Performance evaluation of various machine learning and deep learning models for gene expression

Abstract

Abstract Cancer is among those deadliest diseases that affects a mass. So, it requires the timely detection and treatment. There are number of ways through which cancer can be detected. Some of those ways are some “blood tests, CT (Computerized Tomography) scan, MRI (Magnetic Resonance Imaging), X-Ray, Ultrasound, gene expression, etc.”. Genes help doctors to find whether a person is suffering or going to suffer from any disease or not. In this paper, we have gone through various ML and DL from the literature. The models are trained and tested on 5 different types of datasets. These are “Lung Adenocarcinoma (LUAD), Lung Squamous Cell Carcinoma (LUSC), Breast Invasive Carcinoma (BRCA), Kidney Renal Clear Cell Carcinoma (KIRC), and Uterine Corpus Endometrial Carcinoma (UCEC)”. The models are evaluated on the different performance measures such as “MSE, Precision, Recall, F1_Score and Accuracy”.