A hybrid high‐order type‐2 FCM improved random forest classification method for breast cancer risk assessment

Mahsa Hosseinpour, Sehraneh Ghaemi, Sohrab Khanmohammadi and Sabalan Daneshvar

Applied Mathematics and Computation, 2022, vol. 424, issue C

Abstract: One of the main challenges in breast cancer risk assessment is to provide a patient with an easily interpretable perspective on her disease's situation. This paper proposes a new method for accessing breast cancer risk, called Hybrid High-order Type-2 Fuzzy Cognitive Map Improved Random Forest Classification (H-HT2 FCM IRFC, in which, by taking an exact analysis, the disease risk is qualitatively obtained in three modes, i.e., each optimistic, realistic and pessimistic. Using either FCM or high-order FCM does not make a favorable response in uncertain situations where applying type-2 fuzzy to obtain the weights of FCM will have much better answers. A hybrid version of high-order type-2 FCM, proposed in this work, enables us to assess the breast cancer risk in three modes of optimistic, realistic, and pessimistic. The proposed method has three levels; at the first level, patient profile, family history, and inherited factors are tested by high-order FCM. At the second level, by examining the mass characteristics obtained from the mammograms, the disease risk is achieved by hybrid high-order type-2 FCM in three modes of optimistic, realistic, and pessimistic. The position of the tumor's effect on breast cancer is obtained in the third level by the fuzzy method. Finally, an overall breast cancer risk is predicted by a new algorithm, called Improved Random Forest Classification, which results in superior performance. Compared with the existing methods, the accuracy of the results obtained from the proposed method is desirable. The three-mode assessment will help the patients and their physician (oncologist) run the best treatment. Finally, the proposed method is successfully tested on an actual medical dataset.

Keywords: Type-2 fuzzy systems; Fuzzy cognitive maps; Breast cancer; Risk assessment approach; Image processing; Random forest classification (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0096300322001242
Full text for ScienceDirect subscribers only

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:eee:apmaco:v:424:y:2022:i:c:s0096300322001242

DOI: 10.1016/j.amc.2022.127038

Access Statistics for this article

Applied Mathematics and Computation is currently edited by Theodore Simos

More articles in Applied Mathematics and Computation from Elsevier
Bibliographic data for series maintained by Catherine Liu ().