NCA-GA-SVM: a new two-level feature selection method based on neighborhood component analysis and genetic algorithm in hepatocellular carcinoma (HCC) fatality prognosis
Authors:
- Wojciech Książek,
- Filip Turza,
- Paweł Pławiak
Abstract
Hepatocellular carcinoma (HCC) is one of the major challenges facing biomedical research. Despite the high lethality, methods to predict mortality for this type of aggressive malignant tumor are insufficient. Machine learning is recognized by many authors as a valuable, yet poorly studied tool in this field. Undoubtedly, searching for new feature selection methods is significant in building an effective machine learning model. In this study, we propose the novel hybrid model using neighborhood components analysis, genetic algorithm and support vector machine classifier (NCA-GA-SVM). Due to the fact that SVM works with default parameters characterized by low classification results, we decided to use GA for the proper optimization and feature selection. As reported in the available literature, NCA and GA obtain high classification results. Here, we decided to combine these approaches, building a two-level algorithm for HCC fatality prognosis. We used a well-known dataset collected from 165 patients at Coimbra's Hospital and Universitary Center, Portugal. Our results revealed 96.36% classification accuracy and 95.52% F1-score. Additionally, we compared all data for these metrics published so far. We demonstrated that our algorithm achieved the highest accuracy and can be successfully applied for the assessment of hepatocellular carcinoma mortality in the future. Our findings bring methodological value for future HCC studies and emphasize the possibility of using machine learning techniques to improve the quality of medical decisions.
- Record ID
- CUT36991877d0834ffd8967be60d51fb6d4
- Publication categories
- ;
- Author
- Journal series
- International Journal for Numerical Methods in Biomedical Engineering, ISSN 2040-7939, e-ISSN 2040-7947
- Issue year
- 2022
- Vol
- 38
- No
- 6
- Pages
- [1-16]
- Article number
- e3599
- Other elements of collation
- rys.; schem.; tab.; wykr.; Bibliografia (na s.) - 14-16; Bibliografia (liczba pozycji) - 62; Oznaczenie streszczenia - Abstr.; Data udostępnienia on-line - 2022-04-11; Numeracja w czasopiśmie - Vol. 38, Iss. 6
- Keywords in English
- machine learning, hepatocellular carcinoma (HCC), genetic algorithms, neighborhood component analysis (NCA), feature selection
- ASJC Classification
- ; ; ; ; ;
- DOI
- DOI:10.1002/cnm.3599 Opening in a new tab
- URL
- https://onlinelibrary.wiley.com/doi/full/10.1002/cnm.3599 Opening in a new tab
- Language
- eng (en) English
- Score (nominal)
- 100
- Score source
- journalList
- Score
- Publication indicators
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT36991877d0834ffd8967be60d51fb6d4/
- URN
urn:pkr-prod:CUT36991877d0834ffd8967be60d51fb6d4
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.