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...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/11834/1/P17122_74a7b05371bed1e82a4dc2ac185fae64.pdf%204.pdf http://eprints.uthm.edu.my/11834/ https://doi.org/10.1063/5.0225096 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833419632525967360 |
|---|---|
| author | Shafi, Muhammad Ammar Rusiman, Mohd Saifullah Muhamad Jamil, Siti Afiqah Mohd Zim, Mohd Arif |
| author_facet | Shafi, Muhammad Ammar Rusiman, Mohd Saifullah Muhamad Jamil, Siti Afiqah Mohd Zim, Mohd Arif |
| author_sort | Shafi, Muhammad Ammar |
| building | UTHM Library |
| collection | Institutional Repository |
| content_provider | Universiti Tun Hussein Onn Malaysia |
| content_source | UTHM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| 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 |
| id | my.uthm.eprints-11834 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | en |
| publishDate | 2024 |
| record_format | eprints |
| spelling | my.uthm.eprints-118342025-03-26T03:00:23Z http://eprints.uthm.edu.my/11834/ The prediction of high-risk symptom for colorectal cancer using a new hybrid of fuzzy statistical machine learning approach Shafi, Muhammad Ammar 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 2024-08-27 Conference or Workshop Item PeerReviewed text en http://eprints.uthm.edu.my/11834/1/P17122_74a7b05371bed1e82a4dc2ac185fae64.pdf%204.pdf Shafi, Muhammad Ammar 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 |
| spellingShingle | T Technology (General) Shafi, Muhammad Ammar 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 |
| title | 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_short | 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 |
| topic | T Technology (General) |
| url | http://eprints.uthm.edu.my/11834/1/P17122_74a7b05371bed1e82a4dc2ac185fae64.pdf%204.pdf http://eprints.uthm.edu.my/11834/ https://doi.org/10.1063/5.0225096 |
| url_provider | http://eprints.uthm.edu.my/ |