Data Processing and Machine Learning for Assistive and Rehabilitation Technologies - Research overview

Aug 2, 2026

Upload by Asher

Special Issue “Data Processing and Machine Learning for Assistive and Rehabilitation Technologies” gathers nine cutting-edge research contributions showing how data processing and machine learning advance assistive and rehabilitation science in digital healthcare. Papers address central nervous system and musculoskeletal disease detection, stroke rehabilitation using wearable-device data and deep or hybrid models, and machine-learning-based decoding of movement intention for assistive robotics control. The collection highlights predictive modeling across diverse data sources, supports clinician screening, and proposes new patient-treatment and interaction paradigms.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages2

Reading Time5 min

AccessFree to download

Special Issue goals and scope

Key research lines and application areas

Disease detection and explainable AI

Stroke rehabilitation and wearable-data modeling

Human movement intention decoding for assistive robotics

Editorial Data Processing and Machine Learning for Assistive and Rehabilitation Technologies Andrea Tigrini , Agnese Sbrollini * and Alessandro Mengarelli Received: 10 January 2025 Accepted: 13 January 2025 Published: 15 January 2025 Citation: Tigrini, A.; Sbrollini, A.; Mengarelli, A. Data Processing and Machine Learning for Assistive and Rehabilitation Technologies. Bioengineering 2025, 12, 70 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)bioengineering12010070 Copyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) . Department of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, Italy; [a.mengarelli@staff.univpm.it](a.mengarelli@staff.univpm.it) (A.M.) * Correspondence: [a.sbrollini@staff.univpm.it](a.sbrollini@staff.univpm.it) This Special Issue (SI),“Data Processing and Machine Learning for Assistive and Rehabilitation Technologies”, aimed to collect cutting-edge research papers that frame how data-driven approaches and machine learning techniques are advancing the field of assistive and rehabilitation technologies. Under this SI, a total of nine contributions were collected [1–9] . The selected papers tackle diverse challenges in digital healthcare, ranging from neurodegenerative disease detection, stroke rehabilitation, sleep disorder diagnostics, and robotic therapies. All the contributions published in this SI demonstrated the potential carried by embedding machine learning and data processing technology in assistive and rehabilitation science to create new paradigms of patient treatment, management, and interaction with modern assistive devices. Despite the high variety of topics, three main research lines are recognizable as of interest to the research community, underlining the need to introduce artificial intelligence (AI) technologies as a tool to solve the increasing challenges that the healthcare system is facing. The first topic highlighted by the published papers regards the introduction of such tools for the detection of different diseases affecting the central nervous system or themusculoskeletal system [2,3,5,6,8] . Under this framework, the SI demonstrated once more that different sources of data, from brain imaging to posturographic data, can be valuable to create models that are able to predict pathological conditions in incoming patients. Indeed, Salehi and colleagues [3] explored the potential of long short-term memory (LSTM) networks for Alzheimer’s disease identification from magnetic resonance imaging (MRI), whereas in Dindorf et al. [2] an explainable AI model was leveraged for achieving postural deficits diagnosis. In this case, both deep and machine learning systems can be helpful to clinicians by supporting their screening and by looking for hidden patterns that are not considered in the standard clinical scenario. In addition, sleep disorder diagnosis was a specific aspect considered within this SI, by the work of Alattar et al. [8], who thoroughly reviewed the most recent and cutting-edge AI-based technique in this field. The second area regards the field of AI applied in rehabilitation from stroke recovery. In this framework, the published contributions showed how to process data from wearable devices (e.g., electromyographic and inertial measurement unit signals) and how deep learning and hybrid models can be efficient in assessing movement abnormalities and guiding assistive hand therapy in stroke patients [4,9] . In the work by Bonanno et al. [9], the neural plasticity associated with rehabilitative paths based on robotic devices has been reviewed by focusing on those papers where neurofunctional correl

FAQs

What is the purpose of the Special Issue on assistive and rehabilitation technologies?

It aims to collect advanced research on how data-driven approaches and machine learning techniques are advancing assistive and rehabilitation technologies for digital healthcare.

Which main research directions are highlighted in the collected papers?

Three lines are emphasized: AI tools for detecting central nervous system and musculoskeletal conditions, AI for stroke rehabilitation using wearable-device data, and machine learning for decoding human movement intention to control assistive robotics.

How do the papers propose using different data sources to improve patient outcomes?

They show that combining data sources such as brain imaging, posturographic signals, near-infrared/neuroimaging, and EMG can train models to predict pathological conditions, assess movement abnormalities, and enable more effective assistive interaction.

Aug 2, 2026

Upload by Asher