Performance Evaluation of Colorectal Cancer Diagnosis Classification using Machine Learning Algorithms.
Principal Investigator
Name
HYUNJIN KWON
Degrees
M.D
Institution
Open Convergence Lab
Position Title
Researcher
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-399
Initial CDAS Request Approval
Sep 28, 2018
Title
Performance Evaluation of Colorectal Cancer Diagnosis Classification using Machine Learning Algorithms.
Summary
According to the American Cancer Society survey, the number of people who died from colorectal cancer in 2016 is 49,190. This is the second highest mortality rate after lung cancer. Recently, machine learning technology has been greatly activated in industries such as medical, manufacturing, and finance. According to the increasing use of machine learning technology in the medical field, our project goal is to evaluate the performance of machine learning algorithms which can classify the diagnosis of colorectal cancer. As the machine learning algorithms, kNN, Logistic Regression, ANN, Decision Tree, and SVM would be used to classify the diagnosis of colorectal cancer. The factors such as age, BMI and family history from PLCO data would be used as the input class of machine learning algorithms and this will be trained to classify recurrence of colorectal cancer.
Aims
- Compare the performance evaluation of machine learning algorithms
- Discover the important factors that can affect the diagnosis classification.
Collaborators
JINHYEOK PARK (Open Convergence Lab)
JIHOON JUN (Open Convergence Lab)