|
Title:
|
FEATURE UTILIZATION BY MACHINE LEARNING MODELS FOR COLON CANCER CLASSIFICATION |
|
Author(s):
|
Douglas F. Redd, Qing Zeng-Treitler, Yijun Shao, Laura J. Myers, Barry C. Barker, Stuart J. Nelson and Thomas F. Imperiale |
|
ISBN:
|
978-989-8704-40-5 |
|
Editors:
|
Piet Kommers and Mário Macedo |
|
Year:
|
2022 |
|
Edition:
|
Single |
|
Keywords:
|
Machine Learning, Colon Cancer, Feature Utilization |
|
Type:
|
Full Paper |
|
First Page:
|
205 |
|
Last Page:
|
211 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Many machine learning methods are now available for classification and prediction tasks in the healthcare domain. Some traditional statistical methods, such as logistic regression, are much more readily interpretable than the newer machine learning models. While many prior studies compared machine learning performances in specific tasks, there is no standardized way to assess feature importance/contribution in machine learning models, and few compared the features utilized. This study compares four machine learning and statistical models: logistic regression, support vector machine, random forest, and deep neural network, in their performance in classifying colorectal cancer patients as well as the features used for classification. |
|
|
|
|
|
|
