A Comparative Analysis of Machine Learning Models for Colon Cancer Classification

The field of machine learning (ML) has made significant contributions to the medical domain, notably in the automatic classification of cancer types such as colon cancer. This type of cancer, while generally more common among the elderly, can affect people at any age. The incorporation of ML techniques has minimized the reliance on manual examination and enhanced the capacity to process large datasets in medical research. This paper examines the application of five different ML algorithms—Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), Naïve Bayes (NB), and K-Nearest Neighbor (KNN)—in classifying colon cancer across various age demographics. Utilizing advanced gene technology and analysis of gene expression data, this study addresses the challenges posed by the high dimensionality and limited size of such datasets. The findings reveal that most of the ML models employed here have surpassed expected accuracy levels, highlighting their effectiveness in the precise classification and diagnosis of colon cancer. This not only aids in recognizing age-related patterns in the occurrence and development of the disease but also contributes to the advancement of early detection and treatment modalities. Consequently, these developments hold promise for improving patient care and the overall efficiency of healthcare services in dealing with colon cancer. Keywords: Machine Learning (ML), Colon Cancer, Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), K-Nearest Neighbor (KNN).

Keywords: Colon Cancer, Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Naïve Bayes (NB), K-Nearest Neighbor (KNN), Gene Expression Data, High Dimensionality, Early Detection, Healthcare Efficiency.