A Novel Classifier for Detecting Oropharyngeal Cancer Using Machine Learning Techniques

Throat cancer / Oropharyngeal Cancer is a serious healthcare concern that affects people all over the world and is frequently identified at an advanced stage, resulting in lower treatment efficacy and a worse prognosis. This abstract describes a revolutionary method for detecting throat cancer early combining cutting-edge technology and medical data analysis. Predicting throat cancer with machine learning algorithms is a difficult but potential use of artificial intelligence in healthcare. Early identification and precise prognosis can boost the odds of effective therapy and patient outcomes dramatically. The main objective of this study is to create a reliable and accurate approach for the early identification of throat cancer, which will enhance patient outcomes and minimize the disease’s impact. In this paper, we fill the knowledge gap and present a Novel architecture or Novel Classifier called as ETCP (Ensembled Throat Cancer Prediction Classifier) using machine learning for the continuous evaluation in predicting Throat cancer. To evaluate or predict Throat Cancer, this architecture is composed of three layers that collaborate to gather, process, and analyze data from several sources. And the results obtained from the proposed classifier is then compared with 2 base classifiers like Naive-Bayes and Decision Tree in which the proposed classifier gave the best accuracy in predicting throat cancer when compared with the other 2 classifiers i.e., $\tilde{9} 5 \%$.