Your new experience awaits. Try the new design now and help us make it even better

CLINICAL TRIAL article

Front. Neurol.

Sec. Neurorehabilitation

Volume 16 - 2025 | doi: 10.3389/fneur.2025.1636017

AI-Driven Cognitive Telerehabilitation for Stroke: A Randomized Controlled Trial

Provisionally accepted
  • 1Catholic Kwandong University College of Medicine, Gangneungsi, Republic of Korea
  • 2Incheon St. Mary's Hospital, Incheon, Republic of Korea
  • 3Seosong Hospital, Incheon, Republic of Korea

The final, formatted version of the article will be published soon.

Background: Cognitive impairment is a common consequence of stroke, requiring effective rehabilit ation strategies. Telerehabilitation has emerged as a promising alternative to in-person cognitive thera py, yet existing systems often lack mechanisms for real-time personalization and engagement monito ring. This study aimed to evaluate the clinical effectiveness of a self-guided AIdriven cognitive telerehabilitation compared to a therapist-supervised rehabilitation in subacute strok e patients.In this multicenter, parallel-group, randomized controlled non-inferiority trial, 63 participa nts with cognitive impairment within six months of stroke onset were randomized 1:1 to either a selfguided AI-driven telerehabilitation group or a therapist-supervised rehabilitation group. Both groups completed 24 sessions within six weeks using the same mobile platform. The primary outcomes were cognitive function measures, including the Korean Mini-Mental State Examination-2 (K-MMSE2), Trail Making Tests (A and B), and Digit Span Tests (forward and backward), with non-inferiority for mally tested using the K-MMSE2. Secondary outcomes included functional independence, psychosoc ial measures and usability questionnaire.Results: Fifty-five participants completed the study. Both groups showed significant improvements a cross all primary cognitive measures, with no statistically significant differences between groups. No n-inferiority analysis confirmed that the self-guided AI-driven telerehabilitation was not inferior to th e therapist-supervised rehabilitation based on K-MMSE2 changes. Usability assessment among users of the cognitive rehabilitation system indicated high overall satisfaction with no serious adverse even ts reported.This study demonstrates that a self-guided AI-driven telerehabilitation can deliver cognitive improvements comparable to a therapist-supervised rehabilitation in subacute stroke patients.

Keywords: artificial intelligence, cognitive dysfunction, Mobile Applications, Stroke, telerehabilitation

Received: 27 May 2025; Accepted: 31 Jul 2025.

Copyright: © 2025 Kim, Park, Jeong, Kang and Kim. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Doo Young Kim, Incheon St. Mary's Hospital, Incheon, Republic of Korea

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.