Feature Selection of Non-Small Cell Lung Cancer Nodules
Principal Investigator
Name
Jiaqi Ou
Degrees
Undergraduate student in Data Science and Big Data Technology
Institution
School of Software Engineering, Chengdu University of Information Technology
Position Title
Grade 20 undergraduate student in Data Science and Big Data Technology
Email
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-1045
Initial CDAS Request Approval
Apr 13, 2023
Title
Feature Selection of Non-Small Cell Lung Cancer Nodules
Summary
Feature selection algorithms can be used to identify features with the greatest correlation and predictive power, and ultimately create disease diagnosis and outcome prediction models. This project investigates a data-driven feature selection method combined with support vector machines (SVM) and random forest (RF) to establish a predictive model for the diagnosis of non-small cell lung cancer. We used GP as a feature selector and then used SVM or RF to create a classifier for the diagnosis of non-small cell lung cancer from radiological data.
Aims
This project aims to develop a data-driven feature selection method using symbolic genetic programming combined with support vector machines and random forests to build a predictive model for cancer diagnosis.
Collaborators
Xu Hao - Chengdu University of Information Technology