Scholarlink

Background <p>Migraine drug choice is a multi-criteria decision-making (MCDM) issue due to the heterogeneity of drug classes, varying patient responses, side effects, and cost considerations.</p> Objectives <p>In this paper, a novel Multi-View Neutrosophic Fuzzy Kernel Clustering (MV-NFKC) and Neutrosophic Fuzzy Multi-Criteria Decision-Making (NF-MCDM) method is introduced to enhance migraine drug choice.</p> Methods <p>To address the non-linearity as well as uncertainty of MCDM and enhance the precision of medication categorization, MV-NFKC combines multi-view learning with kernel-based clustering. The MV-NFKC method employs adaptive view weighting to provide stable and impartial drug ranking via dynamic weight adjustment of the selection criteria. Following clustering, NF-MCDM applies a neutrosophic fuzzy TOPSIS-based ranking procedure to rank the most effective drug based on truth, indeterminacy, and falsity values of various attributes. The method avoids the constraints of existing neutrosophic decision models that are expert-weighted and experience difficulties in dealing with high-dimensional data.</p> Results <p>A case study of migraine drug choice illustrates the effectiveness of the suggested methodology, where Python implementation is used for data preprocessing, clustering, and ranking. The outcomes demonstrate that the proposed hybrid framework correctly identifies the optimum drug alternative with higher scalability, flexibility, and interpretability than conventional MCDM techniques.</p> Conclusion <p>This paper contributes to medical decision-making (DM) through a data-driven, rigorous, and scalable methodology for optimizing drug selection to pave the way towards more precise and specific treatment recommendations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A MV-NFKC AND NF-MCDM Framework for Optimizing Migraine Drug Selection Using Kernel-Based Clustering

  • 期刊论文

  • 发表日期：

    2026年3月23日

查看全文
  • Mounika P,
  • Arun Prakash K.

摘要

Background

Migraine drug choice is a multi-criteria decision-making (MCDM) issue due to the heterogeneity of drug classes, varying patient responses, side effects, and cost considerations.

Objectives

In this paper, a novel Multi-View Neutrosophic Fuzzy Kernel Clustering (MV-NFKC) and Neutrosophic Fuzzy Multi-Criteria Decision-Making (NF-MCDM) method is introduced to enhance migraine drug choice.

Methods

To address the non-linearity as well as uncertainty of MCDM and enhance the precision of medication categorization, MV-NFKC combines multi-view learning with kernel-based clustering. The MV-NFKC method employs adaptive view weighting to provide stable and impartial drug ranking via dynamic weight adjustment of the selection criteria. Following clustering, NF-MCDM applies a neutrosophic fuzzy TOPSIS-based ranking procedure to rank the most effective drug based on truth, indeterminacy, and falsity values of various attributes. The method avoids the constraints of existing neutrosophic decision models that are expert-weighted and experience difficulties in dealing with high-dimensional data.

Results

A case study of migraine drug choice illustrates the effectiveness of the suggested methodology, where Python implementation is used for data preprocessing, clustering, and ranking. The outcomes demonstrate that the proposed hybrid framework correctly identifies the optimum drug alternative with higher scalability, flexibility, and interpretability than conventional MCDM techniques.

Conclusion

This paper contributes to medical decision-making (DM) through a data-driven, rigorous, and scalable methodology for optimizing drug selection to pave the way towards more precise and specific treatment recommendations.