Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review.

Manuel Andrés Vélez-Guerrero,Mauro Callejas-Cuervo,Stefano Mazzoleni

doi:10.3390/s21062146

Abstract

Processing and control systems based on artificial intelligence (AI) have progressively improved mobile robotic exoskeletons used in upper-limb motor rehabilitation. This systematic review presents the advances and trends of those technologies. A literature search was performed in Scopus, IEEE Xplore, Web of Science, and PubMed using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology with three main inclusion criteria: (a) motor or neuromotor rehabilitation for upper limbs, (b) mobile robotic exoskeletons, and (c) AI. The period under investigation spanned from 2016 to 2020, resulting in 30 articles that met the criteria. The literature showed the use of artificial neural networks (40%), adaptive algorithms (20%), and other mixed AI techniques (40%). Additionally, it was found that in only 16% of the articles, developments focused on neuromotor rehabilitation. The main trend in the research is the development of wearable robotic exoskeletons (53%) and the fusion of data collected from multiple sensors that enrich the training of intelligent algorithms. There is a latent need to develop more reliable systems through clinical validation and improvement of technical characteristics, such as weight/dimensions of devices, in order to have positive impacts on the rehabilitation process and improve the interactions among patients, teams of health professionals, and technology.

Highlights

The proper functioning of the limbs of the human body plays a fundamental role in people’s health
This article has reviewed the final 30 articles with four different approaches: (i) a general description of the information sources; (ii) technical characteristics of the device: weight, dimensions, portability, and materials used in its manufacturing; (iii) information processing and control techniques based on artificial intelligence (AI); and (iv) the nature of the medical application on the upper limb
The results shown in [32], has demonstrated that robotic exoskeletons for motion assistance can gradually evolve into complete rehabilitation systems

Summary

Introduction

The proper functioning of the limbs of the human body plays a fundamental role in people’s health. When these limbs are temporarily or permanently affected, significant motor difficulties appear. There is a rapid growth of disability-related diseases worldwide. The World Report on Disability [1] highlights that approximately 15% of the world’s population has some form of motor disability and 4% of them suffer from diseases linked to motor or neuromotor dysfunction. Any form of disability, whether mild, moderate, or severe, impairs an individual’s functional autonomy and interaction with the environment. Other underlying social or demographic factors may increase the incidence of disability [2], as may inadequate coverage of traditional or technologybased rehabilitation services, poor coordination of care facilities, and overburdening of existing specialists [3]

Methods

Results

Discussion

Conclusion