Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

Abstract

Objective: The main purpose of this research is the novel use of artificial metaplasticity on multilayer perceptron (AMMLP) as a data mining tool for prediction the outcome of patients with acquired brain injury (ABI) after cognitive rehabilitation. The final goal aims at increasing knowledge in the field of rehabilitation theory based on cognitive affectation. Methods and materials:The data set used in this study contains records belonging to 123 ABI patients with moderate to severe cognitive affectation (according to Glasgow Coma Scale) that underwent rehabilitation at Institut Guttmann Neurorehabilitation Hospital (IG) using the tele-rehabilitation platform PREVIRNEC®. The variables included in the analysis comprise the neuropsychological initial evaluation of the patient (cognitive affectation profile), the results of the rehabilitation tasks performed by the patient in PREVIRNEC® and the outcome of the patient after a 3-5 months treatment. To achieve the treatment outcome prediction, we apply and compare three different data mining techniques: the AMMLP model, a backpropagation neural network (BPNN) and a C4.5 decision tree. Results: The prediction performance of the models was measured by ten-fold cross validation and several architectures were tested. The results obtained by the AMMLP model are clearly superior, with an average predictive performance of 91.56%. BPNN and C4.5 models have a prediction average accuracy of 80.18% and 89.91% respectively. The best single AMMLP model provided a specificity of 92.38%, a sensitivity of 91.76% and a prediction accuracy of 92.07%. Conclusions: The proposed prediction model presented in this study allows to increase the knowledge about the contributing factors of an ABI patient recovery and to estimate treatment efficacy in individual patients. The ability to predict treatment outcomes may provide new insights toward improving effectiveness and creating personalized therapeutic interventions based on clinical evidence.

Neuroplastic Changes Induced by Cognitive Rehabilitation in Traumatic Brain Injury: A Review

“…With regard to the studies on functional neuroplasticity, the following articles were ruled out: 1 article reporting fMRI acquisition only in the pretraining session 32 ; 1 study protocol 34 ; 4 studies referring to individuals with mixed etiology [35][36][37][38] ; 4 studies including patients in the acute phase of recovery 13,[39][40][41] ; 2 articles focusing on the neural changes induced by motor rehabilitation 42,43 ; 13 articles (5 descriptive articles and 8 reviews) that did not specifically focus on the effects of cognitive training in TBI subjects. 24,25,33,[44][45][46][47][48][49][50][51][52][53] None of the articles on structural changes following cognitive training was included. Six articles (5 reviews and 1 descriptive article) were ruled out because they were too general or because they did not specifically focus on the effects of cognitive training in TBI subjects 2,54-58 ; 1 article was excluded because it just analyzed the correlations between cognitive performance and CT findings in TBI subjects, without considering the rehabilitation process, 59 and 1 study was removed because it was about subjects in the acute phase of recovery.…”

Metaplasticity: A Promising Tool to Disentangle Chronic Disorders of Consciousness Differential Diagnosis

“…32 Moreover, we have to acknowledge the relevance of metaplasticity in Bio-Inspired Machine Learning, which could usefully be employed in the management of patients with DoC. [119][120][121] Finally, metaplasticity assessment in patients with DoC may identify the subjects who could benefit from neuromodulation protocols, and help the clinicians implementing more personalized neurorehabilitative training for such a very frail and vulnerable group of patients.…”

Modelling Ecological Cognitive Rehabilitation Therapies for Building Virtual Environments in Brain Injury

“…The disadvantages of these methods are the associated cost of therapeutic interventions and manpower, and the difficulties to monitor the patient's performance. However, there exist technological solutions for those rehabilitation treatments focused on specific cognitive functions that allow improving the rehabilitation process efficiency [16], as well as generating new clinical knowledge [17,18]. This would suggest that appropriate technology could be applied to cognitive, economically-sustainable strategies based on behavioural methods allowing therapeutic tracking and evaluation.…”