| Popis: |
Many distinct forms of cancer have contributed to cancer's label as a heterogeneous illness. In cancer research, an emphasis on early detection and prognosis of a cancer type is essential since it may improve clinical care of patients. Many research organizations in the biomedical and bioinformatics fields have studied the use of ML approaches for risk stratification of cancer patients because of its significance. Therefore, the goal of using these methods to simulate the development and management of malignant situations has been pursued. The capacity of ML algorithms to identify crucial elements in complicated datasets further highlights their significance. Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs), and Decision Trees (DTs) are only few of the methods that have been extensively used in cancer research to construct prediction models, leading to efficient and precise decision making. Although it is clear that ML approaches may enhance our knowledge of cancer development, they still need sufficient validation before they can be taken into account in routine clinical practice. In this paper, we summarize current ML methods used to simulate cancer development. |
