Scholarlink

Abstract <p>This paper proposes a computational model to assess the rehabilitation progress of stroke patients based on fuzzy cognitive maps (FCM). The proposed model addresses the challenges of integrating multidisciplinary clinical variables, patient activities, and collaborative medical activities, which are crucial for effective stroke rehabilitation. Through the development of the FCM, we represent the dynamic interactions between clinical indicators, patient treatment adherence, and collaborative workflows, enabling continuous monitoring and informed decision-making. Our FCM was calibrated using particle swarm optimization (PSO) by using synthetic data, achieving an accuracy of 95% and a Kappa coefficient of 0.92. Additionally, we developed an automated interpreter to translate the FCM results, focusing on a textual description and graphical semaphore, which facilitates clinical decision-making for physicians. Our proposal presents a new approach to assess the rehabilitation progress of stroke patients, integrating soft computing into clinical contexts and collaborative work.</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

Computer-Assisted Assessment of Rehabilitation Progress in Stroke Patients: A Fuzzy Cognitive Map-Based Approach

  • 期刊论文

  • 发表日期：

    2025年12月1日

查看全文
  • Sofía Isabel Fernández Gregorio,
  • Luis G. Montané-Jiménez,
  • Luis Alberto Morales Rosales

摘要

Abstract

This paper proposes a computational model to assess the rehabilitation progress of stroke patients based on fuzzy cognitive maps (FCM). The proposed model addresses the challenges of integrating multidisciplinary clinical variables, patient activities, and collaborative medical activities, which are crucial for effective stroke rehabilitation. Through the development of the FCM, we represent the dynamic interactions between clinical indicators, patient treatment adherence, and collaborative workflows, enabling continuous monitoring and informed decision-making. Our FCM was calibrated using particle swarm optimization (PSO) by using synthetic data, achieving an accuracy of 95% and a Kappa coefficient of 0.92. Additionally, we developed an automated interpreter to translate the FCM results, focusing on a textual description and graphical semaphore, which facilitates clinical decision-making for physicians. Our proposal presents a new approach to assess the rehabilitation progress of stroke patients, integrating soft computing into clinical contexts and collaborative work.