Performance-Based Analysis of K-Medoids and K-Means Algorithms for the Diagnosis and Prediction of Oral Cancer

In many research communities, clustering plays a major role in real-time applications such as health care, financial analysis, crime rate prediction, and customer trend analysis. Clustering offers a variety of potential techniques for determining a diagnosis and making prognosis regarding oral cancer. In this particular investigation, we used two distinct clustering strategies known as K-medoids and K-means to examine a dataset on oral cancer and to predict the likelihood of oral cancer sickness. The amount of time needed to complete each algorithm’s computation is tallied, and the algorithms’ overall effectiveness is evaluated. In order to do the analysis of our research, we employed R programming. Using significant amounts of data pertaining to oral cancer, an analysis of two different clustering methods is carried out in order to determine whether the method is superior. We have at last reached the point where the K-Medoids and K-Means clustering algorithms are accurate. According to the results of the experiments, the K-Means algorithm appears to produce the best results when contrasted with the K-Medoids method