A Comparative Analysis of Machine Learning Models for Colon Cancer Classification

In recent years, the automatic classification of cancer cells, particularly in the context of colon cancer, has emerged as a formidable challenge in the field of machine learning (ML). Colon cancer is a disease that can affect individuals of all ages but is more prevalent among older populations. Advances in computational methods, particularly ML, have revolutionized the way we approach the classification of various types of diseases, including colon cancer. These ML algorithms have greatly reduced the need for extensive human intervention and have made it possible to analyze vast amounts of medical data efficiently. This study explores the classification of colon cancer across different age groups by employing five distinct ML techniques: Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), Naïve Bayes (NB), and K-Nearest Neighbor (KNN). The research leverages the significant strides made in gene technology and gene expression data analysis, despite the inherent challenges of dealing with high-dimensional and limited quantity medical data. Remarkably, the results of this investigation demonstrate that the majority of the implemented ML models achieve an average accuracy rate exceeding expectations. These findings underscore the potential of ML as a powerful tool in the ongoing effort to enhance the classification and diagnosis of colon cancer, especially when considering age-specific variations. This research paves the way for more accurate and efficient early detection and treatment strategies, ultimately improving patient outcomes and healthcare practices.

 Keywords: Machine Learning (ML), Support vector Machine (SVM), Colon Cancer, Random Forest (RF), Decision Tree (DT), K-Nearest Neighbor (KNN).