A Comparative Analysis of Machine Learning Models for Colon Cancer Classification
Rashmi Ranjan Swain, Debasish Swapnesh Kumar Nayak, Tripti Swarnkar
Abstract
One of the trickiest machine learning challenges is the automatic classification of cancer cells. Colon Cancer can strike anyone at any age, but it often strikes older persons. In recent years, several investigations have focused on developing machine learning algorithms that can automatically classify genes of various types of a particular disease, especially colon cancer. The classification of cancer has improved due to improvements in computational methods like machine learning (ML), which required little human interaction and inefficient computers. Since the classification of gene expression data has been extensively studied in conjunction with the advancement of gene technology, a wide variety of techniques, primarily neural network-related, have been applied to the analysis of medical data, which is primarily concerned with the large dimension and very small in quantity. In this work, five different ML techniques were implemented for the classification of colon cancer in different age groups. The implemented ML techniques are Random Forest (RF), Decision Tree (DT), Support vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbour (KNN). It is observed that most of the implemented model has an average accuracy of more than 95%.