Knowledge Mining from Health Data: Application of Feature Selection Approaches

Md. Rabiul Auwul, Md. Ajijul Hakim, Fahmida Tasnim Dhonno, Nusrat Afrin Shilpa and Mohammad Zoynul Abedin ()
Additional contact information
Md. Rabiul Auwul: American International University-Bangladesh
Md. Ajijul Hakim: Travelex Qatar, Golbex Business Center
Fahmida Tasnim Dhonno: Hajee Mohammad Danesh Science and Technology University
Nusrat Afrin Shilpa: Hajee Mohammad Danesh Science and Technology University
Mohammad Zoynul Abedin: Teesside University International Business School, Teesside University

A chapter in Novel Financial Applications of Machine Learning and Deep Learning, 2023, pp 217-231 from Springer

Abstract: Abstract This paper aims to measure the performance of feature selection approaches for mining knowledge from health datasets. We compare seven popular knowledge mining approaches, namely relaxed Lasso, random forest, ReliefF, OneR, information gain, T-test, and Chi-squared test. The support vector machine (SVM) classifier applies to determine the accuracy and area under the curve (AUC) values of the knowledge miners. We use six popular Affymetrix and cDNA datasets. The results reveal that the relaxed lasso works well with Affymetrix, and the relaxed Lasso with random forest approaches perform well with the cDNA datasets. This paper will enrich the existing literature and assist to identify the best feature for knowledge mining in the health informatics domain.

Keywords: Knowledge mining; Feature selection; Classification; Cancer data; SVM; Affymetrix; cDNA datasets (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:isochp:978-3-031-18552-6_13

Ordering information: This item can be ordered from
http://www.springer.com/9783031185526

DOI: 10.1007/978-3-031-18552-6_13

Access Statistics for this chapter

More chapters in International Series in Operations Research & Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().