The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach

Muhammad Ammar Shafi, Muhammad Ammar Shafi and Rusiman, Mohd Saifullah and Muhamad Jamil, Siti Afiqah and Mohd Zim, Mohd Arif (2024) The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach. In: AIP Conference Proceedings.

Text
The prediction of high-risk symptom.pdf
Download (719kB)

Official URL: https://doi.org/10.1063/5.0225096

Abstract

Colorectal cancer (CRC) is a type of cancer that develops in the human colon and rectum. The body's cells proliferating out of control, which is the cause of colorectal cancer, results in these symptoms. Nevertheless, there is still disagreement on the precise signs of a high-risk CRC. The linear regression model struggles with erroneous and ambiguous data. Because the idea of fuzzy set theory can deal with data that does not refer to a precise point value, fuzzy machine learning, a new hybrid linear fuzzy regression with symmetric parameter clustering with a support vector machine model (FLRWSPCSVM), is used in this study to predict the high-risk symptoms causing the development of colorectal cancer in Malaysia (uncertainty data). After analysing secondary data from 180 colorectal cancer patients who underwent treatment in a general hospital, 25 separate symptoms with diverse combinations of variable types were considered in the analysis. Together with the model's parameters, errors, and justifications, two statistical measurement errors were also included. The least values of mean square error (MSE) are 100.605 and root mean square error (RMSE) is 10.030 for FLRWSPCSVM, which were determined to be ovarian and a history of cancer symptoms to be the high-risk symptom for developing colorectal cancer. To monitor and control the high-risk symptoms that can affect colon cancer and lower patient mortality, the hospitality industry could also benefit from this study.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Technology Management and Business > FPTP
Depositing User:	Mrs. Sabarina Che Mat
Date Deposited:	14 Nov 2024 07:13
Last Modified:	14 Nov 2024 07:13
URI:	http://eprints.uthm.edu.my/id/eprint/11960

Actions (login required)

View Item