Multi-Cancer Early Detection And Classification Using Machine Learning Based Approaches
Viswanadham Ravuri, M. Venkata Subbarao, T. Sudheer Kumar, T.S. Kavitha, Dutta Sandeep, Leelavathi Dangeti
Abstract
It's been established that there are numerous distinct types of cancer, hence oncology is considered to be a highly diverse field. In cancer research, an emphasis on early diagnosis and prognosis of a cancer type has emerged as a necessity because of the benefits it can bring to clinical patient care management. A significant number of research companies working in the domains of biomedicine and bioinformatics have investigated the application of machine learning strategies to the essential problem of classifying cancer patients into high and low risk categories. These techniques have thus been utilised to model the occurrence and treatment of cancer. The capacity of ML algorithms to identify crucial features in complicated datasets further demonstrates their significance. Numerous of these techniques, including Decision Trees, Support Vector Machines, and K-Nearest Neighbors, have been extensively used in cancer research to develop prediction models that help decision-makers make more informed and trustworthy choices. Although it is clear that ML approaches can enhance our knowledge of cancer development, they still require sufficient validation before they can be considered for use in routine clinical practice. As a result, an ML strategy was used to the modelling of cancer development. Different supervised ML methods, as well as a wide range of input characteristics and Data Samples, form the basis of the prediction models covered here.