Yiqun Miao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yiqun Miao has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Ying Wu
School of Nursing, Capital Medical University, Beijing, China
12 shared publications - Yuan Luo
School of Nursing, Capital Medical University, Beijing, China
10 shared publications - Yuhan Zhao
School of Nursing, Capital Medical University, Beijing, China
9 shared publications - Huiying Wang
School of Nursing, Capital Medical University, Beijing, China
7 shared publications - Jiawei Li
School of Nursing, Capital Medical University, Beijing, China
3 shared publications - Mingxuan Liu
School of Nursing, Capital Medical University, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 25 October 2026
- Published by Springer Nature in Scientific Reports
Trajectories of leisure-time physical activity behavior and risk of incident cardiovascular disease in middle-aged and older adults
- 25 October 2026
- Published by Springer Nature in Scientific Reports
Open AccessTrajectories of leisure-time physical activity behavior and risk of incident cardiovascular disease in middle-aged and older adults
- Open Access
- 3 August 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e90046
Evaluation Methods for Inference-Time Retrieval-Augmented and Graph Retrieval-Augmented Large Language Models in Health Care: Scoping Review
Background: Inference-time retrieval augmentation is increasingly used to improve the traceability and verifiability of large language model (LLM) applications in health care. Evaluation practices for text-based retrieval-augmented generation (RAG) and graph-structured RAG (GraphRAG) systems remain heterogeneous, which limits comparison across studies and complicates judgments about clinical readiness. Objective: This review mapped evaluation methods for inference-time retrieval-augmented and graph-structured retrieval-augmented LLM systems in health care and characterized how evaluation constructs are defined, operationalized, and reported across system layers and evaluation-setting categories. Methods: We conducted a scoping review in accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews), with search reporting informed by PRISMA-S (PRISMA literature search extension). Searches were conducted through May 14, 2026, in PubMed (MEDLINE), Web of Science Core Collection, IEEE Xplore, ACM Digital Library, arXiv, and medRxiv, with backward and forward citation tracking of included studies. Eligible records described health care–relevant LLM systems using inference-time RAG and reported at least 1 evaluation component. Data were charted on study characteristics, system design, retrieval-layer evaluation, evidence linkage, safety-related and GraphRAG-specific evaluation, and selected reporting and governance characteristics. We also constructed an evidence-and-gap map cross-classifying evaluation-setting categories with key evaluation domains. Results: A total of 157 studies met the inclusion criteria. Clinical question answering was the most frequently represented application (89/157, 56.7%), followed by clinical decision support (70/157, 44.6%). Most evaluations were conducted in offline-only settings (140/157, 89.2%), whereas 17/157 (10.8%) studies reported workflow-facing, prospective, or deployment-level evaluation. Independent retrieval-layer evaluation was reported in 47/157 (29.9%) studies. Grounding and faithfulness evaluation was reported in 41/157 (26.1%) studies, and fine-grained evidence verification was reported in 22/157 (14%) studies. Human evaluation was reported in 94/157 (59.9%) studies, but interrater reliability was reported in 26/94 (27.7%) studies. LLM-as-judge evaluation was reported in 41/157 (26.1%) studies, with bias-control measures reported in 15/41 (36.6%) studies. Formal safety-related evaluation was reported in 45/157 (28.7%) studies. Among 27 (17.2%) GraphRAG studies, intermediate-artifact evaluation was reported in 11/27 (40.7%) studies, and graph construction evaluation was reported in 6/27 (22.2%) studies. The evidence-and-gap map showed limited coverage of fine-grained verification, contradiction handling, safety evaluation, LLM-as-judge safeguards, GraphRAG construction evaluation, and GraphRAG intermediate-artifact evaluation in workflow-facing, prospective, or deployment-level settings. Conclusions: Evaluation of health care RAG and GraphRAG systems has expanded rapidly, yet reporting and operational definitions remain inconsistent across evaluation layers. Current evidence remains concentrated in offline evaluation, with limited workflow-facing, prospective, or deployment-level assessment of retrieval quality, fine-grained evidence linkage, safety, LLM-as-judge safeguards, GraphRAG construction quality, and GraphRAG intermediate artifacts. This review maps these gaps across evaluation-setting categories and translates them into synthesis-informed evaluation considerations. These findings suggest that future evaluation may need to move beyond end-to-end benchmark performance toward more transparent, layer-specific, safety-oriented, and clinically contextualized assessment before workflow-facing implementation.
- 3 August 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e90046
Open AccessEvaluation Methods for Inference-Time Retrieval-Augmented and Graph Retrieval-Augmented Large Language Models in Health Care: Scoping Review
Background: Inference-time retrieval augmentation is increasingly used to improve the traceability and verifiability of large language model (LLM) applications in health care. Evaluation practices for text-based retrieval-augmented generation (RAG) and graph-structured RAG (GraphRAG) systems remain heterogeneous, which limits comparison across studies and complicates judgments about clinical readiness. Objective: This review mapped evaluation methods for inference-time retrieval-augmented and graph-structured retrieval-augmented LLM systems in health care and characterized how evaluation constructs are defined, operationalized, and reported across system layers and evaluation-setting categories. Methods: We conducted a scoping review in accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews), with search reporting informed by PRISMA-S (PRISMA literature search extension). Searches were conducted through May 14, 2026, in PubMed (MEDLINE), Web of Science Core Collection, IEEE Xplore, ACM Digital Library, arXiv, and medRxiv, with backward and forward citation tracking of included studies. Eligible records described health care–relevant LLM systems using inference-time RAG and reported at least 1 evaluation component. Data were charted on study characteristics, system design, retrieval-layer evaluation, evidence linkage, safety-related and GraphRAG-specific evaluation, and selected reporting and governance characteristics. We also constructed an evidence-and-gap map cross-classifying evaluation-setting categories with key evaluation domains. Results: A total of 157 studies met the inclusion criteria. Clinical question answering was the most frequently represented application (89/157, 56.7%), followed by clinical decision support (70/157, 44.6%). Most evaluations were conducted in offline-only settings (140/157, 89.2%), whereas 17/157 (10.8%) studies reported workflow-facing, prospective, or deployment-level evaluation. Independent retrieval-layer evaluation was reported in 47/157 (29.9%) studies. Grounding and faithfulness evaluation was reported in 41/157 (26.1%) studies, and fine-grained evidence verification was reported in 22/157 (14%) studies. Human evaluation was reported in 94/157 (59.9%) studies, but interrater reliability was reported in 26/94 (27.7%) studies. LLM-as-judge evaluation was reported in 41/157 (26.1%) studies, with bias-control measures reported in 15/41 (36.6%) studies. Formal safety-related evaluation was reported in 45/157 (28.7%) studies. Among 27 (17.2%) GraphRAG studies, intermediate-artifact evaluation was reported in 11/27 (40.7%) studies, and graph construction evaluation was reported in 6/27 (22.2%) studies. The evidence-and-gap map showed limited coverage of fine-grained verification, contradiction handling, safety evaluation, LLM-as-judge safeguards, GraphRAG construction evaluation, and GraphRAG intermediate-artifact evaluation in workflow-facing, prospective, or deployment-level settings. Conclusions: Evaluation of health care RAG and GraphRAG systems has expanded rapidly, yet reporting and operational definitions remain inconsistent across evaluation layers. Current evidence remains concentrated in offline evaluation, with limited workflow-facing, prospective, or deployment-level assessment of retrieval quality, fine-grained evidence linkage, safety, LLM-as-judge safeguards, GraphRAG construction quality, and GraphRAG intermediate artifacts. This review maps these gaps across evaluation-setting categories and translates them into synthesis-informed evaluation considerations. These findings suggest that future evaluation may need to move beyond end-to-end benchmark performance toward more transparent, layer-specific, safety-oriented, and clinically contextualized assessment before workflow-facing implementation.
- Open Access
- 15 July 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e89190
Behavior Change Content and Implementation of Large Language Model–Driven Conversational Agents in Cardiometabolic Care: Scoping Review
Background: Large language models (LLMs) are increasingly embedded in conversational agents for cardiometabolic care. These systems could support self-management, but their behavior change content, delivery mechanisms, and implementation transparency are poorly understood. Objective: This scoping review mapped behavior change techniques (BCTs) used in LLM-driven conversational agents for cardiometabolic prevention and management, described how these techniques are delivered across static, rule-based, and generative mechanisms, examined LLM design, personalization, and safety reporting, and summarized user experience and behavioral or clinical outcomes. Methods: We searched PubMed, Web of Science, Embase, CINAHL, APA PsycInfo, IEEE Xplore, ACM Digital Library, arXiv, ClinicalTrials.gov, and the WHO International Clinical Trials Registry Platform for records published from January 1, 2020, to November 30, 2025. The final search was run on March 25, 2026, using this publication-date limit. Eligible studies reported a patient-facing text- or voice-based cardiometabolic conversational agent using an LLM or other transformer-based generative model. Two reviewers independently screened records and extracted data. BCTs were coded using the Behavior Change Technique Taxonomy v1; selected self-management BCTs were classified as static, rule-based or templated, or generative or context-aware. Empirical human-participant– or evaluator-based studies were appraised with the Mixed Methods Appraisal Tool, and a study-specific checklist assessed LLM implementation reporting transparency. Results: Thirty-eight studies were included; 19 involved empirical human-participant– or evaluator-based assessments, whereas 19 were technical and system-level evaluations, including framework-development, simulated-output, and proof-of-concept studies. Studies were concentrated in 2024‐2025. Instruction on how to perform behavior was identified in 30 of 38 (79%) studies, information about health consequences in 27 of 38 (71%) studies, and feedback and monitoring techniques in 19 of 38 (50%) studies. Most agents were positioned as educators or coaches targeting type 2 diabetes, obesity, or related cardiometabolic risk, and GPT-family models embedded in hybrid architectures with retrieval-augmented generation or rule-based components predominated. Generative outputs were used mainly for tailored explanations, risk information, and socioemotional responses, whereas self-monitoring, reminders, and structured interactions were more often rule-based or mixed-mode. Only 13 of 38 (34%) studies fully reported prompts or system messages, and 16 of 38 (42%) studies fully reported safety or oversight mechanisms. User evaluations reported good usability and perceived helpfulness, but behavioral or physiological outcomes were sparse and usually limited to pilot, short-term, or single-case designs. Conclusions: LLM-driven conversational agents for cardiometabolic care are proliferating but remain early-stage and methodologically heterogeneous. Current systems primarily use LLMs as educational and explanatory layers with “synthetic empathy” over rule-based data capture and safety functions, while behavior change content remains dominated by information provision and simple feedback. More rigorous comparative studies with longer follow-up are needed before firm conclusions can be drawn about sustained behavioral or clinical benefit.
- 15 July 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e89190
Open AccessBehavior Change Content and Implementation of Large Language Model–Driven Conversational Agents in Cardiometabolic Care: Scoping Review
Background: Large language models (LLMs) are increasingly embedded in conversational agents for cardiometabolic care. These systems could support self-management, but their behavior change content, delivery mechanisms, and implementation transparency are poorly understood. Objective: This scoping review mapped behavior change techniques (BCTs) used in LLM-driven conversational agents for cardiometabolic prevention and management, described how these techniques are delivered across static, rule-based, and generative mechanisms, examined LLM design, personalization, and safety reporting, and summarized user experience and behavioral or clinical outcomes. Methods: We searched PubMed, Web of Science, Embase, CINAHL, APA PsycInfo, IEEE Xplore, ACM Digital Library, arXiv, ClinicalTrials.gov, and the WHO International Clinical Trials Registry Platform for records published from January 1, 2020, to November 30, 2025. The final search was run on March 25, 2026, using this publication-date limit. Eligible studies reported a patient-facing text- or voice-based cardiometabolic conversational agent using an LLM or other transformer-based generative model. Two reviewers independently screened records and extracted data. BCTs were coded using the Behavior Change Technique Taxonomy v1; selected self-management BCTs were classified as static, rule-based or templated, or generative or context-aware. Empirical human-participant– or evaluator-based studies were appraised with the Mixed Methods Appraisal Tool, and a study-specific checklist assessed LLM implementation reporting transparency. Results: Thirty-eight studies were included; 19 involved empirical human-participant– or evaluator-based assessments, whereas 19 were technical and system-level evaluations, including framework-development, simulated-output, and proof-of-concept studies. Studies were concentrated in 2024‐2025. Instruction on how to perform behavior was identified in 30 of 38 (79%) studies, information about health consequences in 27 of 38 (71%) studies, and feedback and monitoring techniques in 19 of 38 (50%) studies. Most agents were positioned as educators or coaches targeting type 2 diabetes, obesity, or related cardiometabolic risk, and GPT-family models embedded in hybrid architectures with retrieval-augmented generation or rule-based components predominated. Generative outputs were used mainly for tailored explanations, risk information, and socioemotional responses, whereas self-monitoring, reminders, and structured interactions were more often rule-based or mixed-mode. Only 13 of 38 (34%) studies fully reported prompts or system messages, and 16 of 38 (42%) studies fully reported safety or oversight mechanisms. User evaluations reported good usability and perceived helpfulness, but behavioral or physiological outcomes were sparse and usually limited to pilot, short-term, or single-case designs. Conclusions: LLM-driven conversational agents for cardiometabolic care are proliferating but remain early-stage and methodologically heterogeneous. Current systems primarily use LLMs as educational and explanatory layers with “synthetic empathy” over rule-based data capture and safety functions, while behavior change content remains dominated by information provision and simple feedback. More rigorous comparative studies with longer follow-up are needed before firm conclusions can be drawn about sustained behavioral or clinical benefit.
- 1 April 2026
- Published by Wiley in Worldviews on Evidence-Based Nursing
- Vol. 23 (2) , e70136
Effectiveness of Multifactorial and Exercise Programs in Preventing Falls Among Older Adults: A Systematic Review and Component Network Meta‐Analysis
Background: To compare the effectiveness of multifactorial and exercise programs in preventing falls among older adults, with a specific focus on evaluating the individual and combined contributions of their key intervention components. Methods: This study was a systematic review and component network meta‐analysis. PubMed, Embase, and Web of Science were searched from inception to February 2025 for randomized controlled trials, focusing on four primary outcomes: fallers, recurrent fallers, injurious fallers, and fractured fallers. Risk of bias was evaluated using the Cochrane tool, and additive component network meta‐analysis compared intervention group and component efficacy. Results: 69 randomized controlled studies were included. In multifactorial interventions, traditional health education could increase fall risk (iRR: 1.10, 95% CI [1.03; 1.67]) and recurrent fall risk (iRR: 1.25, 95% CI [1.06; 1.48]). Medication management can increase recurrent fall risk (iRR: 1.35, 95% CI [1.09; 1.67]) and fracture risk (iRR: 2.11, 95% CI [1.48; 3.00]). Exercise (iRR: 1.24, 95% CI [1.01; 1.53]) increased fracture risk, and environment modification (iRR: 0.56, 95% CI [0.61; 0.79]) reduced it. The additive effect of risk assessment and advice, exercise, and environment modification reduced fall risk. In exercise programs, gait and balance (iRR: 0.58, 95% CI [0.36; 0.93]) can reduce recurrent fall risk. An intervention containing two components (gait and balance + strength and resistance) reduced the risk of falls and fall‐related injuries. Linking Evidence to Action: Environment modification reduced fracture risk, emphasizing the value of creating safe living spaces. The combination of risk assessment, advice, exercise, and environment modification reduced fall risk, suggesting a holistic approach may be effective in preventing falls. Traditional methods of health education and medication management are in urgent need of updating to synergize with other exercise components and enhance the effectiveness of fall prevention. Prospective clinical trials are needed to optimize combinations of exercise components, particularly integrating gait and balance training with strength and resistance exercises. Trial Registration: The review was registered online in the International Prospective Register of Systematic Reviews (PROSPERO) under registration number (CRD42025643530)
- 1 April 2026
- Published by Wiley in Worldviews on Evidence-Based Nursing
- Vol. 23 (2) , e70136
Effectiveness of Multifactorial and Exercise Programs in Preventing Falls Among Older Adults: A Systematic Review and Component Network Meta‐Analysis
Background: To compare the effectiveness of multifactorial and exercise programs in preventing falls among older adults, with a specific focus on evaluating the individual and combined contributions of their key intervention components. Methods: This study was a systematic review and component network meta‐analysis. PubMed, Embase, and Web of Science were searched from inception to February 2025 for randomized controlled trials, focusing on four primary outcomes: fallers, recurrent fallers, injurious fallers, and fractured fallers. Risk of bias was evaluated using the Cochrane tool, and additive component network meta‐analysis compared intervention group and component efficacy. Results: 69 randomized controlled studies were included. In multifactorial interventions, traditional health education could increase fall risk (iRR: 1.10, 95% CI [1.03; 1.67]) and recurrent fall risk (iRR: 1.25, 95% CI [1.06; 1.48]). Medication management can increase recurrent fall risk (iRR: 1.35, 95% CI [1.09; 1.67]) and fracture risk (iRR: 2.11, 95% CI [1.48; 3.00]). Exercise (iRR: 1.24, 95% CI [1.01; 1.53]) increased fracture risk, and environment modification (iRR: 0.56, 95% CI [0.61; 0.79]) reduced it. The additive effect of risk assessment and advice, exercise, and environment modification reduced fall risk. In exercise programs, gait and balance (iRR: 0.58, 95% CI [0.36; 0.93]) can reduce recurrent fall risk. An intervention containing two components (gait and balance + strength and resistance) reduced the risk of falls and fall‐related injuries. Linking Evidence to Action: Environment modification reduced fracture risk, emphasizing the value of creating safe living spaces. The combination of risk assessment, advice, exercise, and environment modification reduced fall risk, suggesting a holistic approach may be effective in preventing falls. Traditional methods of health education and medication management are in urgent need of updating to synergize with other exercise components and enhance the effectiveness of fall prevention. Prospective clinical trials are needed to optimize combinations of exercise components, particularly integrating gait and balance training with strength and resistance exercises. Trial Registration: The review was registered online in the International Prospective Register of Systematic Reviews (PROSPERO) under registration number (CRD42025643530)
- Top Cited PapersOpen Access
- 21 October 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e80557
Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review
Background: Retrieval-augmented generation (RAG) is increasingly used to improve large language models in the medical and nursing domains. However, a comprehensive understanding of its specific architecture and applications in medical and nursing reasoning remains limited. Objective: We aimed to summarize the current state, existing limitations, and future development directions of RAG in the medical and nursing domains. Methods: The PubMed, Web of Science, IEEE Xplore, and arXiv databases were searched for relevant articles using queries that combined terms related to RAG, medical, and nursing domains, covering the period from November 1, 2022, to May 31, 2025. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Results: A total of 917 articles were retrieved, of which 67 met the inclusion criteria. Most studies focused on the medical domain (63/67, 94%), while only a few addressed nursing applications (4/67, 6%). The RAG frameworks included in this review were categorized into 5 functional types: text-based RAG (36/67, 54%), knowledge graph–enhanced RAG (17/67, 25%), agentic RAG (6/67, 9%), multimodal RAG (2/67, 3%), and plug-and-play RAG (6/67, 9%). On the basis of the Simon decision-making process theory, we divided the RAG workflow into 4 stages: intent recognition, knowledge retrieval, knowledge integration, and generation. Only 26 studies included explicit reasoning support, and few were aligned with real-world clinical workflows. Only 12 studies attempted to address ethical considerations related to RAG. Conclusions: We identified 4 key shifts in recent RAG development: shifting from surface-level matching toward contextualized intent recognition, from vague semantics toward logic-driven dynamic retrieval, from passive toward active knowledge retrieval, and from simple aggregation toward coherent context construction. However, most RAG systems in the medical and nursing domains have not yet introduced reasoning methods, and those that have are still predominantly reliant on data‑driven associations without causal modeling. This highlights the need to integrate causal mechanisms for more effective and domain-relevant reasoning in health care. Trial Registration: OSF Registries 10.17605/OSF.IO/WBSV5; https://osf.io/wbsv5
- 21 October 2025
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e80557
Top Cited PapersOpen AccessImproving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review
Background: Retrieval-augmented generation (RAG) is increasingly used to improve large language models in the medical and nursing domains. However, a comprehensive understanding of its specific architecture and applications in medical and nursing reasoning remains limited. Objective: We aimed to summarize the current state, existing limitations, and future development directions of RAG in the medical and nursing domains. Methods: The PubMed, Web of Science, IEEE Xplore, and arXiv databases were searched for relevant articles using queries that combined terms related to RAG, medical, and nursing domains, covering the period from November 1, 2022, to May 31, 2025. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Results: A total of 917 articles were retrieved, of which 67 met the inclusion criteria. Most studies focused on the medical domain (63/67, 94%), while only a few addressed nursing applications (4/67, 6%). The RAG frameworks included in this review were categorized into 5 functional types: text-based RAG (36/67, 54%), knowledge graph–enhanced RAG (17/67, 25%), agentic RAG (6/67, 9%), multimodal RAG (2/67, 3%), and plug-and-play RAG (6/67, 9%). On the basis of the Simon decision-making process theory, we divided the RAG workflow into 4 stages: intent recognition, knowledge retrieval, knowledge integration, and generation. Only 26 studies included explicit reasoning support, and few were aligned with real-world clinical workflows. Only 12 studies attempted to address ethical considerations related to RAG. Conclusions: We identified 4 key shifts in recent RAG development: shifting from surface-level matching toward contextualized intent recognition, from vague semantics toward logic-driven dynamic retrieval, from passive toward active knowledge retrieval, and from simple aggregation toward coherent context construction. However, most RAG systems in the medical and nursing domains have not yet introduced reasoning methods, and those that have are still predominantly reliant on data‑driven associations without causal modeling. This highlights the need to integrate causal mechanisms for more effective and domain-relevant reasoning in health care. Trial Registration: OSF Registries 10.17605/OSF.IO/WBSV5; https://osf.io/wbsv5
- Open Access
- 7 October 2025
- Published by Taylor & Francis in Annals of Medicine
- Vol. 57 (1) , 2537916
Temporal trends and machine learning prediction for chronic kidney disease due to hypertension in young adults from 1990 to 2021: an analysis of the global burden of disease study 2021
Young adults aged 25-49, at the peak of work and family responsibilities, face serious health and productivity challenges when affected by chronic kidney disease (CKD) due to hypertension. Using Global Burden of Disease (GBD) 1990-2021 data, we assessed global, regional, and national CKD burden due to hypertension in young adults, focusing on mortality and disability-adjusted life years (DALYs). Trends analyzed by Joinpoint regression and forecasted to 2040 using eight machine learning models. In 2021, global mortality from CKD due to hypertension reached 18,675.24 cases, a 157.55% increase since 1990. The age-standardized mortality rate (ASMR) rose from 0.31 to 0.45 per 100,000 persons, with an average annual percentage change (AAPC) of 1.24% (p < 0.05). DALYs increased by 145.84% to 1,122,316.38 person-years. The age-standardized disability rate (ASDR) grew from 19.39 to 27.37 per 100,000 persons, with an AAPC of 1.12% (p < 0.05). The greatest increase occurred in the 25-29 age group, while those aged 45-49 had the highest burden. Most of the CKD burden due to hypertension was in the three lowest SDI quintiles, while high SDI regions saw the greatest increase. The Prophet model was optimal in predicting the ASMR index, while the Autoregressive Integrated Moving Average (ARIMA) model performed best for the ASDR, with projections indicating an increase in both indices by 2040. CKD due to hypertension is a growing global challenge in young adults. Substantial heterogeneity exists in the disease burden and its temporal trends across countries and regions, highlighting the strong distributive inequities of CKD worldwide.
- 7 October 2025
- Published by Taylor & Francis in Annals of Medicine
- Vol. 57 (1) , 2537916
Open AccessTemporal trends and machine learning prediction for chronic kidney disease due to hypertension in young adults from 1990 to 2021: an analysis of the global burden of disease study 2021
Young adults aged 25-49, at the peak of work and family responsibilities, face serious health and productivity challenges when affected by chronic kidney disease (CKD) due to hypertension. Using Global Burden of Disease (GBD) 1990-2021 data, we assessed global, regional, and national CKD burden due to hypertension in young adults, focusing on mortality and disability-adjusted life years (DALYs). Trends analyzed by Joinpoint regression and forecasted to 2040 using eight machine learning models. In 2021, global mortality from CKD due to hypertension reached 18,675.24 cases, a 157.55% increase since 1990. The age-standardized mortality rate (ASMR) rose from 0.31 to 0.45 per 100,000 persons, with an average annual percentage change (AAPC) of 1.24% (p < 0.05). DALYs increased by 145.84% to 1,122,316.38 person-years. The age-standardized disability rate (ASDR) grew from 19.39 to 27.37 per 100,000 persons, with an AAPC of 1.12% (p < 0.05). The greatest increase occurred in the 25-29 age group, while those aged 45-49 had the highest burden. Most of the CKD burden due to hypertension was in the three lowest SDI quintiles, while high SDI regions saw the greatest increase. The Prophet model was optimal in predicting the ASMR index, while the Autoregressive Integrated Moving Average (ARIMA) model performed best for the ASDR, with projections indicating an increase in both indices by 2040. CKD due to hypertension is a growing global challenge in young adults. Substantial heterogeneity exists in the disease burden and its temporal trends across countries and regions, highlighting the strong distributive inequities of CKD worldwide.
- Open Access
- 7 August 2025
- Published by IOS Press
- Vol. 329, 2042-2043
Development and Effectiveness of a Generative Virtual Clinical Decision-Making Training System to Optimize Clinical Decision-Making Ability of Nursing Students: A Randomized, Controlled, Proof-of-Concept Trial
The existing virtual education systems in nursing do not adequately align with the random, dynamic, and variable scenarios essential for developing clinical decision-making skills, thus hindering nursing students’ proficiency. This study developed a generative virtual reality training system for clinical decision-making skills and conducted a randomized controlled trial with nursing students to verify its effectiveness in enhancing these skills.
- 7 August 2025
- Published by IOS Press
- Vol. 329, 2042-2043
Open AccessDevelopment and Effectiveness of a Generative Virtual Clinical Decision-Making Training System to Optimize Clinical Decision-Making Ability of Nursing Students: A Randomized, Controlled, Proof-of-Concept Trial
The existing virtual education systems in nursing do not adequately align with the random, dynamic, and variable scenarios essential for developing clinical decision-making skills, thus hindering nursing students’ proficiency. This study developed a generative virtual reality training system for clinical decision-making skills and conducted a randomized controlled trial with nursing students to verify its effectiveness in enhancing these skills.
- Open Access
- 12 July 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review (Preprint)
BACKGROUND Retrieval-augmented generation (RAG) is increasingly used to improve large language models in the medical and nursing domains. However, a comprehensive understanding of its specific architecture and applications in medical and nursing reasoning remains limited. OBJECTIVE We aimed to summarize the current state, existing limitations, and future development directions of RAG in the medical and nursing domains. METHODS The PubMed, Web of Science, IEEE Xplore, and arXiv databases were searched for relevant articles using queries that combined terms related to RAG, medical, and nursing domains, covering the period from November 1, 2022, to May 31, 2025. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. RESULTS A total of 917 articles were retrieved, of which 67 met the inclusion criteria. Most studies focused on the medical domain (63/67, 94%), while only a few addressed nursing applications (4/67, 6%). The RAG frameworks included in this review were categorized into 5 functional types: text-based RAG (36/67, 54%), knowledge graph–enhanced RAG (17/67, 25%), agentic RAG (6/67, 9%), multimodal RAG (2/67, 3%), and plug-and-play RAG (6/67, 9%). On the basis of the Simon decision-making process theory, we divided the RAG workflow into 4 stages: intent recognition, knowledge retrieval, knowledge integration, and generation. Only 26 studies included explicit reasoning support, and few were aligned with real-world clinical workflows. Only 12 studies attempted to address ethical considerations related to RAG. CONCLUSIONS We identified 4 key shifts in recent RAG development: shifting from surface-level matching toward contextualized intent recognition, from vague semantics toward logic-driven dynamic retrieval, from passive toward active knowledge retrieval, and from simple aggregation toward coherent context construction. However, most RAG systems in the medical and nursing domains have not yet introduced reasoning methods, and those that have are still predominantly reliant on data‑driven associations without causal modeling. This highlights the need to integrate causal mechanisms for more effective and domain-relevant reasoning in health care. CLINICALTRIAL OSF Registries 10.17605/OSF.IO/WBSV5; https://osf.io/wbsv5
- 12 July 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessImproving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review (Preprint)
BACKGROUND Retrieval-augmented generation (RAG) is increasingly used to improve large language models in the medical and nursing domains. However, a comprehensive understanding of its specific architecture and applications in medical and nursing reasoning remains limited. OBJECTIVE We aimed to summarize the current state, existing limitations, and future development directions of RAG in the medical and nursing domains. METHODS The PubMed, Web of Science, IEEE Xplore, and arXiv databases were searched for relevant articles using queries that combined terms related to RAG, medical, and nursing domains, covering the period from November 1, 2022, to May 31, 2025. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. RESULTS A total of 917 articles were retrieved, of which 67 met the inclusion criteria. Most studies focused on the medical domain (63/67, 94%), while only a few addressed nursing applications (4/67, 6%). The RAG frameworks included in this review were categorized into 5 functional types: text-based RAG (36/67, 54%), knowledge graph–enhanced RAG (17/67, 25%), agentic RAG (6/67, 9%), multimodal RAG (2/67, 3%), and plug-and-play RAG (6/67, 9%). On the basis of the Simon decision-making process theory, we divided the RAG workflow into 4 stages: intent recognition, knowledge retrieval, knowledge integration, and generation. Only 26 studies included explicit reasoning support, and few were aligned with real-world clinical workflows. Only 12 studies attempted to address ethical considerations related to RAG. CONCLUSIONS We identified 4 key shifts in recent RAG development: shifting from surface-level matching toward contextualized intent recognition, from vague semantics toward logic-driven dynamic retrieval, from passive toward active knowledge retrieval, and from simple aggregation toward coherent context construction. However, most RAG systems in the medical and nursing domains have not yet introduced reasoning methods, and those that have are still predominantly reliant on data‑driven associations without causal modeling. This highlights the need to integrate causal mechanisms for more effective and domain-relevant reasoning in health care. CLINICALTRIAL OSF Registries 10.17605/OSF.IO/WBSV5; https://osf.io/wbsv5
- Open Access
- 2 December 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8 (1) , e63188
Comparing the Accuracy of Two Generated Large Language Models in Identifying Health-Related Rumors or Misconceptions and the Applicability in Health Science Popularization: Proof-of-Concept Study
Background: Health-related rumors and misconceptions are spreading at an alarming rate, fueled by the rapid development of the internet and the exponential growth of social media platforms. This phenomenon has become a pressing global concern, as the dissemination of false information can have severe consequences, including widespread panic, social instability, and even public health crises. Objective: The aim of the study is to compare the accuracy of rumor identification and the effectiveness of health science popularization between 2 generated large language models in Chinese (GPT-4 by OpenAI and Enhanced Representation through Knowledge Integration Bot [ERNIE Bot] 4.0 by Baidu). Methods: In total, 20 health rumors and misconceptions, along with 10 health truths, were randomly inputted into GPT-4 and ERNIE Bot 4.0. We prompted them to determine whether the statements were rumors or misconceptions and provide explanations for their judgment. Further, we asked them to generate a health science popularization essay. We evaluated the outcomes in terms of accuracy, effectiveness, readability, and applicability. Accuracy was assessed by the rate of correctly identifying health-related rumors, misconceptions, and truths. Effectiveness was determined by the accuracy of the generated explanation, which was assessed collaboratively by 2 research team members with a PhD in nursing. Readability was calculated by the readability formula of Chinese health education materials. Applicability was evaluated by the Chinese Suitability Assessment of Materials. Results: GPT-4 and ERNIE Bot 4.0 correctly identified all health rumors and misconceptions (100% accuracy rate). For truths, the accuracy rate was 70% (7/10) and 100% (10/10), respectively. Both mostly provided widely recognized viewpoints without obvious errors. The average readability score for the health essays was 2.92 (SD 0.85) for GPT-4 and 3.02 (SD 0.84) for ERNIE Bot 4.0 (P=.65). For applicability, except for the content and cultural appropriateness category, significant differences were observed in the total score and scores in other dimensions between them (P<.05). Conclusions: ERNIE Bot 4.0 demonstrated similar accuracy to GPT-4 in identifying Chinese rumors. Both provided widely accepted views, despite some inaccuracies. These insights enhance understanding and correct misunderstandings. For health essays, educators can learn from readable language styles of GLLMs. Finally, ERNIE Bot 4.0 aligns with Chinese expression habits, making it a good choice for a better Chinese reading experience.
- 2 December 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8 (1) , e63188
Open AccessComparing the Accuracy of Two Generated Large Language Models in Identifying Health-Related Rumors or Misconceptions and the Applicability in Health Science Popularization: Proof-of-Concept Study
Background: Health-related rumors and misconceptions are spreading at an alarming rate, fueled by the rapid development of the internet and the exponential growth of social media platforms. This phenomenon has become a pressing global concern, as the dissemination of false information can have severe consequences, including widespread panic, social instability, and even public health crises. Objective: The aim of the study is to compare the accuracy of rumor identification and the effectiveness of health science popularization between 2 generated large language models in Chinese (GPT-4 by OpenAI and Enhanced Representation through Knowledge Integration Bot [ERNIE Bot] 4.0 by Baidu). Methods: In total, 20 health rumors and misconceptions, along with 10 health truths, were randomly inputted into GPT-4 and ERNIE Bot 4.0. We prompted them to determine whether the statements were rumors or misconceptions and provide explanations for their judgment. Further, we asked them to generate a health science popularization essay. We evaluated the outcomes in terms of accuracy, effectiveness, readability, and applicability. Accuracy was assessed by the rate of correctly identifying health-related rumors, misconceptions, and truths. Effectiveness was determined by the accuracy of the generated explanation, which was assessed collaboratively by 2 research team members with a PhD in nursing. Readability was calculated by the readability formula of Chinese health education materials. Applicability was evaluated by the Chinese Suitability Assessment of Materials. Results: GPT-4 and ERNIE Bot 4.0 correctly identified all health rumors and misconceptions (100% accuracy rate). For truths, the accuracy rate was 70% (7/10) and 100% (10/10), respectively. Both mostly provided widely recognized viewpoints without obvious errors. The average readability score for the health essays was 2.92 (SD 0.85) for GPT-4 and 3.02 (SD 0.84) for ERNIE Bot 4.0 (P=.65). For applicability, except for the content and cultural appropriateness category, significant differences were observed in the total score and scores in other dimensions between them (P<.05). Conclusions: ERNIE Bot 4.0 demonstrated similar accuracy to GPT-4 in identifying Chinese rumors. Both provided widely accepted views, despite some inaccuracies. These insights enhance understanding and correct misunderstandings. For health essays, educators can learn from readable language styles of GLLMs. Finally, ERNIE Bot 4.0 aligns with Chinese expression habits, making it a good choice for a better Chinese reading experience.
- 18 November 2024
- Published by Wiley in Journal of Advanced Nursing
- Vol. 81 (7) , 3473-3484
Exploring the Current Applications and Effectiveness of ChatGPT in Nursing: An Integrative Review
Aims: To systematically review the current application status of ChatGPT in nursing and explore its application effects.Design: An integrative review.Methods: Following inclusion and exclusion criteria, two researchers summarised the selected literature and conducted a quality appraisal, followed by narrative synthesis.Data Sources: PubMed, Web of Science and Scopus were searched from January 2022 to June 2024.Results: A total of 31 papers met the inclusion criteria. Fifteen empirical studies were rated as grade 5, while five were rated as grade 4. The references of a minireview were not recently published and lacked ChatGPT‐related articles, and a systematic review was of low quality. The review focused on three main topics: (1) The subsidiary role of ChatGPT in nursing; (2) Comparison of different models' effectiveness and (3) Existing challenges.Conclusions: While adopting new technologies such as ChatGPT, it is important to maintain a balanced perspective on both its benefits and limitations. Nursing professionals must actively address these deficiencies and explore solutions to improve ChatGPT's utility in the field.Implications to the Profession and Patient Care: This review synthesised evidence on ChatGPT's application and highlighted existing challenges in nursing. Nursing researchers, educators and practitioners can further validate these findings to explore its potential in various aspects of nursing practice.Impact: For researchers, ChatGPT can enhance language quality and summarise findings effectively, but adherence to research standards is crucial. For educators, ChatGPT can serve as an effective information source for students, though caution should be taken to avoid overreliance. For practitioners, ChatGPT can offer useful suggestions for clinical practice, but these should be critically evaluated and not followed blindly, as issues of inaccuracy must be addressed.Reporting Method: This review adhered to Preferred Reporting Items for Systematic Reviews and Meta‐Analyses.Patient or Public Contribution: No patient or public contribution.
- 18 November 2024
- Published by Wiley in Journal of Advanced Nursing
- Vol. 81 (7) , 3473-3484
Exploring the Current Applications and Effectiveness of ChatGPT in Nursing: An Integrative Review
Aims: To systematically review the current application status of ChatGPT in nursing and explore its application effects.Design: An integrative review.Methods: Following inclusion and exclusion criteria, two researchers summarised the selected literature and conducted a quality appraisal, followed by narrative synthesis.Data Sources: PubMed, Web of Science and Scopus were searched from January 2022 to June 2024.Results: A total of 31 papers met the inclusion criteria. Fifteen empirical studies were rated as grade 5, while five were rated as grade 4. The references of a minireview were not recently published and lacked ChatGPT‐related articles, and a systematic review was of low quality. The review focused on three main topics: (1) The subsidiary role of ChatGPT in nursing; (2) Comparison of different models' effectiveness and (3) Existing challenges.Conclusions: While adopting new technologies such as ChatGPT, it is important to maintain a balanced perspective on both its benefits and limitations. Nursing professionals must actively address these deficiencies and explore solutions to improve ChatGPT's utility in the field.Implications to the Profession and Patient Care: This review synthesised evidence on ChatGPT's application and highlighted existing challenges in nursing. Nursing researchers, educators and practitioners can further validate these findings to explore its potential in various aspects of nursing practice.Impact: For researchers, ChatGPT can enhance language quality and summarise findings effectively, but adherence to research standards is crucial. For educators, ChatGPT can serve as an effective information source for students, though caution should be taken to avoid overreliance. For practitioners, ChatGPT can offer useful suggestions for clinical practice, but these should be critically evaluated and not followed blindly, as issues of inaccuracy must be addressed.Reporting Method: This review adhered to Preferred Reporting Items for Systematic Reviews and Meta‐Analyses.Patient or Public Contribution: No patient or public contribution.