Making Medical Predictions about Diseases with Gene Expression Data

Abstract

Exploration and studies of human genes play a critical role for improving the healthcare and society development. By using previous data as input, machine learning enables software applications to forecast values more precisely and is a good tool to complete the task of predicting diseases with gene expression data. This paper provides a comprehensive review of studies regarding the combination of machine learning and gene expression analysis related to diseases. The main three applications are (a) the disease prediction: cancer detection and other diseases detection, (b) the control of cancers: the metastasis of cancer and the complete remission of cancers, and (c) the drug response prediction. The reviewed molding method in this paper mainly focus on Regressions, K nearest neighbor (KNN) and Support vector machine (SVM). The combination of gene data and machine learning is meaningful for developing new techniques for detecting diseases and testing new drugs, which improves accuracy and effectiveness.