Hybrid genetic model with ANOVA for predicting breast neoplasm using METABRIC gene data. (2022)

• Record Type: Journal Article
• Authors: Thakur, Bharti; Gupta, Gaurav; Kumar, Nagesh
• Is Part Of: Materials today. Volume 56:Part 4(2022)
• Page Start: 1847
• Page End: 1852
• Publication Date: 2022
• Subjects: Breast Neoplasm -- ANOVA -- Genes -- Genetic algorithm -- Artificial neural network -- Machine Learning; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2021.11.035
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: In 2020, 2.3 million females identified with breast cancer, and it is the second most frequent cancer among females. As a result, there is severe requirement of an accurate procedure to recognize breast cancer. In accordance with breast cancer organization the breast cancer is divided into two types one is invasive and another one is non-invasive. In Indian cities like Delhi, Kolkata and Mumbai have the highest death rate for female due to breast cancer. Unusual alteration in genes is the prime reason for breast cancer. Our paper contains metabric dataset related to 1905 patients along with 31 clinical characteristics and 331 genes. The novelty of this paper is to find out genes which are highly responsible for death from breast cancer with foremost clinical features and implementation of a hybrid method which is a combination of genetic algorithm and artificial neural network to get the best accuracy with the help of machine learning as this can preserve life of females. For attribute scaling standard scaler is used which range data in between 0 and 1. Attribute selection is performed with the help of ANOVA which is a statistical appliance. With this tool 6 leading clinical attributes are examined. In our research 12 genes gsk3b, kmt2c, map4, tsc2, tnk2, pdgfb, ncoa3, akt1, afdn, sdc4, map2k2 and tubb4b which are extremely responsible for death in our dataset are recognized and our hybrid method implementation gives the perfection of 90.57%.