Artificial Intelligence in Stroke Rehabilitation: A 20-Year Bibliometric Analysis of Digital Health Trends and Technologies.

The purpose of this Third Stroke Recovery and Rehabilitation Roundtable (SRRR3) was to develop consensus recommendations to address outstanding barriers for the translation of preclinical and clinical research using the non-invasive brain stimulation (NIBS) techniques Transcranial Magnetic Stimulation (TMS) and Transcranial Direct Current Stimulation (tDCS) and provide a roadmap for the integration of these techniques into clinical practice. International NIBS and stroke recovery experts (N = 18) contributed to the consensus process. Using a nominal group technique, recommendations were reached via a five-stage process, involving a thematic survey, two priority ranking surveys, a literature review and an in-person meeting. Results of our consensus process yielded five key evidence-based and feasibility barriers for the translation of preclinical and clinical NIBS research, which were formulated into five core consensus recommendations. Recommendations highlight an urgent need for (1) increased understanding of NIBS mechanisms, (2) improved methodological rigor in both preclinical and clinical NIBS studies, (3) standardization of outcome measures, (4) increased clinical relevance in preclinical animal models, and (5) greater optimization and individualization of NIBS protocols. To facilitate the implementation of these recommendations, the expert panel developed a new SRRR3 Unified NIBS Research Checklist. These recommendations represent a translational pathway for the use of NIBS in stroke rehabilitation research and practice.

Background and Aims: The purpose of this Third Stroke Recovery and Rehabilitation Roundtable (SRRR3) was to develop consensus recommendations to address outstanding barriers for the translation of preclinical and clinical research using the non-invasive brain stimulation (NIBS) techniques Transcranial Magnetic Stimulation (TMS) and Transcranial Direct Current Stimulation (tDCS) and provide a roadmap for the integration of these techniques into clinical practice. Methods: International NIBS and stroke recovery experts (N = 18) contributed to the consensus process. Using a nominal group technique, recommendations were reached via a five-stage process, involving a thematic survey, two priority ranking surveys, a literature review and an in-person meeting. Results and Conclusions: Results of our consensus process yielded five key evidence-based and feasibility barriers for the translation of preclinical and clinical NIBS research, which were formulated into five core consensus recommendations. Recommendations highlight an urgent need for (1) increased understanding of NIBS mechanisms, (2) improved methodological rigor in both preclinical and clinical NIBS studies, (3) standardization of outcome measures, (4) increased clinical relevance in preclinical animal models, and (5) greater optimization and individualization of NIBS protocols. To facilitate the implementation of these recommendations, the expert panel developed a new SRRR3 Unified NIBS Research Checklist. These recommendations represent a translational pathway for the use of NIBS in stroke rehabilitation research and practice.

I have always been passionate about my work and research in stroke rehabilitation but never truly understood where this stemmed from. Drawing upon accessible music making, my PhD research developed and trialed a novel approach for post-stroke rehabilitation: an intervention created to simultaneously address arm/hand function and well-being outcomes. The focus of the research was to empower stroke survivors with limited to no movement in their arm/hand, as this subset of survivors are generally overlooked by the medical system (due to a projected poor prognosis of recovery). In 2020, during my engagement with the PhD research, the Black Lives Matter movement was reignited in response to the death of George Floyd. As a Woman of Colour, this movement deeply impacted me and led to reflection about my personal experiences of adversity. Through deep reflection, I started to understand the impact of my adverse experiences on my passion for advocacy in stroke rehabilitation. This paper explores the impact of my complex identity on my current approach to music therapy research and advocacy in stroke rehabilitation. Positioning myself as an Australian of Indian origin, I share personal reflections about my journey to research with the intent of highlighting the importance of visibility and change in music therapy research and practice.
 
 Correction notice: An error in the year for which the Portugese rule over Goa ended is incorrect in the Version of Record (VoR) on page 5 of the PDF. The correct year is 1961, and the correct sentence should be: “Along with this, Goa, the place of my family’s origin in India, was under the rule of the Portuguese for as long as 450 years, reclaiming independence quite recently in 1961 (Kamat, 2011)”.
 Kamat, P. (2011). The Road To Liberation. Retrieved November 24, 2020 from https://timesofindia.indiatimes.com/city/goa/THE-ROAD-TO-LIBERATION/articleshow/11174565.cms

Background:Vertebral compression fractures (VCF) are a common cause of pain and disability, particularly in the aging population. Although artificial intelligence (AI) has shown promise across various medical domains, its application in VCF diagnosis and treatment remains fragmented. A comprehensive understanding of the research trends and key contributors to this field is lacking.Objective:This study aimed to map the knowledge landscape of AI applications in VCF through bibliometric analysis, identifying temporal patterns, intellectual hotspots, and influential contributors to guide future research.Methods:A total of 462 English-language articles published between 2004 and 2023 were retrieved from the Web of Science Core Collection. CiteSpace 6.2.R6 was used to perform the co-authorship, keyword co-occurrence, citation burst, and clustering analyses. Parameters such as time-slicing, g-index (k = 50), and pathfinder network scaling were applied. The key metrics included publication trends, keyword bursts, and centrality scores. Statistical trends were visualized to identify the developmental inflection points and thematic shifts.Results:The number of publications increased modestly until 2018, followed by a notable surge in 2019, which marked the rapid integration of AI-intensive learning into VCF research. Keyword analysis revealed a thematic evolution from traditional procedures (e.g., vertebroplasty) to AI-driven diagnostics and robotic-assisted interventions. “Deep learning” exhibited the strongest citation burst since 2019. Influential authors, such as Bizhan Aarabi, and institutions in the United States and China were prominent, with SPINE identified as the most frequently cited journal.Conclusion:AI technologies, especially deep learning and robot-assisted surgery, have become transformative tools in the VCF domain, enhancing diagnostic accuracy and treatment precision. This bibliometric analysis reveals a shift toward technology-driven research paradigms and highlights the critical actors and trends shaping the field. Ongoing interdisciplinary collaboration and clinical validation are essential to fully realize AI’s potential of AI in orthopedic care and improve patient outcomes.

BackgroundRobotic and artificial intelligence (AI)-assisted neurorehabilitation has emerged as a rapidly growing interdisciplinary field, integrating engineering innovations with clinical practice to enhance motor and cognitive recovery in neurological disorders. While research in this domain has expanded substantially over the last two decades, only a few bibliometric studies have examined related topics (e.g., new technologies in neurorehabilitation, rehabilitation robotics after stroke, AI in stroke care), and, to our knowledge, no study has provided a comprehensive bibliometric mapping specifically focused on robotics and artificial intelligence applications in neurorehabilitation. This study aimed to analyse the global trends, influential contributors, thematic evolution, and collaborative networks in robotic and AI-assisted neurorehabilitation.MethodsA bibliometric analysis was conducted using the Web of Science Core Collection. A comprehensive search covering 2003–2025 identified relevant articles using controlled terms for neurorehabilitation, robotics, and AI. Data were exported as plain text files (savedrecs.txt) from the Web of Science Core Collection and processed using the Bibliometrix R package via the Biblioshiny interface. Analyses included annual growth, citation performance, authorship patterns, journal impact, keyword co-occurrence, thematic mapping, and international collaboration networks.ResultsA total of 468 articles were retrieved from 191 sources, showing a rapid annual growth rate of 19.57%. The average citation per article was 24.22, with 17,792 references cited overall. Authorship analysis revealed contributions from 1,972 authors, with an average of 5.49 co-authors per paper and 32.05% international collaboration. The Journal of NeuroEngineering and Rehabilitation (h-index = 15, 1,740 citations) and Sensors (m-index = 1.714) were identified as the leading journals. The most prolific authors included Aiguo Song (8 publications) and Robert Riener (6 publications), while Marchal-Crespo L. and Reinkensmeyer D.J. were the most locally cited. Keyword analysis highlighted “stroke” (n = 93), “rehabilitation” (n = 82), “design” (n = 58), “recovery” (n = 53), and “exoskeleton” (n = 49) as dominant themes, with stroke rehabilitation and robotic exoskeletons representing core research foci. China (n = 697) and the USA (n = 251) emerged as the most productive countries, with strong collaborative ties.ConclusionRobotic and AI-assisted neurorehabilitation has demonstrated exponential growth, reflecting both technological innovation and clinical translation. Stroke rehabilitation and gait training remain central themes, while emerging areas such as AI-based assessment systems, wearable sensors, and tele-rehabilitation suggest future directions. To our knowledge, this study provides a comprehensive bibliometric overview specifically centred on robotics and artificial intelligence applications in neurorehabilitation, offering strategic insights for guiding future research and clinical integration.

The aim of this bibliometric study was to systematically map the evolution, structural characteristics and methodological profile of artificial intelligence (AI) research in endodontics by analysing publication trends, collaboration networks, thematic development and citation impact. A bibliometric analysis was conducted using publications indexed in the Web of Science Core Collection, Scopus and PubMed from 1 January 1990 to 19 August 2025. Following deduplication and eligibility screening, 245 articles were included. Authorship, country-level collaboration and keyword co-occurrence networks were analysed using VOSviewer. Citation data were harmonised across databases using regression-based normalisation. Negative binomial regression was applied to evaluate the association between citation counts and publication year, document type and open-access status. AI-related research in endodontics showed minimal activity before 2020, followed by rapid growth driven predominantly by deep learning (DL) based imaging applications. Periapical radiographs (PA) and cone-beam computed tomography (CBCT) were the most frequently used data sources. China accounted for the highest publication volume, whereas the United States demonstrated the greatest citation-weighted influence and centrality within international collaboration networks. Keyword co-occurrence analysis identified six thematic clusters, dominated by radiographic diagnostics, with a recent emergence of natural language processing and generative AI applications. Publication year was the only significant predictor of citation counts (p < 0.001); document type and open-access status were not significantly associated. AI research in endodontics has evolved into a rapidly expanding, imaging-centred research domain characterised by increasing output but limited methodological diversity, restricted use of explainable AI and inconsistent adoption of reporting guidelines. These findings provide a structured overview of the field's development and current research profile.

Cognitive impairment is an important target for rehabilitation as it is common following stroke, is associated with reduced quality of life and interferes with motor and other types of recovery interventions. Cognitive function following stroke was identified as an important, but relatively neglected area during the first Stroke Recovery and Rehabilitation Roundtable (SRRR I), leading to a Cognition Working Group being convened as part of SRRR II. There is currently insufficient evidence to build consensus on specific approaches to cognitive rehabilitation. However, we present recommendations on the integration of cognitive assessments into stroke recovery studies generally and define priorities for ongoing and future research for stroke recovery and rehabilitation. A number of promising interventions are ready to be taken forward to trials to tackle the gap in evidence for cognitive rehabilitation. However, to accelerate progress requires that we coordinate efforts to tackle multiple gaps along the whole translational pathway.

Cognitive impairment is an important target for rehabilitation as it is common following stroke, is associated with reduced quality of life and interferes with motor and other types of recovery interventions. Cognitive function following stroke was identified as an important, but relatively neglected area during the first Stroke Recovery and Rehabilitation Roundtable (SRRR I), leading to a Cognition Working Group being convened as part of SRRR II. There is currently insufficient evidence to build consensus on specific approaches to cognitive rehabilitation. However, we present recommendations on the integration of cognitive assessments into stroke recovery studies generally and define priorities for ongoing and future research for stroke recovery and rehabilitation. A number of promising interventions are ready to be taken forward to trials to tackle the gap in evidence for cognitive rehabilitation. However, to accelerate progress requires that we coordinate efforts to tackle multiple gaps along the whole translational pathway.

BackgroundDepressive disorders are clinically heterogeneous and mechanistically complex psychiatric conditions. Transcranial direct current stimulation (tDCS), a key non-invasive neuromodulation technique, has expanded rapidly in both therapeutic application and mechanistic research. However, the field is marked by rapid publication growth, thematic diversity, and variability in evidence quality. A systematic quantitative synthesis is therefore needed to map the research landscape, identify hotspots, and inform future directions.MethodsA systematic search was conducted for English-language publications in the Web of Science Core Collection (WoSCC), Scopus, and PubMed using the terms (“Transcranial direct current stimulation” OR “tDCS”) AND (“depression” OR “major depressive disorder” OR “depressive disorder” OR “MDD”). Only articles and reviews were included. Records from 2026 and non-research publications, including conference abstracts, editorials, letters, news items, and errata, were excluded. Deduplication was performed using DOI-based matching followed by title-assisted matching. Bibliometrix (R), VOSviewer, and CiteSpace were used to analyze publication trends, contributions by countries/regions, institutions, authors, and journals, collaboration networks, keyword co-occurrence, thematic clustering, and burst terms. Citation analysis was based on WoSCC data only.ResultsResearch on tDCS for depression showed sustained growth, with marked acceleration after 2020 and a peak in 2024. The United States, Germany, and Brazil occupied central positions in both productivity and international collaboration, with the United States ranking first in publication volume. Major research hubs included the Universidade de São Paulo, the University of Toronto, and Harvard University, while Brain Stimulation, Journal of Affective Disorders, and Frontiers in Psychiatry were the leading publication venues. Highly cited studies mainly focused on neurophysiological mechanisms, pivotal randomized controlled trials, and evidence-based guidelines. Keyword analyses indicated a shift from early attention to cortical excitability, safety, and short-term efficacy toward a more integrated framework involving prefrontal-targeted stimulation, cognitive function, functional connectivity, treatment outcomes, and cross-disorder applications.ConclusiontDCS research in depression is entering a multidimensional and interdisciplinary phase, with increasing emphasis on network-level mechanisms and precision intervention. Functional connectivity is emerging as a potential biomarker for patient stratification and outcome prediction. Further progress depends on multicenter standardization, reproducible analytic pipelines, and high-quality comparative effectiveness research.

Although artificial intelligence (AI) has become a powerful driver of innovation in marketing, existing research often treats its applications in predictive analytics, customer segmentation, and personalization as fragmented domains. This lack of integration limits a comprehensive understanding of how AI can shape modern marketing strategies. To address this gap, this study conducted a systematic review of 20 peer-reviewed articles published between 2020 and 2025, following PRISMA guidelines. Bibliometric techniques and thematic content analysis were employed to identify intellectual structures, citation patterns, and emerging research themes. The analysis revealed four thematic clusters: (1) AI for personalization and customer relationship management (CRM), (2) predictive analytics and strategic marketing, (3) global and supply chain applications of AI, and (4) bibliometric and conceptual foundations. Keyword and trend mapping highlighted dominant themes such as machine learning and customer behavior, while new areas of interest—including emotion AI, federated learning, and AI ethics—are gaining prominence. This review not only synthesizes dispersed literature but also provides a roadmap for future research, emphasizing explainable AI, adaptive models, ethical governance, and interdisciplinary collaboration to support responsible and innovative AI adoption in marketing.

Introduction A modern and accessible healthcare system requires digital innovation and connectivity. The term “Digital health” covers vide range technologies, such as mobile health and applications, electronic records, telehealth and telemedicine, wearable devices, robotics, virtual reality and artificial intelligence. Methods Scientometrics is the method that we have done in this study by Cite Space and VOSviewer software, and the result of searching the Web of Science database in plain text format to perform analysis and scientometrics and create outputs in the form of graphs and tables in the field of digital health has been used in stroke rehabilitation. Result A total of 2933 documents related to digital health technologies in stroke rehabilitation were identified by searching for the terms “stroke rehabilitation” or “stroke recovery” in the title and “digital health” across all fields. The strongest citations related to cerebrovascular disease spanned from 1994 to 2007, with randomised clinical trials occurring almost simultaneously and ended by 2012. Consequently, stroke rehabilitation by virtual reality technology has obtained the most citations and clinical trials and as an important part of digital health in the future research process. Conclusion This scientometric study offers insights into how digital health technology can assist stroke patients in self-managing their health and well-being, in addition to supporting integrated stroke rehabilitation. The analysis revealed that three themes were present: author contributors and collaboration networks, temporal evolution, the strongest citation explosions for digital health technologies in stroke rehabilitation research, and semantic analysis.

BackgroundCurrently, artificial intelligence (AI) has been widely used for the prediction, diagnosis, evaluation and rehabilitation of stroke. However, the quantitative and qualitative description of this field is still lacking.ObjectiveThis study aimed to summarize and elucidate the research status and changes in hotspots on the application of AI in stroke over the past 20 years through bibliometric analysis.Materials and MethodsPublications on the application of AI in stroke in the past two decades were retrieved from the Web of Science Core Collection. Microsoft Excel was used to analyze the annual publication volume. The cooperation network map among countries/regions was generated on an online platform (https://bibliometric.com/). CiteSpace was used to visualize the co-occurrence of institutions and analyze the timeline view of references and burst keywords. The network visualization map of keywords co-occurrence was generated by VOSviewer.ResultsA total of 4437 publications were included. The annual number of published documents shows an upwards trend. The USA published the most documents and has the top 3 most productive institutions. Journal of Neuroengineering and Rehabilitation and Stroke are the journals with the most publications and citations, respectively. The keywords co-occurrence network classified the keywords into four themes, that is "rehabilitation," "machine learning," "recovery" and "upper limb function." The top 3 keywords with the strongest burst strength were "arm," "upper limb" and "therapy." The most recent keywords that burst after 2020 and last until 2023 included "scores," "machine learning," "natural language processing" and "atrial fibrillation."ConclusionThe USA shows a leading position in this field. At present and in the next few years, research in this field may focus on the prediction/rapid diagnosis of potential stroke patients by using machine learning, deep learning and natural language processing.

Brain science research is considered the crown jewel of 21st-century scientific research; the United States, the United Kingdom, and Japan have elevated brain science research to a national strategic level. This study employs bibliometric analysis and knowledge graph visualization to map global trends, research hotspots, and collaborative networks in brain science, providing insights into the field's evolving landscape and future directions. We analyzed 13,590 articles (1990-2023) from the Web of Science Core Collection using CiteSpace and VOSviewer. Metrics included publication volume, co-authorship networks, citation patterns, keyword co-occurrence, and burst detection. Analytical tools such as VOSviewer, CiteSpace, and online bibliometric platforms were employed to facilitate this investigation. The United States, China, and Germany dominated research output, with China's publications rising from sixth to second globally post-2016, driven by national initiatives like the China Brain Project. However, China exhibited limited international collaboration compared to the United States and European Union. Key journals included Human Brain Mapping and Journal of Neural Engineering, while emergent themes centered on "task analysis," "deep learning," and "brain-computer interfaces" (BCIs). Research clusters revealed three focal areas: (1) Brain Exploration (e.g., fMRI, diffusion tensor imaging), (2) Brain Protection (e.g., stroke rehabilitation, amyotrophic lateral sclerosis therapies), and (3) Brain Creation (e.g., neuromorphic computing, BCIs integrated with AR/VR). Despite China's high output, its influence lagged in highly cited scholars, reflecting a "quantity-over-quality" challenge. Brain science research is in a golden period of development. This bibliometric analysis offers the first comprehensive review, encapsulating research trends and progress in brain science. It reveals current research frontiers and crucial directions, offering a strategic roadmap for researchers and policymakers to navigate countries when planning research layouts.

Data-driven trends in critical care informatics: a bibliometric analysis of global collaborations using the MIMIC database (2004-2024).

Although artificial intelligence (AI) has the potential to drive significant business innovation, many firms struggle to realize its benefits. We investigate why some firms succeed in using AI for innovation, whereas others fail, focusing on the organizational support necessary for leveraging AI in both novel and incremental innovation. Specifically, we examine how the lean startup method (LSM) influences the impact of AI on product innovation in startups. Analyzing data from 1,800 Chinese startups between 2011 and 2020, alongside policy shifts by the Chinese government in encouraging AI adoption, we find that companies with strong AI capabilities produce more innovative products. Moreover, our study reveals that AI investments complement LSM in innovation, with effectiveness varying by the type of innovation and AI capability. We differentiate between discovery-oriented AI, which reduces uncertainty in novel areas of innovation, and optimization-oriented AI, which refines and optimizes existing processes. Within the framework of LSM, we further distinguish between prototyping—focused on developing minimum viable products—and controlled experimentation—focused on rigorous testing such as A/B testing. We find that LSM complements discovery-oriented AI by utilizing AI to expand the search for market opportunities and employing prototyping to validate these opportunities, thereby reducing uncertainties and facilitating the development of the first release of products. Conversely, LSM complements optimization-oriented AI by using A/B testing to experiment with the universe of input features and using AI to streamline iterative refinement processes, thereby accelerating the improvement of iterative releases of products. As a result, when firms use AI and LSM for product development, they are able to generate more high-quality products in less time. These findings, applicable to both software and hardware development, underscore the importance of treating AI as a heterogeneous construct because different AI capabilities require distinct organizational processes to achieve optimal outcomes. This paper was accepted by D. J. Wu, Special Issue on the Human-Algorithm Connection. Funding: Financial support from the Mack Institute for Innovation Management is gratefully acknowledged. Supplemental Material: The data files are available at https://doi.org/10.1287/mnsc.2022.03905 .