Expert System for Neurocognitive Rehabilitation Based on the Transfer of the ACE-R to CHC Model Factors

Abstract

This article focuses on developing an expert system applicable to the area of neurocognitive rehabilitation. The benefit of this interdisciplinary research is to propose an expert system that has been adapted based on real patients’ results from the Addenbrooke’s cognitive examination (ACE-R). One of this research’s main results is a unique proposal to transfer the ACE-R result to the CHC (Cattell–Horn–Carroll) intelligence model. This unique approach enables transforming the CHC model domains according to the modified ACE-R factor analysis, which has never been used before. The expert system inference results allow the automated optimized design of a neurorehabilitation plan to train patients’ cognitive functions according to the CHC model. A set of tasks in 6 difficulty levels (Level 1–Level 6) was proposed for each of the nine CHC model domains. For each patient, the ACE-R results helped determine specific CHC domains to be rehabilitated as well as the starting game level for the rehabilitation within each domain. The proposed expert system has been verified on real data of 705 patients and achieved an average error of 5.94% for all CHC model domains. The proposed system is to be included in the outcomes of the research project of the Technology Agency of the Czech Republic as a verified procedure for healthcare providers.

Proposal of neural network model for neurocognitive rehabilitation and its comparison with fuzzy expert system model

“…In the article [ 3 ], we describe in detail the use of fuzzy expert systems for initial patient classification into recommended training game levels. This article builds upon that work and aims to describe and experimentally verify the proposed Eddie neurorehabilitation system, whose core is artificial neural networks.…”

“…The transformation of ACE-R results into CHC model domains was achieved by modifying the factor analysis according to Connolly et al [ 2 ]. Authors of the article published this topic in [ 3 ]. Expert systems were used there as the artificial intelligence model, which were adapted and verified on real patient data.…”

“…Therefore, this article describes the proposed a personal neurorehabilitation system based on artificial neural networks that were used there as the artificial intelligence model. We used the same real dataset as in [ 3 ] for our experimental validation study and we compared obtained results with outputs from the expert system.…”

“…Outputs from the ACE-R test for each of the five cognitive domains are analysed and translated into CHC abilities. This is described in detail in [ 3 ].…”

“…We used the default settings of evaluative expressions, which permit a limited use of modifiers with atomic expressions. While it’s possible to alter the parameters of modifiers, we opted to stick with the default settings in our work, as detailed in the article concerning the proposed expert system [ 3 ] Fig. 2 .…”