Comparison of Four Data Mining Algorithms for Predicting Colorectal Cancer Risk

Background & Objective: Colorectal cancer (CRC) is one of the most prevalent malignancies in world. The early detection CRC not only a simple process but also key to treatment. Data mining algorithms could be potentially useful prognosis, diagnosis, and Therefore, main focus this study measure performance some data classifier predicting providing an warning high-risk groups. Materials Methods: This was performed on 468 subjects, including 194 patients 274 non-CRC cases. We used dataset from Imam Hospital, Sari, Iran. Chi-square feature selection method utilized analyze risk factors. Next, four popular were compared terms their CRC, and, finally, best algorithm identified. Results: outcome obtained by J-48 with F-measure=0.826, receiver operating characteristic (ROC)=0.881, precision=0.826, sensitivity =0.827. Bayesian net second-best performer (F-Measure=0.718, ROC=0.784, precision=0.719, sensitivity=0.722) followed random forest (F-Measure=0.705, ROC=0.758, sensitivity=0.712). multilayer perceptron technique had worst (F-Measure=0.702, ROC=0.76, precision=0.701, sensitivity=0.703). Conclusion: According results study, provide better insights than other proposed prediction models for clinical applications. © 2021, Zanjan University Medical Sciences Health Services. All rights reserved.