Predicting Disease Susceptibility with Machine Learning in Genomics

Abstract

This research paper aims at reviewing the field of genomics and its use of machine learning to find out the chances of one getting a disease. Genetic risk prediction currently incorporates various strategies, and new ideas to conducting analysis based on genome massive dimensionality are introduced here. Paper research focuses on several machine learning algorithms; the ones considered are support vector machines, random forests, and deep neural networks that determine disease risk. We also explore the multi-integration of omics data and how explainable AI can be used to derive biological understanding. These methodologies are thus applied in case studies involving cardiovascular diseases, cancers and inherited genetic disorder conditions. After reviewing the current research, the paper also presents clinical implications, as well as directions for future research for such a rapidly growing topic. Based on these observations, widening the use of integrated machine learning methods can help advance the accuracy of disease risk prediction, and can be applied in the development of a preventive and individualized medicine.