Cover Image

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

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 li...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Ammar Shafi, Muhammad Ammar Shafi, Rusiman, Mohd Saifullah, Muhamad Jamil, Siti Afiqah, Mohd Zim, Mohd Arif
Format: Conference or Workshop Item
Language:English
Published: 2024
Subjects:
T Technology (General)
Online Access:http://eprints.uthm.edu.my/11960/1/The%20prediction%20of%20high-risk%20symptom.pdf
http://eprints.uthm.edu.my/11960/
https://doi.org/10.1063/5.0225096
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uthm.eprints.11960
record_format eprints
spelling my.uthm.eprints.119602024-11-14T07:13:30Z http://eprints.uthm.edu.my/11960/ 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 Rusiman, Mohd Saifullah Muhamad Jamil, Siti Afiqah Mohd Zim, Mohd Arif T Technology (General) 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. 2024-08-24 Conference or Workshop Item PeerReviewed text en http://eprints.uthm.edu.my/11960/1/The%20prediction%20of%20high-risk%20symptom.pdf 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. https://doi.org/10.1063/5.0225096
institution Universiti Tun Hussein Onn Malaysia
building UTHM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tun Hussein Onn Malaysia
content_source UTHM Institutional Repository
url_provider http://eprints.uthm.edu.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Muhammad Ammar Shafi, Muhammad Ammar Shafi
Rusiman, Mohd Saifullah
Muhamad Jamil, Siti Afiqah
Mohd Zim, Mohd Arif
The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
description 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.
format Conference or Workshop Item
author Muhammad Ammar Shafi, Muhammad Ammar Shafi
Rusiman, Mohd Saifullah
Muhamad Jamil, Siti Afiqah
Mohd Zim, Mohd Arif
author_facet Muhammad Ammar Shafi, Muhammad Ammar Shafi
Rusiman, Mohd Saifullah
Muhamad Jamil, Siti Afiqah
Mohd Zim, Mohd Arif
author_sort Muhammad Ammar Shafi, Muhammad Ammar Shafi
title The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
title_short The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
title_full The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
title_fullStr The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
title_full_unstemmed The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
title_sort prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach
publishDate 2024
url http://eprints.uthm.edu.my/11960/1/The%20prediction%20of%20high-risk%20symptom.pdf
http://eprints.uthm.edu.my/11960/
https://doi.org/10.1063/5.0225096
_version_ 1816133310864162816
score 13.235796

Similar Items