Scholarlink

<p>Hospital-based Health Technology Assessment (HB-HTA) requires active stakeholder participation and significant financial investment. Selecting the appropriate healthcare assessment scheme and reaching consensus are essential. Given the diversity in educational backgrounds, knowledge, and experiences, HB-HTA participants often rely on linguistic information to express their individual preferences. However, since word meanings can vary among individuals, this leads to different semantic interpretations in large-scale group decision-making (LSGDM). These interpretations evolve with changes in information, highlighting the necessity for personalized individual semantics (PISs) continuous learning. This study introduces a self-organized approach to achieving consensus in LSGDM through PISs continuous learning. First, we present a continuous learning model for PISs that employs a consistency-driven approach for updates. Next, a novel clustering algorithm is designed to partition large populations based on individual cognitive similarity, thereby reducing computational complexity. Subsequently, an adaptive feedback adjustment mechanism is introduced, integrating identification-direction rules and optimization-based consensus rules to enhance group consensus. Finally, the applicability of the proposed approach is demonstrated through a case study on HB-HTA for managing medical consumables.</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 self-organized consensus-reaching model considering personalized individual semantic continuous learning for LSGDM: application for medical consumables assessment

  • 期刊论文

  • 发表日期：

    2025年5月24日

查看全文
  • Chai Yang,
  • Xiaoxuan Hu,
  • Decai Yu,
  • Yanjun Wang

摘要

Hospital-based Health Technology Assessment (HB-HTA) requires active stakeholder participation and significant financial investment. Selecting the appropriate healthcare assessment scheme and reaching consensus are essential. Given the diversity in educational backgrounds, knowledge, and experiences, HB-HTA participants often rely on linguistic information to express their individual preferences. However, since word meanings can vary among individuals, this leads to different semantic interpretations in large-scale group decision-making (LSGDM). These interpretations evolve with changes in information, highlighting the necessity for personalized individual semantics (PISs) continuous learning. This study introduces a self-organized approach to achieving consensus in LSGDM through PISs continuous learning. First, we present a continuous learning model for PISs that employs a consistency-driven approach for updates. Next, a novel clustering algorithm is designed to partition large populations based on individual cognitive similarity, thereby reducing computational complexity. Subsequently, an adaptive feedback adjustment mechanism is introduced, integrating identification-direction rules and optimization-based consensus rules to enhance group consensus. Finally, the applicability of the proposed approach is demonstrated through a case study on HB-HTA for managing medical consumables.