Global trends and hotspots of artificial intelligence in pain management: A bibliometric analysis

Abstract

Objective

To systematically explore international research trends and dynamics in the interdisciplinary field of artificial intelligence (AI) and pain management over the past decade (2016-2025) and delineate current research frontiers.

Methods

Publications were retrieved from Web of Science Core Collection database and subjected to bibliometric analysis. VOSviewer, Scimago Graphica, and other tools were used for bibliometric analysis and visualization.

Results

A total of 1022 articles were included. Publication output showed an exponential upward trend overall, despite a temporary slowdown in 2022, followed by accelerated growth from 2023 onward. The United States led in global publication volume and served as the core hub of international collaborative networks, followed by China. In terms of journals, Pain published the highest number of relevant studies. Regarding authorship, Cao Rui, Wang Bin, and David Borsook emerged as the most influential scholars. Reference and keyword analyses delineate a clear evolution: early research established foundational insights into mechanisms. Mid-period work integrated AI and machine learning with multimodal tools like functional magnetic resonance imaging (fMRI) for objective assessment; recent advances have shifted toward clinical translation, focusing on precision medicine and the refinement of pain classification and assessment frameworks.

Conclusion

This study maps the evolutionary trajectory of AI research in pain management over the past decade. Future efforts should prioritize strengthening international collaboration, promoting large-scale clinical validation of AI tools, standardizing data sharing, and addressing equity in access to technology to meet unmet clinical needs in pain care.

Keywords

artificial intelligence bibliometrics citespace pain management visual analysis VOSviewer

1. Introduction

Pain management represents a complex and multifaceted clinical challenge, significantly impacting global health outcomes, patient quality of life, and socioeconomic burdens.^1,2 Traditional approaches to diagnosis, monitoring, and treatment often struggle with subjectivity, variability in patient response, and the complex, multidimensional nature of pain.^3–6 In recent years, artificial intelligence (AI) has emerged as a transformative force in healthcare, offering novel tools to decipher complex patterns from large-scale, heterogeneous data.^7–10 Within pain medicine, AI applications spanning machine learning, deep learning, and natural language processing show immense promise for objective pain assessment through multimodal data analysis, predictive modeling for personalized treatment pathways, and the optimization of interventional strategies.^11–15 This convergence has sparked a rapidly expanding body of research aimed at leveraging computational power to make pain management more precise, proactive, and effective.

Given the dynamic and interdisciplinary growth of AI in pain management, a systematic mapping of the research landscape is essential to understand its evolution, knowledge structure, and future trends. While narrative reviews have synthesized scientific findings, a quantitative, macro-level analysis is lacking.¹⁶ Bibliometrics, the statistical analysis of scientific publications, provides a powerful lens to objectively chart the development of a field.^17–20 It employs visualization techniques such as knowledge mapping, co-authorship networks, and thematic clustering to transform complex publication data into interpretable structural patterns. It can identify core research themes, influential authors and institutions, collaborative networks, emerging trends, and knowledge gaps that may not be apparent through traditional review methods.

This study therefore employs a comprehensive bibliometric approach to analyze the scholarly output at the intersection of AI and pain management. We aim to quantify and visualize the growth trajectory, key contributors, international collaboration patterns, and thematic foci of this domain over time. By examining citation networks, co-occurrence of keywords, and the evolution of research fronts, this paper provides a data-based summary of the current state of the field, identifies its foundational work, and suggests useful directions for future research and clinical practice. The findings are meant to serve as a practical reference for understanding the past, present, and potential future of AI-driven innovations in pain management.

2. Materials and methods

2.1. Data collection and search strategy

This study is a retrospective bibliometric analysis that conducted a topic search based on the Web of Science Core Collection (WOSCC) database. The search query was constructed using Boolean operators: TS= ((“pain management” OR “pain control” OR analgesia OR “chronic pain” OR “perioperative analgesia” OR “drug therapy”) AND (“artificial intelligence” OR “machine learning” OR “neural network*” OR “deep learning” OR “large language model*”)). Core and extended keywords from the two fields of artificial intelligence and pain management were selected hierarchically and combined using “OR” within groups and “AND” between groups to comprehensively cover the relevant research topics. Wildcard symbols were employed to ensure the inclusion of related terms. The search was conducted on January 21, 2026, and limited to the period from January 1, 2016, to December 31, 2025. The document types were restricted to Article and Review Article and the language to English. The duplicate articles were eliminated. The analysis parameters are summarized in Supplementary Table 1, the bibliographic records are provided in Supplementary Table 2, and the study flowchart is shown in Supplementary Figure 1.

2.2. Analysis tools

This study employs a multi-tool collaborative analysis framework, which specifically includes: CiteSpace 6.4. R1 for constructing literature co-citation networks and analyzing keyword evolution. VOSviewer 1.6.19 for constructing and visualizing collaboration networks and co-occurrence networks.^21,22 Scimago Graphica 1.0.25 for presenting country/region collaboration networks. WPS Excel 2023 and GraphPad Prism 10.1 for basic statistical analysis and chart creation.

2.2.1. Bibliometric parameter settings

The CiteSpace analysis parameters were configured as follows: (1) Time Slicing: from 2016 to 2025 (sliced in 1-year intervals); (2) Threshold Selection: g-index (k=10); (3) Network Pruning: The Pathfinder algorithm was applied to prune the network within each time slice, and then reapplied for secondary pruning after merging the networks; (4) Visualization Settings: Node diameter is proportional to the frequency of occurrence, and link width is proportional to the co-occurrence strength.

2.2.2. Collaboration and co-occurrence network analysis procedure

The VOSviewer analysis procedure included: (1) Data Preprocessing: The raw data files exported from Web of Science were saved in UTF-8 encoding format; (2) Network Construction and Layout Optimization: The network layout was optimized using the Linlog/modularity-based algorithm; (3) Node Weight Setting: Node size was set to be proportional to the number of documents or citations, with specific weighting determined according to the analysis objectives.

2.2.3. Country collaboration network visualization

Scimago Graphica was primarily used to analyze and visualize the country collaboration network. The specific operational procedure was as follows: The GML-formatted country collaboration data table exported from VOSviewer was imported into Scimago Graphica, with parameters set as follows: (1) Node labels were set as ‘Country’; (2) Node clustering was based on the country name string. In the final generated country collaboration network map, node diameter corresponds to a country’s publication volume, and line thickness corresponds to the frequency of collaboration between countries.

2.2.4. Basic statistical analysis and visualization

WPS Excel 2023 and GraphPad Prism 10.1 were primarily used to perform descriptive statistical analysis and to transform various analysis result data into charts for presentation, including doughnut charts, bar graphs, and column charts.

3. Results

3.1. Annual trends in publications and citations

The initial search yielded 1070 records. By restricting the document types to Article and Review Article and the language to English, and by eliminating duplicate articles, a total of 1022 publications was included, comprising 826 Articles and 196 Review Articles. Based on the annual publication data from 2016 to 2025 (Figure 1), research in this field demonstrates an overall trend of sustained and rapid growth. The annual number of publications increased steadily from 9 in 2016 to 121 in 2021, reflecting the field’s initial surge in widespread attention. A slight growth stagnation was observed in 2022, but since 2023, the field has entered a phase of exponential acceleration in development. Coinciding with this trend, citation counts have also risen exponentially, indicating a rapid expansion in both the scale and influence of research within this domain.

Figure 1.

Annual publication volume from 2016 to 2025.

3.2. National contributions and international collaboration network

The analysis of national contributions and international collaboration networks reveals that in the interdisciplinary field of artificial intelligence and pain management research, global scientific efforts are characterized by a collaborative landscape centered on a few developed countries with broad participation from numerous nations. Cluster analysis identified five distinct clusters spanning the globe (Figure 2(a)). Cluster 1 comprises Western European nations such as Germany, Italy, France, and Belgium, demonstrating close internal collaboration. Cluster 2 includes China, Australia, Canada, and Japan, forming a trans-Pacific cluster. Cluster 3 consists of the United Kingdom, Israel, Iran, and Austria, exhibiting unique cross-regional collaborative ties. Cluster 4 is centered on the United States, which, together with Switzerland and South Korea, forms a high-impact global collaboration. Cluster 5 includes Saudi Arabia, Denmark, and Egypt, demonstrating Middle East-Northern Europe collaboration. International collaboration in this field presents a network structure with the United States as the global hub and regional clusters as its key structural features. The United States, Europe, and the Asia-Pacific region collectively constitute the main knowledge production and collaboration zones (Figure 2(b)). In terms of publication volume within this interdisciplinary domain, the United States holds a leading position. With 377 publications, a total citation counts of 6,685, and an international collaboration strength of 192, it serves as the academic core and primary knowledge producer. China follows closely with 285 publications, ranking second. However, its total citation count (2,935) and international collaboration strength (81) still show a gap compared to the United States. Countries such as the United Kingdom, Canada, Germany, and Australia form a high-impact second tier. Although their publication volumes are relatively limited, their active openness and collaborative nature are evidenced by higher levels of international collaboration strength (Table 1). Regarding the decade-long trend in the proportional contribution of national literature output, the United States consistently held the highest share but showed a gradual declining trend. China’s proportion has continuously increased, with significant growth in the latter period. The proportions of countries like Italy and Australia remained relatively stable. Overall, this reflects the dynamic evolution of the global contribution pattern in this field (Figure 2(c)).

Figure 2.

(a) Country/region collaboration network visualization. (b) Chord diagram of country/region collaborations. (c) Distribution of publication share among the top 10 countries/regions by total publication volume.

Table 1.

The top 10 countries by total publication volume.

Rank	Country	Documents	Citations	Total link strength	Average citations
1	usa	377	6685	192	18
2	china	285	2935	81	10
3	united kingdom	63	1688	102	27
4	canada	60	1252	59	21
5	italy	60	858	47	14
6	germany	55	1407	81	26
7	australia	50	1075	75	22
8	south korea	44	471	19	11
9	india	39	389	29	10
10	spain	34	720	39	21

3.3. Research institutions and collaboration networks

Clustering analysis and visualization of the institutional collaboration network were performed using VOSviewer. The institutional collaboration network revealed a decentralized collaborative landscape in the interdisciplinary research field of artificial intelligence and pain management, predominantly led by top-tier medical research centers and comprehensive universities. Harvard Medical School occupied a central position with 38 publications, a total citation counts of 817, and a collaboration strength of 38, demonstrating strong knowledge output and collaborative research capabilities. Seven distinct clusters were identified and color-coded in the institutional collaboration network to elucidate regional cooperative relationships (Figure 4 (a)). The red cluster represents Chinese institutions: exemplified by Capital Medical University, the Chinese Academy of Sciences, Shanghai Jiao Tong University, and Sichuan University, forming an independent and internally tightly connected Chinese research network. The green cluster includes King’s College London, University of Oxford, University of Zurich, and ETH Zurich, also connecting with New York University and the University of Pittsburgh, forming a high-level transatlantic collaborative link. The blue cluster includes mainly US eastern institutions, consisting of Brown University, Yale University, University of Pennsylvania, and several American public research universities. The yellow cluster is the north American research group: centered on Johns Hopkins University and Duke University, collaborating with Canadian institutions like the University of Toronto, McGill University, and University Health Network. The purple cluster is the Australian University Alliance: including The University of Sydney, The University of Melbourne, and The University of Queensland, forming a regional collaborative system. The cyan cluster is centered on Stanford University, the University of California system, and the University of Washington. The orange cluster is the US medical cluster: with Harvard Medical School, Massachusetts General Hospital, Mayo Clinic, and Boston Children’s Hospital at its core, forming a high-quality clinical pain research cluster. Among the top ten institutions by publication volume, seven are from the United States, two from Canada, and one from China (Figure 3(b)). All top ten institutions by citation count are located in the United States and Canada, indicating their relatively high academic influence in the interdisciplinary field of pain management and artificial intelligence research (Figure 3(c)).

Figure 3.

(a) Institutional collaboration network visualization. (b) Top 10 research institutions by publication volume. (c) Top 10 research institutions by citation count.

3.4. Journal publication and citation analysis

Literature in the interdisciplinary field of artificial intelligence and pain management is widely distributed across multiple clusters of specialized journals in pain medicine, neuroscience, and medical informatics, demonstrating a distinct interdisciplinary nature. Both specialized and comprehensive journals collectively form the knowledge dissemination system for this field (Figure 4(a)). The distribution of publication volume and influence is uneven. Among these, the journal Pain holds a central position in terms of publication volume, total citation count, and collaboration network strength. The top ten journals by publication volume primarily consist of specialized pain medicine journals and comprehensive open-access journals. Pain (43 articles) and Scientific Reports (41 articles) are the two journals publishing the most relevant literature. The Impact Factors of these journals range from 2.3 to 6.0, indicating that research outputs in this field are published across platforms with varying levels of academic influence (Figure 4(b)). The top ten journals by citation count reflect the main sources of high-impact knowledge in this domain. Pain leads significantly with 1,250 citations, underscoring its academic standing as the flagship journal in the field. Most of the highly cited journals are ranked in JCR Q1 or Q2, suggesting that high-quality research tends to be published in journals with relatively higher impact (Figure 4(c)).

Figure 4.

(a) Journal co-publication/collaboration network visualization. (b) Impact factors of the top 10 journals by publication volume. (c) JCR quartile distribution of the top 10 journals by citation count.

3.5. Author collaboration networks and analysis of academic influence

Analysis of the author collaboration network in this field reveals a pattern characterized by broad distribution and multiple cores, indicating that research efforts are relatively decentralized and no single, overwhelmingly dominant core author group has yet emerged. Certain authors demonstrate high collaboration intensity. For instance, Kong, Jian and Liang, Fan-Rong, acting as hubs within their respective teams, coordinate several internally cohesive research groups (Figure 5(a)). The most prolific authors and the most influential authors, in terms of citations, are not entirely the same. The author with the highest publication volume is Cascella, Marco (10 articles) (Figure 5(b)), while the authors with the highest total citation counts are Cao, Rui (360 citations), Wang, Bin (311 citations), and Borsook, David (303 citations) (Figure 5(c)).

Figure 5.

(a) Author collaboration network visualization. (b) Top 10 authors by publication volume. (c) Top 10 authors by total citation count.

3.6. Keyword clustering and research focus evolution

Based on bibliometric data, the thematic structure and evolutionary trajectory of research on artificial intelligence in pain management through keyword clustering, analysis of burst strength, and timeline mapping were systematically unveiled. The co-occurrence clustering analysis identified 9 distinct thematic clusters within the research landscape (Figure 6(a)). These clusters are: #0 immune system, #1 chronic pain, #2 machine learning, #3 functional connectivity, #4 osteoarthritis, #5 neural networks, #6 Parkinson’s disease, #7 low back pain, and #8 artificial intelligence. The top 20 keywords with the strongest citation bursts in the field illustrate the temporal evolution of research focus (Figure 6(b)). Keywords such as brain (strength = 7.07, 2016–2019) and functional connectivity (strength = 5.29, 2016–2021) emerged as foundational topics in the early period. The subsequent introduction of technical terms like classification (strength = 7.17, 2017–2020) and fmri (functional magnetic resonance imaging, strength = 3.12, 2017–2021) reflected the growing integration of computational and neuroimaging approaches. In more recent years, there has been a shift toward clinical and public health themes, evidenced by the appearance of precision medicine (strength = 3.07, 2022–2023), pain assessment (strength = 3.52, 2022–2023), and prevalence (strength = 4.06, 2021–2025), indicating a trend toward translational and population-based research. The timeline view of the nine research clusters and their associated keywords illustrates the distinct evolutionary pathways of each research focus (Figure 6(c)). Early studies were mainly centered on chronic pain, functional connectivity, neuropathic pain, and low back pain, with keywords such as “brain,” “stimulation,” and “connectivity” suggesting an initial emphasis on neurobiological mechanisms. Around 2020, the research focus showed an increasing orientation toward predictive and management-related applications, as reflected by terms including “model,” “outcome,” “prediction,” “quality of life,” and “validation.” More recent keywords, such as “prevalence,” “modulation,” “health,” and “cancer pain,” suggest an expansion toward population-level assessment, disease-specific pain conditions, and clinically relevant applications.

Figure 6.

(a) Keyword cluster map based on co-occurrence network analysis. (b) Top 20 keywords with the strongest citation bursts. (c) Timeline visualization of keyword evolution within major clusters.

3.7. Co-citation relationships and burst characteristics of high-impact literature

Through co-citation analysis of the references, this study identified the knowledge base and key seminal literature within the field (Figure 7(a)). Highly cited references constitute the consensus knowledge foundation of the domain^1,16,23–30 (Table 2). Among these, the revision of the International Association for the Study of Pain (IASP) definition of pain by Raja SN et al. (2020)²³ and the perspective on the application of machine learning in pain research by Lötsch J et al. (2018)²⁴ are the two most widely influential publications. Furthermore, articles by Davis KD (2020)²⁵ and Cohen SP (2021)¹ provided important theoretical frameworks for the field from the perspectives of biomarker development and clinical practice, respectively, while the scoping review by Zhang MN (2023)¹⁶ on AI models for pain assessment and management represents a key technical publication that has rapidly gained attention in recent years. References with high betweenness centrality reveal knowledge hubs that connect different research directions^{16,24,31–38} (Table 3). The review on machine learning in pain medicine by Matsangidou M (2021)³¹ has the highest centrality (0.38), suggesting that this paper represents a key node that facilitates the development of the new technology and influences subsequent research developments. Robinson ME (2015)³² employed machine learning to demonstrate the superior diagnostic validity of subjective pain reports compared to neuroimaging, suggesting that an over-reliance on AI applications should be approached with caution. The presence of Lötsch J (2018)²⁴ and Zhang MN (2023)¹⁶ in both the high-citation and high-centrality lists is a sign of their key role as central, influential hubs that continue to shape the field.

Figure 7.

(a) Co-citation network of highly cited references. (b) Thematic research areas revealed by co-citation cluster analysis. (c) Top 20 references with the strongest citation bursts and their active time periods.

Table 2.

The top 10 most frequently cited references.

Rank	Author	Year	Citations	Journal	Doi
1	Raja, Srinivasa N.	2020	34	PAIN	10.1097/j.pain.0000000000001939
2	Loetsch, Joern	2018	31	PAIN	10.1097/j.pain.0000000000001118
3	Davis KD	2020	19	NAT REV NEUROL	10.1038/s41582-020-0362-2
4	Cohen SP	2021	19	LANCET	10.1016/S0140-6736(21)00393-7
5	Treede RD	2019	17	PAIN	10.1097/j.pain.0000000000001384
6	Zhang MN	2023	17	J AM MED INFORM ASSN	10.1093/jamia/ocac231
7	Werner P	2022	15	IEEE T AFFECT COMPUT	10.1109/TAFFC.2019.2946774
8	Hashimoto DA	2020	15	ANESTHESIOLOGY	10.1097/ALN.0000000000002960
9	Cascella M	2023	14	PAIN RES MANAG	10.1155/2023/6018736
10	Lee J	2019	13	PAIN	10.1097/j.pain.0000000000001417

Table 3.

The top 10 references in terms of centrality.

Rank	Author	Year	Centrality	Journal	Doi
1	Matsangidou M	2021	0.38	PAIN THER	10.1007/s40122-021-00324-2
2	Robinson ME	2015	0.34	J PAIN	10.1016/j.jpain.2015.02.002
3	Lötsch J	2018	0.27	PAIN	10.1097/j.pain.0000000000001118
4	Zhang MN	2023	0.25	J AM MED INFORM ASSN	10.1093/jamia/ocac231
5	Tighe PJ	2015	0.24	PAIN MED	10.1111/pme.12713
6	Miettinen T	2021	0.2	PAIN	10.1097/j.pain.0000000000002002
7	Levitt J	2020	0.18	NEUROIMAGE	10.1016/j.neuroimage.2020.117256
8	Adams MCB	2023	0.17	REGION ANESTH PAIN M	10.1136/rapm-2023-104526
9	van der Miesen MM	2019	0.16	PAIN REP	10.1097/PR9.0000000000000751
10	Wager TD	2013	0.15	NEW ENGL J MED	10.1056/NEJMoa1204471

The co-citation cluster analysis reveals 12 distinct thematic research clusters within the field, which include: #0 emotional contagion, #1 sickle cell disease, #2 EEG, #3 electrocardiography, #4 automatic pain assessment, #5 irritable bowel syndrome, #6 spinal cord stimulation, #7 fMRI, #8 empathic pain, #9 pain assessment, #10 non-pharmacological treatment, and #11 analgesics (Figure 7(b)). Burst detection analysis of the references clearly illustrates the evolution of the field’s knowledge focus^{23,24,30–32,34,37–50} (Figure 7(c)). The early foundation of the field was primarily established through research on the neural mechanisms of pain, exemplified by influential studies such as Wager TD’s work³⁸ on fMRI-based neurologic signatures of pain and Woo CW’s investigation³⁹ into constructing improved biomarkers by translating brain models from neuroimaging, alongside key neuroscience reviews by Bushnell MC⁴⁰ and Kucyi A.⁴¹ After 2019, while exploration into pain mechanisms continued, the focus began shifting toward AI-assisted diagnosis and characterization of pain-related conditions. This transition is reflected in studies such as López-Solà M’s⁴² Investigation into the neurophysiological signatures of fibromyalgia, van der Miesen MM’s³⁷ review on neuroimaging-based pain biomarkers, Lee J’s³⁰ machine learning approach to clinical pain prediction using multimodal neuroimaging and autonomic indicators, and Chu YQ’s⁴³ method for measuring pain intensity based on physiological signals. Recent burst references (2022–2025) further concentrate on reflections and updates regarding pain definitions, classifications, and clinical guidelines, as represented by Raja SN’s²³ revised IASP definition of pain and Yong RJ’s⁴⁴ commentary on prevalence of chronic pain. This evolution highlights the field’s ongoing reconstruction of clinical practice frameworks, driven by the continuous integration of advanced technologies.

4. Discussion

Pain, as defined by the International Association for the Study of Pain (IASP), is “an aversive sensory and emotional experience associated with, or resembling that associated with, actual or potential tissue damage.”.²³ Chronic pain alone affects 11-40% of the global population, imposing substantial personal suffering and socioeconomic burdens.^47,51 Its etiologies are diverse, ranging from musculoskeletal conditions such as osteoarthritis to autoimmune diseases.^52,53 The development and modulation of pain constitute a complex physiological process that involves peripheral nerves, the central nervous system, as well as emotional and cognitive factors.^1,54 Current therapeutic interventions are often limited by significant inter-individual variability in response, notable side effects, and the complex multidimensional mechanisms underlying chronic pain.⁵⁵ In recent years, deepened understanding of pain neurobiology, immune interactions, and psychosocial factors has driven a shift in pain management from empirical, standardized treatment towards personalized and precision medicine.⁵⁶ Within this context, the rise of AI technology provides unprecedented tools to decipher the heterogeneity and complexity of pain. By mining multidimensional data, identifying biomarkers, predicting treatment responses, and optimizing clinical decision-making, AI is propelling pain management into a new, data-driven era.

Over the past decade, research at the intersection of AI and pain management has exhibited near-exponential growth in both publication and citation counts. A brief stagnation observed in 2022 is likely attributable to a pandemic-related slowdown in global research activity.^57–59 This phenomenon indicates the emergence of AI in pain management as a rapidly evolving area, which not only reflects the interdisciplinary recognition of AI’s transformative potential in addressing unmet clinical needs in pain care but also signals a shift toward more data-driven and personalized approaches in the field.

At the national level, the global research landscape is characterized by a collaborative network centered on developed economies, with the United States, Europe, and the Asia-Pacific region as core knowledge production hubs. The United States leads with the highest publications and total citations, and robust international collaboration, solidifying its position as the academic anchor, likely driven by robust funding for digital health, advanced medical informatics infrastructure, and interdisciplinary research ecosystems. China ranks second in total output and exhibits the most rapid growth trajectory. Not only is there a competitive trend between China and the United States in the field of AI, but it is also consistent in the AI application field of pain management. Although the number of articles published in China is gradually increasing, its influence is still insufficient. To elevate its global scientific influence, China needs to enhance cross-border partnerships, share high-quality clinical data, and participate more actively in global consensus-building to elevate its scientific influence. Countries including the United Kingdom, Canada, and Germany form a high-impact second tier, leveraging smaller publication volumes to drive impact through open collaboration and translational research.

The institutional collaboration network exhibits a decentralized yet interconnected structure, dominated by top-tier medical research centers and comprehensive universities. Harvard Medical School stands out as a central node, reflecting the critical role of interdisciplinary hubs in integrating AI expertise, clinical pain management, and neuroscience. The emergence of prominent Chinese institutional clusters, such as Capital Medical University, the Chinese Academy of Sciences, and Shanghai Jiao Tong University, foregrounds a collaboration network that remains primarily domestically centered, while transatlantic and trans-Pacific clusters demonstrate the global nature of AI-driven pain research. Notably, seven of the top ten institutions by publication volume and all top ten by citation count are from North America, underscoring the region’s current leadership in driving high-impact, translational research. This distribution also highlights the need for greater institutional collaboration between established hubs and emerging research powerhouses to accelerate knowledge exchange.

Journal distribution highlights the strongly interdisciplinary nature of the field. Research outputs are concentrated in flagship pain medicine journals such as Pain and also widely disseminated in multidisciplinary comprehensive journals like Scientific Reports. Highly cited literature is primarily found in JCR Q1/Q2 journals, indicating that high-quality research tends to be published in platforms with greater influence, ensuring the authority and dissemination efficiency of domain knowledge. This trend also underscores the importance of interdisciplinary journals in facilitating cross-domain dialogue between artificial intelligence and clinical pain management. The decentralized, multi-core structure of the author collaboration network reflects the emergent, interdisciplinary nature of AI in pain management, with no single group yet dominating. This suggests the field is currently being shaped by diverse perspectives and methodologies from various research teams. A notable divergence exists between productive output and scholarly influence, with Cascella, Marco being the most prolific author, while Cao, Rui and Wang, Bin lead in total citations.

Through co-occurrence, clustering, and burst analysis of keywords and references, this study clearly delineates the evolution of research hotspots and frontiers. Early research primarily focused on elucidating the neuroscientific foundations and mechanisms of pain. Utilizing technologies such as fMRI, investigations centered on “brain” activity and “functional connectivity,” aiming to identify objective biomarkers of pain, thereby establishing a firm scientific foundation for subsequent studies. Subsequently, the research emphasis shifted toward the integration of technological methodologies. The adoption of AI methods such as machine learning to analyze multimodal data including neuroimaging and physiological signals for clinical pain prediction and assessment marked a pivotal turn, positioning artificial intelligence and computational analytics as essential tools for parsing complex pain-related data and aiding in objective diagnosis and evaluation. In recent years, cutting-edge research has deeply converged on clinical integration and application. This involves not only tailoring approaches to specific disease contexts but also prompting a critical reassessment and updating of the fundamental definition of pain, its classification standards, and clinical management guidelines, with an increased focus on multidimensional patient outcomes. This intellectual trajectory underscores the field’s evolution from pure mechanistic exploration toward leveraging advanced technologies to empower clinical practice, with the overarching goal of constructing a multidimensional (encompassing physiological, psychological, and social aspects) integrated precision pain management system. The keyword analysis delineates a thematic landscape comprising nine distinct clusters, spanning from broad methodological foundations (#2 machine learning, #8 artificial intelligence) and neurobiological mechanisms (#0 immune system, #3 functional connectivity) to specific pain conditions (#4 osteoarthritis, #6 Parkinson’s disease, #7 low back pain). The 12 research clusters identified through co-citation cluster analysis form a profound complement to the keyword cluster analysis. Among them, the automatic pain assessment and pain assessment clusters constitute the core of intelligent evaluation, resonating with methodological foundations such as machine learning and artificial intelligence, thereby highlighting the central logic of technology-driven innovation in pain management. The EEG, electrocardiography, and fMRI clusters establish a supporting framework of neurophysiological detection technologies, providing objective physiological data for intelligent algorithms and deeply intersecting with research on neurobiological mechanisms like functional connectivity. Emotional contagion and empathic pain introduce an affective-psychological dimension. The spinal cord stimulation, non-pharmacological treatment, and analgesics clusters construct a multi-dimensional intervention system, revealing the field’s evolution from AI-powered pain assessment towards treatment optimization. This illustrates the field’s developmental trajectory from preliminary technological application towards advancing precision pain management through the integration of physiological and psychological dimensions.

In the context of pain management, AI tools such as ChatGPT, along with online platforms like YouTube, have increasingly become accessible sources of health-related information for patients seeking preliminary guidance or supplementary information.^60–64 This trend was further accelerated by the COVID-19 pandemic, which drove patients and health professionals toward digital resources.^65,66 These digital resources offer easily accessible health content, yet their reliability and readability often vary significantly. Consequently, patients may encounter incomplete or misleading information that could influence treatment expectations and decision-making.^66–69 Its independent use as a primary source of patient information or within clinical decision-making processes is not appropriate. In critical domains such as risk-benefit assessment, individualized recommendations, and recognition of red flags, AI-generated responses tend to remain superficial when compared with established clinical guidelines.⁶⁸ Leveraging AI to evaluate, summarize, and personalize online health information represents a promising direction to bridge the gap between patient self-education and evidence-based clinical practice.^70,71

Despite significant progress, the field faces several critical challenges that must be addressed to realize its full clinical potential. First, clinical validation remains a major bottleneck. While many AI models demonstrate promise in proof-of-concept studies, few have undergone rigorous, large-scale, multicenter trials to prove their reliability and generalizability across diverse patient populations. Second, the development of robust AI tools is constrained by data limitations. Model training requires large, high-quality datasets, yet progress is hindered by data heterogeneity, strict privacy regulations, and the overall scarcity of well-curated clinical data, which limits the performance and applicability of existing algorithms. Third, there is a notable imbalance in research focus. Current efforts predominantly target chronic pain conditions such as osteoarthritis and low back pain, while acute and subacute pain scenarios such as postoperative pain, trauma-related pain, or perioperative pain receive comparatively less attention, leaving gaps in the management of the pain. Fourth, persistent interdisciplinary communication gaps slow translational progress. AI specialists often lack deep clinical context, while pain clinicians may have limited understanding of AI methodologies, hindering the co-development of clinically relevant and technically sound solutions.

The field of AI and pain management has experienced rapid growth over the past decade, driven by technological advancements, unmet clinical needs, and global investment in digital health. However, addressing challenges related to clinical validation, data sharing, imbalanced research focus will be critical to realizing AI’s full potential in transforming pain care. Future research should prioritize large-scale, real-world validation of AI models, development of standardized data repositories, the expansion of applications to acute and subacute pain, and interdisciplinary training programs to bridge the gap between technology and clinical practice. By addressing these priorities, AI has the potential to revolutionize pain assessment, personalize treatment strategies, and improve the quality of life for millions of pain patients worldwide.

This bibliometric analysis offers a comprehensive and up-to-date overview of the evolving landscape at the intersection of AI and pain management. This approach not only delineates the thematic structure of the field, but also traces the dynamic evolution of research frontiers, from early mechanistic exploration to current clinical integration and precision pain management. Furthermore, by mapping collaborative networks at the national, institutional, and author levels, the study identifies core knowledge hubs and prevailing collaborative patterns, while highlighting notable disparities between research output and scholarly influence. This analysis offers insights into the future development of this field. However, this study has several limitations inherent to bibliometric analysis. First, the data were sourced exclusively from the WOSCC database. While comprehensive, this may not encompass all relevant literature published in regional databases or in journals not indexed by WOSCC, potentially introducing selection bias and limiting the completeness of the analysis. Second, the inclusion criteria were restricted to literature published in English, which may introduce language bias and exclude relevant studies published in other languages. Third, as a bibliometric study, this analysis focuses on quantitative trends and visible academic networks; it does not assess the quality, clinical validity, or methodological robustness of the individual studies included.

5. Conclusion

This study uses bibliometric methods to analyze research on AI in pain management from 2016 to 2025, systematically mapping the field’s current landscape, core hotspots, and developmental trends. The findings offer insights for optimizing pain management strategies and identifying key research directions. Over the past decade, global interest in this interdisciplinary research has grown exponentially. The field of AI and pain management has undergone a clear evolution, advancing from an initial neuro-mechanistic exploration phase, through a period of technology-driven integration where AI enabled objective assessment from multimodal data, to the current frontier of clinical-systemic translation, which is focused on refining diagnostic frameworks and progressing toward a multidimensional, precision medicine paradigm. In recent years, AI has emerged as a promising new strategy for pain management, enhancing the potential for personalized care and improved patient outcomes. However, issues such as clinical validation of AI tools, data standardization, and extended application require further investigation to maximize their clinical value while addressing practical challenges, thereby providing pain patients with safer and more effective care options.

Supplemental material

Supplemental material - Global trends and hotspots of artificial intelligence in pain management: A bibliometric analysis

Supplemental material for Global trends and hotspots of artificial intelligence in pain management: A bibliometric analysis by Yi-fei Wang, Liang-jie Ma, Yu-xin Han, Guang-yao Chen, and Xiao Ma in DIGITAL HEALTH.

Supplemental material

Supplemental material - Global trends and hotspots of artificial intelligence in pain management: A bibliometric analysis

Supplemental material

Supplemental material - Global trends and hotspots of artificial intelligence in pain management: A bibliometric analysis

Footnotes

Acknowledgements

The authors have no acknowledgements to declare.

ORCID iDs

Yi-fei Wang

Liang-jie Ma

Yu-xin Han

Guang-yao Chen

Xiao Ma

Author contributions

Yi-fei Wang interpreted the results and drafted the original manuscript. Liang-jie Ma collected the data and performed data analysis. Yu-xin Han prepared the visualizations. Guang-yao Chen critically revised the manuscript for important intellectual content. Xiao Ma conceived and designed the study.

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Guarantor

Xiao Ma

Supplemental material

Supplemental material for this article is available online.

References

Cohen

Vase

Hooten

. Chronic pain: an update on burden, best practices, and new advances. Lancet 2021; 397(10289): 2082–2097. https://doi.org/10.1016/S0140-6736(21)00393-7

Barke

Korwisi

Jakob

, et al. Classification of chronic pain for the International Classification of Diseases (ICD-11): results of the 2017 international World Health Organization field testing. Pain 2022; 163(2): e310–e318. https://doi.org/10.1097/j.pain.0000000000002287

Savoy

. Systems-Based Practice in Chronic Pain Management. Prim Care 2022; 49(3): 485–496. https://doi.org/10.1016/j.pop.2022.01.004

Stanaway

Campbell

. The complexity of disparities in pain. Pain 2022; 163(9): 1651–1652. https://doi.org/10.1097/j.pain.0000000000002575

Ismail

Curfman

Park

, et al. Optimizing Photoneuromodulation Techniques to Evaluate the Role of Green Light-Emitting Diodes in Pain Management. J Vis Exp 2025; 28: 217. https://doi.org/10.3791/67821

Ozduran

Hanci

Erkin

. Evaluating the readability, quality and reliability of online patient education materials on chronic low back pain. Natl Med J India 2024; 37(3): 124–130. https://doi.org/10.25259/NMJI_327_2022

Eliwa

EHI

Mohamed El Koshiry

Abd El-Hafeez

, et al. Secure and Transparent Lung and Colon Cancer Classification Using Blockchain and Microsoft Azure. Adv Respir Med 2024; 92(5): 395–420. https://doi.org/10.3390/arm92050037

Eliwa

EHI

Abd El-Hafeez

. Particle swarm optimization framework for Parkinson's disease prediction. PeerJ Comput Sci 2025; 11: e3135. https://doi.org/10.7717/peerj-cs.3135

Mostafa

Mahmoud

Abd El-Hafeez

, et al. The power of deep learning in simplifying feature selection for hepatocellular carcinoma: a review. BMC Med Inform Decis Mak 2024; 24(1): 287. https://doi.org/10.1186/s12911-024-02682-1

10.

Abdel Hady

Mabrouk

Abd El-Hafeez

. Employing machine learning for enhanced abdominal fat prediction in cavitation post-treatment. Sci Rep 2024; 14(1): 11004. https://doi.org/10.1038/s41598-024-60387-x

11.

A Abdel Hady

Abd El-Hafeez

. Utilizing machine learning to analyze trunk movement patterns in women with postpartum low back pain. Sci Rep 2024; 14(1): 18726. https://doi.org/10.1038/s41598-024-68798-6

12.

Fouad

Mahfouz

Mohamed

, et al. Classification of musculoskeletal pain using machine learning. Sci Rep 2025; 15(1): 27158. https://doi.org/10.1038/s41598-025-12049-9

13.

Mabrouk

Hady

DAA

Abd El-Hafeez

. Machine learning insights into scapular stabilization for alleviating shoulder pain in college students. Sci Rep 2024; 14(1): 28430. https://doi.org/10.1038/s41598-024-79191-8

14.

Antel

Whitelaw

Gore

, et al. Moving towards the use of artificial intelligence in pain management. Eur J Pain 2025; 29(3): e4748. https://doi.org/10.1002/ejp.4748

15.

Jayakumar

Moore

Furlough

, et al. Comparison of an Artificial Intelligence-Enabled Patient Decision Aid vs Educational Material on Decision Quality, Shared Decision-Making, Patient Experience, and Functional Outcomes in Adults With Knee Osteoarthritis: A Randomized Clinical Trial. JAMA Netw Open 2021; 4(2): e2037107. https://doi.org/10.1001/jamanetworkopen.2020.37107

16.

Zhang

Zhu

Lin

, et al. Using artificial intelligence to improve pain assessment and pain management: a scoping review. J Am Med Inform Assoc 2023; 30(3): 570–587. https://doi.org/10.1093/jamia/ocac231

17.

Chen

Yan

Wang

, et al. Rheumatoid Arthritis and Fibromyalgia Syndrome: A Bibliometric and Bioinformatics Perspective on Comorbidity Research. J Multidiscip Healthc 2025; 18: 6811–6827. https://doi.org/10.2147/JMDH.S547111

18.

Deacon

Keezer

. The performance of bibliometric analyses in the health sciences. Curr Med Res Opin 2024; 40(1): 97–101. https://doi.org/10.1080/03007995.2023.2281503

19.

Bagcier

Yurdakul

Ozduran

. Top 100 cited articles on ankylosing spondylitis. Reumatismo 2021; 72(4): 218–227. https://doi.org/10.4081/reumatismo.2020.1325

20.

Zhao

Chen

Fang

. Research Trends of Rheumatoid Arthritis and Depression from 2019 to 2023: A Bibliometric Analysis. J Multidiscip Healthc 2024; 17: 4465–4474. https://doi.org/10.2147/JMDH.S478748

21.

Arruda

Silva

Lessa

, et al. VOSviewer and Bibliometrix. J Med Libr Assoc 2022; 110(3): 392–395. https://doi.org/10.5195/jmla.2022.1434

22.

van Eck

Waltman

. Software survey: VOSviewer, a computer program for bibliometric mapping. Scientometrics 2010; 84(2): 523–538. https://doi.org/10.1007/s11192-009-0146-3

23.

Raja

Carr

Cohen

, et al. The revised International Association for the Study of Pain definition of pain: concepts, challenges, and compromises. Pain 2020; 161(9): 1976–1982. https://doi.org/10.1097/j.pain.0000000000001939

24.

Lötsch

Ultsch

. Machine learning in pain research. Pain 2018; 159(4): 623–630. https://doi.org/10.1097/j.pain.0000000000001118

25.

Davis

Aghaeepour

Ahn

, et al. Discovery and validation of biomarkers to aid the development of safe and effective pain therapeutics: challenges and opportunities. Nat Rev Neurol 2020; 16(7): 381–400. https://doi.org/10.1038/s41582-020-0362-2

26.

Treede

Rief

Barke

, et al. Chronic pain as a symptom or a disease: the IASP Classification of Chronic Pain for the International Classification of Diseases (ICD-11). Pain 2019; 160(1): 19–27. https://doi.org/10.1097/j.pain.0000000000001384

27.

Werner

Lopez-Martinez

Walter

, et al. Automatic Recognition Methods Supporting Pain Assessment: A Survey. IEEE Transactions on Affective Computing 2022; 13(1): 530–552. https://doi.org/10.1109/TAFFC.2019.2946774

28.

Hashimoto

Witkowski

Gao

, et al. Artificial Intelligence in Anesthesiology: Current Techniques, Clinical Applications, and Limitations. Anesthesiology 2020; 132(2): 379–394. https://doi.org/10.1097/ALN.0000000000002960

29.

Cascella

Schiavo

Cuomo

, et al. Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives. Pain Res Manag 2023; 2023: 6018736. https://doi.org/10.1155/2023/6018736

30.

Lee

Mawla

Kim

, et al. Machine learning-based prediction of clinical pain using multimodal neuroimaging and autonomic metrics. Pain 2019; 160(3): 550–560. https://doi.org/10.1097/j.pain.0000000000001417

31.

Matsangidou

Liampas

Pittara

, et al. Machine Learning in Pain Medicine: An Up-To-Date Systematic Review. Pain Ther 2021; 10(2): 1067–1084. https://doi.org/10.1007/s40122-021-00324-2

32.

Robinson

O'Shea

Craggs

, et al. Comparison of machine classification algorithms for fibromyalgia: neuroimages versus self-report. J Pain 2015; 16(5): 472–477. https://doi.org/10.1016/j.jpain.2015.02.002

33.

Tighe

Harle

Hurley

, et al. Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain. Pain Med 2015; 16(7): 1386–1401. https://doi.org/10.1111/pme.12713

34.

Miettinen

Mäntyselkä

Hagelberg

, et al. Machine learning suggests sleep as a core factor in chronic pain. Pain 2021; 162(1): 109–123. https://doi.org/10.1097/j.pain.0000000000002002

35.

Levitt

Edhi

Thorpe

, et al. Pain phenotypes classified by machine learning using electroencephalography features. Neuroimage 2020; 223: 117256. https://doi.org/10.1016/j.neuroimage.2020.117256

36.

Adams

MCB

Nelson

Narouze

. Daring discourse: artificial intelligence in pain medicine, opportunities and challenges. Reg Anesth Pain Med 2023; 48(9): 439–442. https://doi.org/10.1136/rapm-2023-104526

37.

van der Miesen

Lindquist

Wager

. Neuroimaging-based biomarkers for pain: state of the field and current directions. Pain Rep 2019; 4(4): e751. https://doi.org/10.1097/PR9.0000000000000751

38.

Wager

Atlas

Lindquist

, et al. An fMRI-based neurologic signature of physical pain. N Engl J Med 2013; 368(15): 1388–1397. https://doi.org/10.1056/NEJMoa1204471

39.

Woo

Chang

Lindquist

, et al. Building better biomarkers: brain models in translational neuroimaging. Nat Neurosci 2017; 20(3): 365–377. https://doi.org/10.1038/nn.4478

40.

Bushnell

Ceko

Low

. Cognitive and emotional control of pain and its disruption in chronic pain. Nat Rev Neurosci 2013; 14(7): 502–511. https://doi.org/10.1038/nrn3516

41.

Kucyi

Davis

. The dynamic pain connectome. Trends Neurosci 2015; 38(2): 86–95. https://doi.org/10.1016/j.tins.2014.11.006

42.

López-Solà

Woo

Pujol

, et al. Towards a neurophysiological signature for fibromyalgia. Pain 2017; 158(1): 34–47. https://doi.org/10.1097/j.pain.0000000000000707

43.

Chu

Zhao

Han

, et al. Physiological Signal-Based Method for Measurement of Pain Intensity. Front Neurosci 2017; 11: 279. https://doi.org/10.3389/fnins.2017.00279

44.

Yong

Mullins

Bhattacharyya

. Prevalence of chronic pain among adults in the United States. Pain 2022; 163(2): e328–e332. https://doi.org/10.1097/j.pain.0000000000002291

45.

Davis

Flor

Greely

, et al. Brain imaging tests for chronic pain: medical, legal and ethical issues and recommendations. Nat Rev Neurol 2017; 13(10): 624–638. https://doi.org/10.1038/nrneurol.2017.122

46.

Misra

Wang

Archer

, et al. Automated classification of pain perception using high-density electroencephalography data. J Neurophysiol 2017; 117(2): 786–795. https://doi.org/10.1152/jn.00650.2016

47.

Dahlhamer

Lucas

Zelaya

, et al. Prevalence of Chronic Pain and High-Impact Chronic Pain Among Adults - United States, 2016. MMWR Morb Mortal Wkly Rep 2018; 67(36): 1001–1006. https://doi.org/10.15585/mmwr.mm6736a2

48.

Mouraux

Iannetti

. The search for pain biomarkers in the human brain. Brain 2018; 141(12): 3290–3307. https://doi.org/10.1093/brain/awy281

49.

Bargshady

Zhou

Deo

, et al. Ensemble neural network approach detecting pain intensity from facial expressions. Artif Intell Med 2020; 109: 101954. https://doi.org/10.1016/j.artmed.2020.101954

50.

Nickel

Tiemann

, et al. Brain dysfunction in chronic pain patients assessed by resting-state electroencephalography. Pain 2019; 160(12): 2751–2765. https://doi.org/10.1097/j.pain.0000000000001666 Erratum in: Pain. 2020 Jul 1;161(7):1684. doi: 10.1097/j.pain.0000000000001948.

51.

Fayaz

Croft

Langford

, et al. Prevalence of chronic pain in the UK: a systematic review and meta-analysis of population studies. BMJ Open 2016; 6(6): e010364. https://doi.org/10.1136/bmjopen-2015-010364

52.

Chen

, et al. AMPK signaling in osteoarthritis: from mechanisms to targeted therapeutics. Front Pharmacol 2025; 16: 1681610. https://doi.org/10.3389/fphar.2025.1681610

53.

Yuan

Chen

, et al. Single-Cell Transcriptomics Reveals CCL3+ Classical Monocyte Subset Linked to Autoimmune Pathogenesis. J Inflamm Res 2025; 18: 16273–16291. https://doi.org/10.2147/JIR.S547283

54.

Barroso

Branco

Apkarian

. Brain mechanisms of chronic pain: critical role of translational approach. Transl Res 2021; 238: 76–89. https://doi.org/10.1016/j.trsl.2021.06.004

55.

Glymph

King

Rodney

, et al. Pain Management and Health Disparities. Nurs Clin North Am 2025; 60(4): 681–694. https://doi.org/10.1016/j.cnur.2025.01.001

56.

Bhagar

Le-Niculescu

Corey

, et al. Next-generation precision medicine for pain. Mol Psychiatry 2026; 31(2): 869–894. https://doi.org/10.1038/s41380-025-03186-8

57.

Gao

Yin

Myers

, et al. Potentially long-lasting effects of the pandemic on scientists. Nat Commun 2021; 12(1): 6188. https://doi.org/10.1038/s41467-021-26428-z

58.

Wang

Lou

, et al. Research Trends and Hotspots in JAK Inhibitors for Ulcerative Colitis: A Bibliometric Analysis From 2015 to 2024. J Multidiscip Healthc 2025; 18: 6755–6771. https://doi.org/10.2147/JMDH.S548268

59.

Myers

Tham

Yin

, et al. Unequal effects of the COVID-19 pandemic on scientists. Nat Hum Behav 2020; 4(9): 880–883. https://doi.org/10.1038/s41562-020-0921-y

60.

Gunduz

Matis

Ozduran

, et al. Evaluating the Readability, Quality, and Reliability of Online Patient Education Materials on Spinal Cord Stimulation. Turk Neurosurg 2024; 34(4): 588–599. https://doi.org/10.5137/1019-5149.JTN.42973-22.3

61.

Kara

Ozduran

Kara

, et al. Evaluating the readability, quality, and reliability of responses generated by ChatGPT, Gemini, and Perplexity on the most commonly asked questions about Ankylosing spondylitis. PLoS One 2025; 20(6): e0326351. https://doi.org/10.1371/journal.pone.0326351

62.

Özduran

. Evaluation of the readability of Turkish internet-based patient education materials related to low back pain. J Dokuz Eylul Univ Med Fac 2022; 36(2): 135–150. https://doi.org/10.18614/deutip.1174522

63.

Hancı

Öner

Özduran

, et al. Youtube as a source of information about Percutan Tracheostomy. Gazi Med J 2023; 34(4): 372–378. https://doi.org/10.12996/gmj.2023.77

64.

Özduran

. YouTube as an Information Source for Myofascial Pain Syndrome. In: Ünlü

(ed). Current Approaches to Myofascial Pain Syndrome. 1st ed. Türkiye Klinikleri, 2026, pp. 377–382. https://doi.org/10.5336/978-625-395-854-1_p377

65.

Özduran

Hancı

. Exploring the Reliability and Accessibility of Youtube for Cerebral Palsy Rehabilitation Information. Journal of Child 2024; 24(1): 15–24. https://doi.org/10.26650/jchild.2024.1301406

66.

Özduran

Hancı

. YouTube as a source of information about pulmonary rehabilitation during the COVID-19 pandemic. Eurasian J Pulmonol 2022; 24(2): 107–114. https://doi.org/10.14744/ejp.2022.9221

67.

Özduran

Akkoc

Büyükçoban

, et al. Readability, reliability and quality of responses generated by ChatGPT, gemini, and perplexity for the most frequently asked questions about pain. Medicine (Baltimore) 2025; 104(11): e41780. https://doi.org/10.1097/MD.0000000000041780

68.

Özbek

Özduran

Hancı

. Artificial intelligence in pain: A comprehensive review. Med J. West. Black Sea 2026; 10: 168–178. https://doi.org/10.29058/mjwbs.1881313

69.

Mengi

Özduran

. Evaluating the Readability, Quality, and Reliability of Responses Generated By Artificial Intelligence Programs About Acupuncture for Pain. Journal of Physical Medicine and Rehabilitation Sciences 2026; 29(2): 245–253. https://doi.org/10.31609/jpmrs.2025-115285

70.

Özbek

İC

Hancı

Özduran

. Digital Guidance: Quality and Readability Analysis of Artificial Intelligence-Generated Spondyloarthropathy Texts. Turk J Osteoporos 2025; 31(1): 12–18. https://doi.org/10.4274/tod.galenos.2024.76743

71.

Özbek

İC

Özduran

. Digital Rehabilitation in Parkinson’s Disease: The Role of Artificial Intelligence-Assisted Exercise Training. Turk J Osteoporos 2025; 12. https://doi.org/10.4274/tod.galenos.2025.66664

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.11 MB

0.09 MB

0.00 MB

0.26 MB