ML Based HCC Survival Prediction System
Jayaraman Vikas1, G Vijendar Reddy2, N V Ganapathi Raju3, A Sai Hanuman4, Lakshmi Sushma Kolli5

1Jayaraman Vikas, Bachelor, Department of Information Technology from Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad (Telangana), India.
2Mr. G Vijendar Reddy, Associate Professor, Department of Information Technology, Pursing Ph.D in Computer Science Engineering from JNTU, Hyderabad (Telangana), India.
3Dr. N V Ganapathi Raju working as Professor, Department of IT, GRIET. Completed Ph.D. in CSE From Jawaharlal Nehru Technological University Kakinada (Andhra Pradesh), India.
4Dr. Akundi Sai Hanuman, Professor, Department of Computer Science and Engineering, Completed His Ph.D. From Acharya Nagarjuna University, in Guntur, (Andhra Pradesh), India.
5Ms. Lakshmi Sushma Kolli, Assistant Professor, Department of Information Technology, Completed Her M.Tech. from KL University, Vaddeswaram, Guntur (Andhra Pradesh), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 343-347 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3589048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Data Science is an interdisciplinary branch of technology, which deals with extraction of knowledge and insights from large amounts of data. It combines different fields of work of statistics and computation for data interpretation to facilitate decision making. Hepatocellular Carcinoma (HCC) is any individual who is hepatitis C positive. It is most common type of primary cancer in adults. If observed from 1980, the incidence of HCC is almost tripled. In 2018, around 42,220 adults have been estimated to have been dead. Among the affected, it was observed that more men were affected with HCC than women. This was more common in African and Asian continents. The death of a person disturbs the stability at home. This paper proposes to use data science and machine learning to build a system that may not help in predicting how long one will survive, but to find how much the treatment can be successful for him/her. Also, it provides an insight on how many people are alive with the same stage of disease and also throw light on the effectiveness of the treatment methodologies. This project performs a comparative study on various ML classifiers to identify the best one and has found Logistic Regression to offer the best performance with an accuracy of 99.49%.
Keyword: HCC, Machine Learning, Python, Survival Prediction.
Scope of the Article: Regression and Prediction