 Volume 2018:10 Pages 235—251
Checked for plagiarism Yes
Review by Single-blind
Peer reviewer comments 3
Editor who approved publication: Professor Henrik Toft Sørensen
Inmaculada Arostegui,1–3 Nerea Gonzalez,2,4 Nerea Fernández-de-Larrea,5,6 Santiago Lázaro-Aramburu,7 Marisa Baré,2,8 Maximino Redondo,2,9 Cristina Sarasqueta,2,10 Susana Garcia-Gutierrez,2,4 José M Quintana2,4
On behalf of the REDISSEC CARESS-CCR Group2
1Department of Applied Mathematics, Statistics and Operations Research, University of the Basque Country UPV/EHU, Leioa, Bizkaia, Spain; 2Health Services Research on Chronic Patients Network (REDISSEC), Galdakao, Bizkaia, Spain; 3Basque Center for Applied Mathematics – BCAM, Bilbao, Bizkaia, Spain; 4Research Unit, Galdakao-Usansolo Hospital, Galdakao, Bizkaia, Spain; 5Environmental and Cancer Epidemiology Unit, National Center of Epidemiology, Instituto de Salud Carlos III, Madrid, Spain; 6Consortium for Biomedical Research in Epidemiology and Public Health (CIBERESP), Madrid, Spain; 7General Surgery Service, Galdakao-Usansolo Hospital, Galdakao, Bizkaia, Spain; 8Clinical Epidemiology and Cancer Screening Unit, Parc Taulí Sabadell-Hospital Universitari, UAB, Sabadell, Barcelona, Spain; 9Research Unit, Costa del Sol Hospital, Marbella, Malaga, Spain; 10Research Unit, Donostia Hospital, Donostia-San Sebastián, Gipuzkoa, Spain
Introduction: Colorectal cancer is one of the most frequently diagnosed malignancies and a common cause of cancer-related mortality. The aim of this study was to develop and validate a clinical predictive model for 1-year mortality among patients with colon cancer who survive for at least 30 days after surgery.
Methods: Patients diagnosed with colon cancer who had surgery for the first time and who survived 30 days after the surgery were selected prospectively. The outcome was mortality within 1 year. Random forest, genetic algorithms and classification and regression trees were combined in order to identify the variables and partition points that optimally classify patients by risk of mortality. The resulting decision tree was categorized into four risk categories. Split-sample and bootstrap validation were performed. ClinicalTrials.gov Identifier: NCT02488161.
Results: A total of 1945 patients were enrolled in the study. The variables identified as the main predictors of 1-year mortality were presence of residual tumor, American Society of Anesthesiologists Physical Status Classification System risk score, pathologic tumor staging, Charlson Comorbidity Index, intraoperative complications, adjuvant chemotherapy and recurrence of tumor. The model was internally validated; area under the receiver operating characteristic curve (AUC) was 0.896 in the derivation sample and 0.835 in the validation sample. Risk categorization leads to AUC values of 0.875 and 0.832 in the derivation and validation samples, respectively. Optimal cut-off point of estimated risk had a sensitivity of 0.889 and a specificity of 0.758.
Conclusion: The decision tree was a simple, interpretable, valid and accurate prediction rule of 1-year mortality among colon cancer patients who survived for at least 30 days after surgery.
Keywords: clinical prediction rules, colonic neoplasms, colorectal surgery, tree-based methods, prediction model, 1-year-mortality
This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at https://www.dovepress.com/terms.php and incorporate the Creative Commons Attribution - Non Commercial (unported, v3.0) License. By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms.Download Article [PDF] View Full Text [HTML][Machine readable]