Download PDFOpen PDF in browser

Identification and Augury of Chronic Disease by Logit Regression and Machine Learning

EasyChair Preprint no. 8017

10 pagesDate: May 22, 2022


Every year, a lot of deaths occurred from different chronic diseases in which Cancer is one of the most harmful diseases. It is the most common type diseases who are leading cause of death in the people worldwide. Cancer happens only when abnormal cells produce and replicate in an uncontrolled way in a explicit part of the body. These cancer cells can invade and destroy surrounding healthy tissue, including organs. The prediction and diagnosis of chronic diseases are challenge for healthy life and researcher on early stage of Cancer also. Therefore, high accuracy in predicting chronic disease is more important for treatment in all aspects for the patients. Here we use the Machine learning Concept and its significant contribution to the predicting and early detection of type of chronic disease (Cancer). Breast cancer is the second most common cancer in women after skin cancer. Cancer occurs as a result of mutations, or abnormal changes, in the genes responsible for regulating the growth of cells and keeping them healthy. To detect it on early stages we have use machine learning algorithms, Support Vector Machine (SVM), Random Forest, Logistic Regression, and Logit Regression, for breast cancer. Using this we are able to predict and diagnose breast cancer on early stages and find the effectiveness in terms of confusion matrix, accuracy, and accuracy. With the help of Logit regression the outperform gets accuracy (93.2%).

Keyphrases: Benign, Logit regression, machine learning, Malignant

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Radhesh Pandey and Kamal Srivastava},
  title = {Identification and Augury of Chronic Disease by Logit Regression and Machine Learning},
  howpublished = {EasyChair Preprint no. 8017},

  year = {EasyChair, 2022}}
Download PDFOpen PDF in browser