{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T06:07:44Z","timestamp":1779084464276,"version":"3.51.4"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>Neurorehabilitation poses a crucial problem in clinical recovery tasks, particularly for individuals with poor motor functions and neurological impairments, and problems in activities of daily living (ADL). To resolve this, we design a novel model, Rehab-DRLX, with a hybrid deep learning (HDL) framework that combines deep reinforcement learning (DRL) with an explainable transformer model to provide interpretable, accurate prognostic results. The propounded model is designed to effectively process the multimodal data inputs, which include clinical records, sensor-entrenched motion data, and neuroimaging, along with time-dependent recovery patterns from its reinforced representation learning (RRL) module. The RRL module employs a convolutional neural network (CNN) within the DRL agent, which performs spatiotemporal feature encoding and dynamically recovers a policy from its reward-guided learning method. To ensure interpretability, the explainable prognosis transformer (XPT) is utilized, which contains clinical contextual positional encoding and a hierarchical attention mechanism to enable transparent and reliable decision-making. This duality in the Rehab-DRLX architecture enables effective forecasting of the recovery outcomes, including functional independence probability, with both interpretability and accuracy, addressing the drawbacks of conventional black box prognosis tools. The experimental results of Rehab-DRLX show the noteworthy improvements in metrics such as accuracy (94.6%), F1-score (0.93), root mean square (RMSE) (0.082), and mean absolute error (MAE) (0.061) compared to existing studies. The ablation studies reveal the significant contribution of every architectural component and its overall performance. The results show the practical viability of Rehab-DRLX, which not only improves decision-making but also builds clinical trust through explainable insights.<\/jats:p>","DOI":"10.3389\/fncom.2026.1808274","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T05:42:16Z","timestamp":1779082936000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Rehab-DRLX: explainable neurorehabilitation prognosis using deep reinforcement learning and transformer-based models"],"prefix":"10.3389","volume":"20","author":[{"given":"Hadeel","family":"Alsolai","sequence":"first","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University","place":["Riyadh, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shakir","family":"Khan","sequence":"additional","affiliation":[{"name":"Information Technology Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU)","place":["Riyadh, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rakesh Kumar","family":"Mahendran","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Saveetha Engineering College","place":["Chennai, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arvind","family":"Panwar","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Galgotias University, Greater Noida","place":["UP, India"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bayan Ibrahimm","family":"Alabduallah","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University","place":["Riyadh, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatimah","family":"Alhayan","sequence":"additional","affiliation":[{"name":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University","place":["Riyadh, Saudi Arabia"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"pzad140","DOI":"10.1093\/ptj\/pzad140","article-title":"Uptake of technology for neurorehabilitation in clinical practice: a scoping review","volume":"104","author":"Alt Murphy","year":"2024","journal-title":"Phys. Ther."},{"key":"B2","doi-asserted-by":"publisher","first-page":"176","DOI":"10.2478\/ebtj-2024-0017","article-title":"Examining tongue movement intentions in EEG-based BCI with machine and deep learning: an approach for dysphagia rehabilitation","volume":"8","author":"Aslan","year":"2024","journal-title":"EuroBiotech J."},{"key":"B3","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1097\/CCO.0000000000000999","article-title":"Neurorehabilitation in brain tumours: evidences and suggestions for spreading of knowledge and research implementation","volume":"35","author":"Bartolo","year":"2023","journal-title":"Curr. Opin. Oncol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/s11063-022-10744-6","article-title":"HDL-PSR: modelling spatio-temporal features using hybrid deep learning approach for post-stroke rehabilitation","volume":"55","author":"Bijalwan","year":"2023","journal-title":"Neural Process. Lett."},{"key":"B5","doi-asserted-by":"publisher","first-page":"785","DOI":"10.3390\/bioengineering10070785","article-title":"Gait analysis in neurorehabilitation: from research to clinical practice","volume":"10","author":"Bonanno","year":"2023","journal-title":"Bioengineering"},{"key":"B6","doi-asserted-by":"publisher","first-page":"517","DOI":"10.32604\/cmc.2025.060368","article-title":"GACL-Net: hybrid deep learning framework for accurate motor imagery classification in stroke rehabilitation","volume":"83","author":"Bunterngchit","year":"2025","journal-title":"Comput. Mater. Contin."},{"key":"B7","doi-asserted-by":"publisher","first-page":"2415","DOI":"10.3390\/biomedicines12102415","article-title":"Towards transforming neurorehabilitation: the impact of artificial intelligence on diagnosis and treatment of neurological disorders","volume":"12","author":"Calderone","year":"2024","journal-title":"Biomedicines"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e26","DOI":"10.12786\/bn.2022.15.e26","article-title":"Use of machine learning in stroke rehabilitation: a narrative review","volume":"15","author":"Choo","year":"2022","journal-title":"Brain Neurorehabil."},{"key":"B9","doi-asserted-by":"publisher","first-page":"6347","DOI":"10.3390\/app14146347","article-title":"A comprehensive review on brain\u2013computer interface (BCI)-based machine and deep learning algorithms for stroke rehabilitation","volume":"14","author":"Elashmawi","year":"2024","journal-title":"Appl. Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3390\/robotics13030049","article-title":"Intelligent robotics in pediatric cooperative neurorehabilitation: a review","volume":"13","author":"Ezra Tsur","year":"2024","journal-title":"Robotics"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1101\/2024.04.15.24305831","article-title":"Vestibular rehabilitation practice in neurorehabilitation: an Italian survey protocol","author":"Ferri","year":"2024","journal-title":"medRxiv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"780147","DOI":"10.3389\/fnins.2021.780147","article-title":"A novel active rehabilitation model for stroke patients using electroencephalography signals and deep learning technology","volume":"15","author":"Gao","year":"2021","journal-title":"Front. Neurosci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1245707","DOI":"10.3389\/fnhum.2024.1245707","article-title":"Motor imagery for paediatric neurorehabilitation: how much do we know? Perspectives from a systematic review","volume":"18","author":"Gentile","year":"2024","journal-title":"Front. Hum. Neurosci."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/B978-0-443-13772-3.00014-5","article-title":"\u201cAI-based technologies, challenges, and solutions for neurorehabilitation: a systematic mapping,\u201d","author":"Gupta","year":"2024","journal-title":"Computational Intelligence and Deep Learning Methods for Neuro-Rehabilitation Applications"},{"key":"B15","volume-title":"Computational Intelligence and Deep Learning Methods for Neuro-Rehabilitation Applications","author":"Hemanth","year":"2023"},{"key":"B16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/10749357.2023.2200304","article-title":"Limitations in utilization and prioritization of standardized somatosensory assessments after stroke: a cross-sectional survey of neurorehabilitation clinicians","volume":"31","author":"Hoh","year":"2024","journal-title":"Top. Stroke Rehabil."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3558884.3558897","article-title":"\u201cEvaluating neurorehabilitation exercises captured with commodity sensors and machine-learning framework,\u201d","author":"Islam","year":"2022","journal-title":"Proceedings of the 7th International Workshop on Sensor-Based Activity Recognition and Artificial Intelligence"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1431815","DOI":"10.3389\/fncom.2024.1431815","article-title":"Electroencephalogram-based adaptive closed-loop brain-computer interface in neurorehabilitation: a review","volume":"18","author":"Jin","year":"2024","journal-title":"Front. Comput. Neurosci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"6051009","DOI":"10.1155\/2021\/6051009","article-title":"Magnetic resonance image feature analysis under deep learning in diagnosis of neurological rehabilitation in patients with cerebrovascular diseases","volume":"2021","author":"Li","year":"2021","journal-title":"Contrast Media Mol. Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1109\/TNSRE.2024.3384498","article-title":"Explainable deep-learning prediction for brain-computer interfaces supported lower extremity motor gains based on multi-state fusion","volume":"32","author":"Lin","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B21","doi-asserted-by":"publisher","first-page":"6003","DOI":"10.1109\/JBHI.2022.3205436","article-title":"A transferable deep learning prognosis model for predicting stroke patients' recovery in different rehabilitation trainings","volume":"26","author":"Lin","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"B22","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1080\/02699052.2022.2059813","article-title":"Neurorehabilitation for people with disorders of consciousness: an international survey of health-care structures and access to treatment, (part 1)","volume":"36","author":"Maurer-Karattup","year":"2022","journal-title":"Brain Inj."},{"key":"B23","doi-asserted-by":"publisher","first-page":"30283","DOI":"10.1109\/ACCESS.2021.3055960","article-title":"Upper limb rehabilitation system for stroke survivors based on multi-modal sensors and machine learning","volume":"9","author":"Miao","year":"2021","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2339","DOI":"10.1007\/s00521-020-05125-w","article-title":"Effect of hand grip actions on object recognition process: a machine learning-based approach for improved motor rehabilitation","volume":"33","author":"Mishra","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"B25","doi-asserted-by":"publisher","first-page":"122954","DOI":"10.1016\/j.eswa.2023.122954","article-title":"EEG sensor driven assistive device for elbow and finger rehabilitation using deep learning","volume":"244","author":"Mukherjee","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.1080\/09638288.2023.2201514","article-title":"Quantifying patient experiences with therapeutic neurorehabilitation technologies: a scoping review","volume":"46","author":"Nguyen","year":"2024","journal-title":"Disabil. Rehabil."},{"key":"B27","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.1080\/17483107.2024.2316312","article-title":"EEG-based brain-computer interface methods with the aim of rehabilitating advanced stage ALS patients","volume":"19","author":"Pirasteh","year":"2024","journal-title":"Disabil. Rehabil. Assist. Technol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/B978-0-443-13772-3.00012-1","article-title":"\u201cMachine learning for cognitive treatment planning in patients with neurodisorder and trauma injuries,\u201d","author":"Sandhu","year":"2024","journal-title":"Computational Intelligence and Deep Learning Methods for Neuro-Rehabilitation Applications"},{"key":"B29","doi-asserted-by":"publisher","first-page":"13573","DOI":"10.1007\/s00521-025-11201-w","article-title":"Classifying EEG data from spinal cord injured patients using manifold learning methods for brain-computer interface-based rehabilitation","volume":"37","author":"Sayilgan","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"B30","doi-asserted-by":"publisher","first-page":"36026","DOI":"10.1109\/ACCESS.2024.3373910","article-title":"A survey of wearable sensors and machine learning algorithms for automated stroke rehabilitation","volume":"12","author":"Sengupta","year":"2024","journal-title":"IEEE Access"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3375","DOI":"10.1109\/TNSRE.2023.3305474","article-title":"A novel neurorehabilitation prognosis prediction modeling on separated left-right hemiplegia based on brain-computer interfaces assisted rehabilitation","volume":"31","author":"Shao","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B32","doi-asserted-by":"publisher","first-page":"7003","DOI":"10.3390\/jcm11237003","article-title":"Neurorehabilitation in multiple sclerosis\u2014a review of present approaches and future considerations","volume":"11","author":"S\u00eerbu","year":"2022","journal-title":"J. Clin. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"673","DOI":"10.3390\/diagnostics11040673","article-title":"Machine-learning-based rehabilitation prognosis prediction in patients with ischemic stroke using brainstem auditory evoked potential","volume":"11","author":"Sohn","year":"2021","journal-title":"Diagnostics"},{"key":"B34","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s11910-022-01181-y","article-title":"Gamified neurorehabilitation strategies for post-stroke motor recovery: challenges and advantages","volume":"22","author":"Tosto-Mancuso","year":"2022","journal-title":"Curr. Neurol. Neurosci. Rep."},{"key":"B35","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/B978-0-443-22158-3.00008-9","article-title":"\u201cAssistive technology for neuro-rehabilitation applications using machine learning techniques,\u201d","author":"Tripathi","year":"2025","journal-title":"Machine Learning Models and Architectures for Biomedical Signal Processing"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.3390\/neurolint14040084","article-title":"EEG in neurorehabilitation: a bibliometric analysis and content review","volume":"14","author":"Tsiamalou","year":"2022","journal-title":"Neurol. Int."},{"key":"B37","doi-asserted-by":"publisher","first-page":"100749","DOI":"10.1016\/j.sbsr.2025.100749","article-title":"TraxVBF: A hybrid transformer-xLSTM framework for EMG signal processing and assistive technology development in rehabilitation","volume":"47","author":"Zendehbad","year":"2025","journal-title":"Sens. Bio-Sens. Res."},{"key":"B38","doi-asserted-by":"publisher","first-page":"909610","DOI":"10.3389\/fnhum.2022.909610","article-title":"EEG-based brain network analysis of chronic stroke patients after BCI rehabilitation training","volume":"16","author":"Zhan","year":"2022","journal-title":"Front. Hum. Neurosci."},{"key":"B39","doi-asserted-by":"publisher","first-page":"12935","DOI":"10.1038\/s41598-025-96611-5","article-title":"Multi-scale convolutional transformer network for motor imagery brain-computer interface","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"B40","doi-asserted-by":"publisher","first-page":"49","DOI":"10.4028\/p-2Jc2QF","article-title":"Active rehabilitation gloves based on brain-computer interfaces and deep learning","volume":"63","author":"Zhu","year":"2023","journal-title":"J. Biomim. Biomater. Biomed. Eng."}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1808274\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T05:42:17Z","timestamp":1779082937000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2026.1808274\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":40,"alternative-id":["10.3389\/fncom.2026.1808274"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2026.1808274","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"article-number":"1808274"}}