Phylogeny, Predicton and Analysis of Sickle Cell Anaemia Using Data Mining Tools from Chhattisgarh State, India

EasyChair Preprint 7143

Abstract

Sickle-Cell Anemia is a genetically inherited blood disorder that transmits millions of people around the world. A phylogenetic tree was constructed and the gene of Sickle cell Anemia from Human is found related to the M. cynomolgus Beta-globin. Sickle cell trait was now observing in some regions of Chhattisgarh state of India. Data collection from 156 patients in nine regions (Bilaspur, Pendra, Bilha, Sipat, Jairamnagar, Belgahana, Kota, Takhatpur and Mungeli) has been collected in September 2018. There are more number of Sickle cell people in Bilaspur(CG) followed by Pendra, Bilha, Sipat, Jairamnagar, Belgahana, Kota, Takhatpur and Mungeli. Based on Linear Regression analysis, Females, age with 34 and blood as major cells from pendra region is predicted test positive. Based on the data mining results of Sickle-Cell Anemia disease dataset using WEKA software, BayesNet and Adbaboost M1 classifier provides highest accuracy 80.52% and 80.12% respectively, compared with NaiveBayes, Bagging, J48, Random forest, Random tree and CART classifiers.

Keyphrases: Chhattisgarh, Data Mining, Sickle cell anemia

@booklet{EasyChair:7143,
  author    = {Aakanksha Sharma and Dowluru Kaladhar},
  title     = {Phylogeny, Predicton and Analysis of Sickle Cell Anaemia Using Data Mining Tools from Chhattisgarh State, India},
  howpublished = {EasyChair Preprint 7143},
  year      = {EasyChair, 2021}}