作者: Enayatollah Bakhshi , Mahmood Reza Gohari , Akbar Biglarian , Mohammad Amin Pourhoseingholi
DOI:
关键词:
摘要: Background & Objectives: The aim of this study was to determine the prognostic factors Iranian colorectal cancer (CRC) patients and their importance using an artificial neural network (ANN) model. Methods: This a historical cohort data gathered from 1,219 registered CRC between January 2002 October 2007 at Research Center for Gastroenterology Liver Disease Shahid Beheshti University Medical Sciences, Tehran, Iran. For determining risk survival prediction patients, (NN) Cox regression models were used, utilizing R 2.12.0 software. Results: One, three five-year estimated probability in colon 0.92, 0.71, 0.48 rectum 0.86, 0.42, respectively. By ANN model, pathologic distant metastasis, regional lymph nodes, tumor grade, high behavior, primary tumor, familial history size variables determined as ordered important cancer. Tumor stage, age diagnosis, size, metastasis first treatment model lead more accurate predictions compared (true 89.0% vs. 78.6% 82.7% 70.7% patients). Conclusion: showed that is powerful tool influential Therefore, recommended predicting these patients.