Performance Analysis of Gene Expression Profiles of Lung Cancer Prediction using JR Algorithm
Sriharsha Vikruthi, Kishore Babu Thippagudisa, Pathan Hussain Basha, PerlaBala Vamsi, Gudavalli Mahesh Chandra, VattemKasiVenkata Sai Kiran
Abstract
Every year, more than one million people worldwide die from lung cancer, a prevalent cancer. There are two primary subtypes of lung cancer, lung Adeno Carcinoma (AC) and lung Squamous Cell Cancer (SCC), which differ in various ways. Lung cancer mortality rates have been rising in recent years, making determining whether a tumor has turned cancerous is increasingly necessary. It is vital to detect the disease early to save lives, as a correct decision may also assist doctors in beginning medication. The scanned images of the patient's lungs are analyzed to determine the condition. An X-ray, CT scan (computed tomography), or MRI (Magnetic Resonance Imaging) could be the subject of this scan analysis. Since various imaging techniques are utilized to visualize the patient's lungs, one of the challenging aspects is the automated categorization of lung cancer. Lung cancer detection and classification have been demonstrated to have a lot of potential when employing image processing and Machine Learning (ML) approaches. Because of this, a performance analysis of the JR (Johnson Reducer) algorithm's prediction of Gene expression patterns for lung cancer is reported in this investigation. Accuracy, specificity, and sensitivity are measured in the performance examination of the suggested model.