Detection Analysis of Various Types of Cancer by Logistic Regression using Machine Learning
Heena Nankani1, Shruti Gupta2, Shubham Singh3, S. S. Subashka Ramesh4

1Heena Nankani, Student of SRMIST, Ramapuram, Chennai, India.
2Shruti Gupta, Student of SRMIST, Ramapuram, Chennai, India.
3Shubham Singh, Student of SRMIST, Ramapuram, Chennai, India.
4Dr. S. S. Subashka Ramesh, Assistant Professor of Computer Science And Engineering, SRMIST, Ramapuram, Chennai, India.
Manuscript received on September 18, 2019. | Revised Manuscript received on October 20, 2019. | Manuscript published on October 30, 2019. | PP: 99-104 | Volume-9 Issue-1, October 2019 | Retrieval Number: A1055109119/2019©BEIESP | DOI: 10.35940/ijeat.A1055.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Cancer is now a day’s one of the main diseases which has widely affected among the peoples. A molecular pathologist selects a list of genetic variations of interest that he/she wants to analyze. The molecular pathologist searches for evidence in the medical literature that somehow is relevant to the genetic variations of interest Finally this molecular pathologist spends a huge amount of time detecting the evidence which is related to each of the variations to classify them. The ultimate goal is to replace step 3 by a machine learning model. The molecular pathologist will still have to decide which variations area of interest, and also collect the relevant evidence. In this paper, we apply machine learning methods especially logistic regression (which is more accurate) on the datasets to determine and examine whether there are any signs or possibilities of cancer and if the person is examined as cancerous then the stage of cancer is also determined. Cancer disease is classified into four types named type 1, type 2, type 3 and type 4. Id, Gene, variation, and class are the fields used.
Keywords: Cancer, Gene, Variations, Class, Pathologist, machine learning model