Advancing Brain-Computer Interface Closed-Loop Systems for Neurorehabilitation: Systematic Review of AI and Machine Learning Innovations in Biomedical Engineering
Bibliographic record
Abstract
Background: Brain-computer interface (BCI) closed-loop systems have emerged as a promising tool in health care and wellness monitoring, particularly in neurorehabilitation and cognitive assessment. With the increasing burden of neurological disorders, including Alzheimer disease and related dementias (AD/ADRD), there is a critical need for real-time, noninvasive monitoring technologies. BCIs enable direct communication between the brain and external devices, leveraging artificial intelligence (AI) and machine learning (ML) to interpret neural signals. However, challenges such as signal noise, data processing limitations, and privacy concerns hinder widespread implementation. Objective: The primary objective of this study is to investigate the role of ML and AI in enhancing BCI closed-loop systems for health care applications. Specifically, we aim to analyze the methods and parameters used in these systems, assess the effectiveness of different AI and ML techniques, identify key challenges in their development and implementation, and propose a framework for using BCIs in the longitudinal monitoring of AD/ADRD patients. By addressing these aspects, this study seeks to provide a comprehensive overview of the potential and limitations of AI-driven BCIs in neurological health care. Methods: A systematic literature review was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, focusing on studies published between 2019 and 2024. We sourced research articles from PubMed, IEEE, ACM, and Scopus using predefined keywords related to BCIs, AI, and AD/ADRD. A total of 220 papers were initially identified, with 18 meeting the final inclusion criteria. Data extraction followed a structured matrix approach, categorizing studies based on methods, ML algorithms, limitations, and proposed solutions. A comparative analysis was performed to synthesize key findings and trends in AI-enhanced BCI systems for neurorehabilitation and cognitive monitoring. Results: The review identified several ML techniques, including transfer learning (TL), support vector machines (SVMs), and convolutional neural networks (CNNs), that enhance BCI closed-loop performance. These methods improve signal classification, feature extraction, and real-time adaptability, enabling accurate monitoring of cognitive states. However, challenges such as long calibration sessions, computational costs, data security risks, and variability in neural signals were also highlighted. To address these issues, emerging solutions such as improved sensor technology, efficient calibration protocols, and advanced AI-driven decoding models are being explored. In addition, BCIs show potential for real-time alert systems that support caregivers in managing AD/ADRD patients. Conclusions: BCI closed-loop systems, when integrated with AI and ML, offer significant advancements in neurological health care, particularly in AD/ADRD monitoring and neurorehabilitation. Despite their potential, challenges related to data accuracy, security, and scalability must be addressed for widespread clinical adoption. Future research should focus on refining AI models, improving real-time data processing, and enhancing user accessibility. With continued advancements, AI-powered BCIs can revolutionize personalized health care by providing continuous, adaptive monitoring and intervention for patients with neurological disorders.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.048 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.008 |
| Bibliometrics | 0.013 | 0.012 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".