A Systematic Review of Machine Learning Techniques for The Diagnosis of Colorectal Cancer

Abstract

In recent years, have attended surpassing developments in the area of machine learning in various fields, particularly in the medical sector. The use of machine learning technologies has become a promising tool for supporting diagnosis, prediction, and clinical decision-making, contributing to improving the quality of healthcare and reducing human error. One of the important applications which have emerged is the use of machine learning technologies in cancer diagnosis, given the critical importance of this field in increasing survival rates and improving treatment results. Colorectal cancer is one of the most common and risky types of cancer worldwide, ranking top in terms of incidence and mortality rates. Early detection of colon cancer is a crucial factor in improving survival rates. This study focuses attention on the need for intelligent tools capable of supporting clinical decisions based on exact and in-depth analyses of medical data. Machine learning techniques have demonstrated a high ability to analyze the vast amount of clinical data, radiological images, and genetic patterns associated with colon cancer, opening up new possibilities for achieving more accurate early diagnosis compared to traditional methods. This paper presents a systematic survey of the available literature that uses machine learning techniques in colon cancer diagnosis, which will help identify innovations applied in this research area and explore future trends. This paper aims to conduct a literature survey of machine learning techniques in colon cancer diagnosis using the SLR methodology, analyze and compare the literature, and identify the appropriate technique to address issues in colon cancer diagnosis.