A new method for disease diagnosis based on hierarchical BRB with power set

Han, Wence; Kang, Xin; He, Wei; Jiang, Li; Li, Hongyu; Xu, Bing

doi:10.1016/j.heliyon.2023.e13619

Cited by 6 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a typical gray-box model, the BRB model is highly accurate because of its ability to handle uncertain and incomplete data [ 17 , 18 ]. It can integrate different sources of evidence to make accurate predictions and decisions.…”

Section: Introductionmentioning

confidence: 99%

An interpretable model for stock price movement prediction based on the hierarchical belief rule base

Yin,

Zhang,

et al. 2023

Heliyon

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

An interpretable model for stock price movement prediction based on the hierarchical belief rule base

Yin,

Zhang,

et al. 2023

Heliyon

Self Cite

View full text Add to dashboard Cite

“…Meanwhile, BRB effectively expresses the uncertainty associated with beliefs by means of confidence distribution [16]. Currently, BRB has been proven effective in multiple various fields such as medical decision making [17], fault diagnosis [18] and aerospace [19]. However, the following deficiencies still exist in the current BRB breast cancer diagnosis studies.…”

Section: Et Al Introduced a Breast Cancer Diagnosis Model Based On Th...mentioning

confidence: 99%

An online belief rule base breast cancer diagnosis method with interpretability

Han

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Early diagnosis of breast cancer is critical for effective treatment. Artificial intelligence (AI) technology has shown promise in assisting physicians with diagnosis. However, the combination of qualitative and quantitative information in surveillance data leads to ambiguity and uncertainty. Belief rule bases (BRB) can address these issues by incorporating confidence distributions. However, existing BRB models rely on offline training and lack adaptability to changes in patient metrics. In addition, the ethical implications of using BRB for breast cancer diagnosis require attention to the interpretability of the model. Therefore, this paper presents an online belief rule base breast cancer diagnosis method with interpretability. The method uses online learning to achieve dynamic growth. It also overcomes the problem of interpretability loss in the optimization process by implementing interpretability constraints. The proposed method achieves competitive accuracy and interpretability in breast cancer diagnosis, as demonstrated by experiments using a large dataset of breast cancer cases.

show abstract

“…It is essentially a white-box model with a completely transparent inference process and strong interpretability of the results [19]. BRBs have been implemented in the fields of fault detection [20], risk assessment [21], industrial alarms [22] and disease diagnosis [23]. However, the system of education quality evaluation is complex with numerous indicators, which will lead to too many belief rules in constructing the BRB, so the ER algorithm is used to simplify the rules.…”

Section: Introductionmentioning

confidence: 99%

A new method for education quality evaluation based on belief rule base with power set and evidential reasoning

Liang,

Zhou,

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The evaluation of education quality is an important part of the construction of the education system, and it is a direct path to improving education quality. Education quality is a complex evaluation system that takes into account a number of dimensions, such as objectives, attitudes and outcomes. In teaching practice, these dimensions are often good or bad, making it difficult to assess the results of a comprehensive evaluation, leading to the problem of ignorance. Therefore, a belief rule base with power set (PBRB) is used to construct the model for education quality evaluation. The model extends the set of evaluation results into a power set that expresses a variety of evaluation ratings that are difficult to characterize, and uses the BRB to assign belief degrees to each rating in the power set. In addition, because the evaluation of education quality requires a great number of indicators, the BRB faces the rule combination explosion problem. To solve the problem, the transformation matrix is constructed to unify the evaluation indicators, which are then fused using the evidential reasoning (ER) algorithm to reduce the number of PBRB attributes. Finally, the parameters are optimized with the projected covariance matrix adaptive evolution strategy (P-CMA-ES) to improve the model accuracy. According to the experimental results, compared with other methods, the education quality evaluation method based on the EPBRB proposed in this paper can give a clear evaluation grade and has better accuracy and stability.

show abstract

A new method for disease diagnosis based on hierarchical BRB with power set

Cited by 6 publications

References 36 publications

An interpretable model for stock price movement prediction based on the hierarchical belief rule base

An interpretable model for stock price movement prediction based on the hierarchical belief rule base

An online belief rule base breast cancer diagnosis method with interpretability

A new method for education quality evaluation based on belief rule base with power set and evidential reasoning

Contact Info

Product

Resources

About