Jiawen Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jiawen Hu has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Xiaojian Ji
Department of Rheumatology, Chinese PLA General Hospital, Beijing, China
4 shared publications - Kunpeng Li
Department of Rheumatology and Immunology, the First Medical Center, Chinese PLA General Hospital, Beijing, China
3 shared publications - Anan Wang
Department of Medical Innovation Research, Chinese PLA General Hospital, Beijing, China
2 shared publications - Da Teng
Beijing Institute of Petrochemical Technology, Beijing, China
2 shared publications - Dong Pu
Dataa Robotics Co, Ltd, Beijing, China
2 shared publications - Fazhan Zhang
Dataa Robotics Co, Ltd, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 8 May 2025
- Published by SAGE Publications in Therapeutic Advances in Musculoskeletal Disease
- Vol. 17
Muscle health in ankylosing spondylitis: effects of disease duration, inflammation, education level, and spinal mobility on skeletal muscle atrophy
Background: Ankylosing spondylitis (AS) is a progressive chronic disease that primarily affects the axial skeleton, leading to significant musculoskeletal impairment. This condition may extend its inflammatory impact to peripheral muscles, potentially resulting in muscle wasting. Objectives: The study aimed to investigate the prevalence of sarcopenia among AS patients, to determine the specific cutoff values for muscle status, and to identify risk factors that may impact muscle status in AS patients. Design: A cross-sectional study was conducted involving consecutive AS patients attending the Department of Rheumatology and Immunology at the First Medical Center of the Chinese PLA General Hospital. Clinical characteristics and body composition were evaluated. Methods: Based on the Asian Working Group for Sarcopenia criteria, the prevalence of sarcopenia among AS patients were calculated. Additionally, specific cutoff values for muscle mass and muscle strength in AS patients were analyzed. Univariable and multivariable logistic regression analyses were employed to scrutinize risk factors impacting muscle status in AS patients, including appendicular skeletal muscle mass index (ASMI) and grip strength. Results: Measurements of body composition, including ASM at 22.79 kg and ASMI at 7.69 kg/m², were significantly lower compared to the healthy control group ( p < 0.05). The prevalence of sarcopenia, as identified by the sex-specific fifth percentile, is 8.66% in AS patients. In our study, the ASMI cutoffs were set at 7.48 kg/m² for males and 5.63 kg/m² for females. Logistic regression analysis revealed that AS patients who had a longer disease duration, lower level of education, elevated inflammatory markers, and a higher Bath Ankylosing Spondylitis Metrology Index (BASMI) were more likely to experience a decrease in ASMI. Regarding the muscle strength, lower education level and higher Bath Ankylosing Spondylitis Functional Index were correlated with a reduced grip strength in individuals with AS. Conclusion: Our study indicates that AS patients may have a diminished muscle status. Although the incidence of sarcopenia among AS patients is relatively low, a notable subset does suffer from muscle atrophy. Variables such as disease duration, education level, inflammatory markers, and BASMI are likely to influence muscle status in AS patients, warranting consideration in clinical management and intervention strategies.
- 8 May 2025
- Published by SAGE Publications in Therapeutic Advances in Musculoskeletal Disease
- Vol. 17
Open AccessMuscle health in ankylosing spondylitis: effects of disease duration, inflammation, education level, and spinal mobility on skeletal muscle atrophy
Background: Ankylosing spondylitis (AS) is a progressive chronic disease that primarily affects the axial skeleton, leading to significant musculoskeletal impairment. This condition may extend its inflammatory impact to peripheral muscles, potentially resulting in muscle wasting. Objectives: The study aimed to investigate the prevalence of sarcopenia among AS patients, to determine the specific cutoff values for muscle status, and to identify risk factors that may impact muscle status in AS patients. Design: A cross-sectional study was conducted involving consecutive AS patients attending the Department of Rheumatology and Immunology at the First Medical Center of the Chinese PLA General Hospital. Clinical characteristics and body composition were evaluated. Methods: Based on the Asian Working Group for Sarcopenia criteria, the prevalence of sarcopenia among AS patients were calculated. Additionally, specific cutoff values for muscle mass and muscle strength in AS patients were analyzed. Univariable and multivariable logistic regression analyses were employed to scrutinize risk factors impacting muscle status in AS patients, including appendicular skeletal muscle mass index (ASMI) and grip strength. Results: Measurements of body composition, including ASM at 22.79 kg and ASMI at 7.69 kg/m², were significantly lower compared to the healthy control group ( p < 0.05). The prevalence of sarcopenia, as identified by the sex-specific fifth percentile, is 8.66% in AS patients. In our study, the ASMI cutoffs were set at 7.48 kg/m² for males and 5.63 kg/m² for females. Logistic regression analysis revealed that AS patients who had a longer disease duration, lower level of education, elevated inflammatory markers, and a higher Bath Ankylosing Spondylitis Metrology Index (BASMI) were more likely to experience a decrease in ASMI. Regarding the muscle strength, lower education level and higher Bath Ankylosing Spondylitis Functional Index were correlated with a reduced grip strength in individuals with AS. Conclusion: Our study indicates that AS patients may have a diminished muscle status. Although the incidence of sarcopenia among AS patients is relatively low, a notable subset does suffer from muscle atrophy. Variables such as disease duration, education level, inflammatory markers, and BASMI are likely to influence muscle status in AS patients, warranting consideration in clinical management and intervention strategies.
- 17 March 2025
- Published by Oxford University Press (OUP) in Rheumatology
- Vol. 64 (7) , 4133-4142
From awareness to action: poor knowledge of physical activity correlates with lower activity and worse disease in axial spondyloarthritis
Objective: To investigate the awareness, implementation and factors influencing physical activity (PA) engagement among Chinese patients with radiographic axial spondyloarthritis (r-axSpA), and their relationships with disease status. Methods: This cross-sectional study enrolled 151 r-axSpA patients and evaluated their awareness of PA while collecting sociodemographic and disease-related parameters. PA levels were assessed with the Godin Leisure-Time Exercise Questionnaire (GLTEQ) and daily steps recorded by smartphones. Influencing factors were evaluated using the Inflammatory arthritis FAcilitators and Barriers (IFAB) questionnaire. Spearman's correlation analysis was used to explore relationships between variables. Results: Among 151 r-axSpA patients, 98.0% were aware of health benefits of PA, and 97.4% reported that physicians had recommended PA to them. However, fewer patients knew the World Health Organization recommendations on aerobic PA (33.8%) and muscle-strengthening activities (33.1%), as well as the European League Against Rheumatism (EULAR) recommendations for PA (55.6%). According to daily steps, only 13.2% were classified as active. Individual exercise (62.3%) was the main form. A sedentary group (GLTEQ score < 14) demonstrated significantly poorer awareness of recommendations and higher disease activity compared with a moderately active/active group (GLTEQ score ≥ 14). Awareness of EULAR recommendations was positively correlated with GLTEQ score (P = 0.003). IFAB6 (lack of motivation, P = 0.015) and IFAB8 (knowledge of benefits of PA, P = 0.045) showed significant differences between the sedentary and the moderately active/active group. Conclusion: Despite recognizing health benefits of PA, patients had limited awareness of PA recommendations and under-engaged in PA. This insufficient awareness correlated with lower activity and worse disease status. Healthcare professionals should enhance PA education and encourage regular PA.
- 17 March 2025
- Published by Oxford University Press (OUP) in Rheumatology
- Vol. 64 (7) , 4133-4142
From awareness to action: poor knowledge of physical activity correlates with lower activity and worse disease in axial spondyloarthritis
Objective: To investigate the awareness, implementation and factors influencing physical activity (PA) engagement among Chinese patients with radiographic axial spondyloarthritis (r-axSpA), and their relationships with disease status. Methods: This cross-sectional study enrolled 151 r-axSpA patients and evaluated their awareness of PA while collecting sociodemographic and disease-related parameters. PA levels were assessed with the Godin Leisure-Time Exercise Questionnaire (GLTEQ) and daily steps recorded by smartphones. Influencing factors were evaluated using the Inflammatory arthritis FAcilitators and Barriers (IFAB) questionnaire. Spearman's correlation analysis was used to explore relationships between variables. Results: Among 151 r-axSpA patients, 98.0% were aware of health benefits of PA, and 97.4% reported that physicians had recommended PA to them. However, fewer patients knew the World Health Organization recommendations on aerobic PA (33.8%) and muscle-strengthening activities (33.1%), as well as the European League Against Rheumatism (EULAR) recommendations for PA (55.6%). According to daily steps, only 13.2% were classified as active. Individual exercise (62.3%) was the main form. A sedentary group (GLTEQ score < 14) demonstrated significantly poorer awareness of recommendations and higher disease activity compared with a moderately active/active group (GLTEQ score ≥ 14). Awareness of EULAR recommendations was positively correlated with GLTEQ score (P = 0.003). IFAB6 (lack of motivation, P = 0.015) and IFAB8 (knowledge of benefits of PA, P = 0.045) showed significant differences between the sedentary and the moderately active/active group. Conclusion: Despite recognizing health benefits of PA, patients had limited awareness of PA recommendations and under-engaged in PA. This insufficient awareness correlated with lower activity and worse disease status. Healthcare professionals should enhance PA education and encourage regular PA.
- Open Access
- 24 May 2024
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 13, e57001
Assessing and Optimizing Large Language Models on Spondyloarthritis Multi-Choice Question Answering: Protocol for Enhancement and Assessment
Background: Spondyloarthritis (SpA), a chronic inflammatory disorder, predominantly impacts the sacroiliac joints and spine, significantly escalating the risk of disability. SpA’s complexity, as evidenced by its diverse clinical presentations and symptoms that often mimic other diseases, presents substantial challenges in its accurate diagnosis and differentiation. This complexity becomes even more pronounced in nonspecialist health care environments due to limited resources, resulting in delayed referrals, increased misdiagnosis rates, and exacerbated disability outcomes for patients with SpA. The emergence of large language models (LLMs) in medical diagnostics introduces a revolutionary potential to overcome these diagnostic hurdles. Despite recent advancements in artificial intelligence and LLMs demonstrating effectiveness in diagnosing and treating various diseases, their application in SpA remains underdeveloped. Currently, there is a notable absence of SpA-specific LLMs and an established benchmark for assessing the performance of such models in this particular field. Objective: Our objective is to develop a foundational medical model, creating a comprehensive evaluation benchmark tailored to the essential medical knowledge of SpA and its unique diagnostic and treatment protocols. The model, post-pretraining, will be subject to further enhancement through supervised fine-tuning. It is projected to significantly aid physicians in SpA diagnosis and treatment, especially in settings with limited access to specialized care. Furthermore, this initiative is poised to promote early and accurate SpA detection at the primary care level, thereby diminishing the risks associated with delayed or incorrect diagnoses. Methods: A rigorous benchmark, comprising 222 meticulously formulated multiple-choice questions on SpA, will be established and developed. These questions will be extensively revised to ensure their suitability for accurately evaluating LLMs’ performance in real-world diagnostic and therapeutic scenarios. Our methodology involves selecting and refining top foundational models using public data sets. The best-performing model in our benchmark will undergo further training. Subsequently, more than 80,000 real-world inpatient and outpatient cases from hospitals will enhance LLM training, incorporating techniques such as supervised fine-tuning and low-rank adaptation. We will rigorously assess the models’ generated responses for accuracy and evaluate their reasoning processes using the metrics of fluency, relevance, completeness, and medical proficiency. Results: Development of the model is progressing, with significant enhancements anticipated by early 2024. The benchmark, along with the results of evaluations, is expected to be released in the second quarter of 2024. Conclusions: Our trained model aims to capitalize on the capabilities of LLMs in analyzing complex clinical data, thereby enabling precise detection, diagnosis, and treatment of SpA. This innovation is anticipated to play a vital role in diminishing the disabilities arising from delayed or incorrect SpA diagnoses. By promoting this model across diverse health care settings, we anticipate a significant improvement in SpA management, culminating in enhanced patient outcomes and a reduced overall burden of the disease. International Registered Report Identifier (IRRID): DERR1-10.2196/57001
- 24 May 2024
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 13, e57001
Open AccessAssessing and Optimizing Large Language Models on Spondyloarthritis Multi-Choice Question Answering: Protocol for Enhancement and Assessment
Background: Spondyloarthritis (SpA), a chronic inflammatory disorder, predominantly impacts the sacroiliac joints and spine, significantly escalating the risk of disability. SpA’s complexity, as evidenced by its diverse clinical presentations and symptoms that often mimic other diseases, presents substantial challenges in its accurate diagnosis and differentiation. This complexity becomes even more pronounced in nonspecialist health care environments due to limited resources, resulting in delayed referrals, increased misdiagnosis rates, and exacerbated disability outcomes for patients with SpA. The emergence of large language models (LLMs) in medical diagnostics introduces a revolutionary potential to overcome these diagnostic hurdles. Despite recent advancements in artificial intelligence and LLMs demonstrating effectiveness in diagnosing and treating various diseases, their application in SpA remains underdeveloped. Currently, there is a notable absence of SpA-specific LLMs and an established benchmark for assessing the performance of such models in this particular field. Objective: Our objective is to develop a foundational medical model, creating a comprehensive evaluation benchmark tailored to the essential medical knowledge of SpA and its unique diagnostic and treatment protocols. The model, post-pretraining, will be subject to further enhancement through supervised fine-tuning. It is projected to significantly aid physicians in SpA diagnosis and treatment, especially in settings with limited access to specialized care. Furthermore, this initiative is poised to promote early and accurate SpA detection at the primary care level, thereby diminishing the risks associated with delayed or incorrect diagnoses. Methods: A rigorous benchmark, comprising 222 meticulously formulated multiple-choice questions on SpA, will be established and developed. These questions will be extensively revised to ensure their suitability for accurately evaluating LLMs’ performance in real-world diagnostic and therapeutic scenarios. Our methodology involves selecting and refining top foundational models using public data sets. The best-performing model in our benchmark will undergo further training. Subsequently, more than 80,000 real-world inpatient and outpatient cases from hospitals will enhance LLM training, incorporating techniques such as supervised fine-tuning and low-rank adaptation. We will rigorously assess the models’ generated responses for accuracy and evaluate their reasoning processes using the metrics of fluency, relevance, completeness, and medical proficiency. Results: Development of the model is progressing, with significant enhancements anticipated by early 2024. The benchmark, along with the results of evaluations, is expected to be released in the second quarter of 2024. Conclusions: Our trained model aims to capitalize on the capabilities of LLMs in analyzing complex clinical data, thereby enabling precise detection, diagnosis, and treatment of SpA. This innovation is anticipated to play a vital role in diminishing the disabilities arising from delayed or incorrect SpA diagnoses. By promoting this model across diverse health care settings, we anticipate a significant improvement in SpA management, culminating in enhanced patient outcomes and a reduced overall burden of the disease. International Registered Report Identifier (IRRID): DERR1-10.2196/57001
- Open Access
- 1 May 2024
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 19, 827-841
Non-Pharmacological Strategies for Managing Sarcopenia in Chronic Diseases
This article focuses on a range of non-pharmacological strategies for managing sarcopenia in chronic diseases, including exercise, dietary supplements, traditional Chinese exercise, intestinal microecology, and rehabilitation therapies for individuals with limited limb movement. By analyzing multiple studies, the article aims to summarize the available evidence to manage sarcopenia in individuals with chronic diseases. The results strongly emphasize the role of resistance training in addressing chronic diseases and secondary sarcopenia. Maintaining the appropriate frequency and intensity of resistance training can help prevent muscle atrophy and effectively reduce inflammation. Although aerobic exercise has limited ability to improve skeletal muscle mass, it does have some positive effects on physical function. Building upon this, the article explores the potential benefits of combined training approaches, highlighting their helpfulness for overall quality of life. Additionally, the article also highlights the importance of dietary supplements in combating muscle atrophy in chronic diseases. It focuses on the importance of protein intake, supplements rich in essential amino acids and omega-3, as well as sufficient vitamin D to prevent muscle atrophy. Combining exercise with dietary supplements appears to be an effective strategy for preventing sarcopenia, although the optimal dosage and type of supplement remain unclear. Furthermore, the article explores the potential benefits of intestinal microecology in sarcopenia. Probiotics, prebiotics, and bacterial products are suggested as new treatment options for sarcopenia. Additionally, emerging therapies such as whole body vibration training, blood flow restriction, and electrical stimulation show promise in treating sarcopenia with limited limb movement. Overall, this article provides valuable insights into non-pharmacological strategies for managing sarcopenia in individuals with chronic diseases. It emphasizes the importance of a holistic and integrated approach that incorporates exercise, nutrition, and multidisciplinary interventions, which have the potential to promote health in the elderly population. Future research should prioritize high-quality randomized controlled trials and utilize wearable devices, smartphone applications, and other advanced surveillance methods to investigate the most effective intervention strategies for sarcopenia associated with different chronic diseases.
- 1 May 2024
- Published by Taylor & Francis in Clinical Interventions in Aging
- Vol. ume 19, 827-841
Open AccessNon-Pharmacological Strategies for Managing Sarcopenia in Chronic Diseases
This article focuses on a range of non-pharmacological strategies for managing sarcopenia in chronic diseases, including exercise, dietary supplements, traditional Chinese exercise, intestinal microecology, and rehabilitation therapies for individuals with limited limb movement. By analyzing multiple studies, the article aims to summarize the available evidence to manage sarcopenia in individuals with chronic diseases. The results strongly emphasize the role of resistance training in addressing chronic diseases and secondary sarcopenia. Maintaining the appropriate frequency and intensity of resistance training can help prevent muscle atrophy and effectively reduce inflammation. Although aerobic exercise has limited ability to improve skeletal muscle mass, it does have some positive effects on physical function. Building upon this, the article explores the potential benefits of combined training approaches, highlighting their helpfulness for overall quality of life. Additionally, the article also highlights the importance of dietary supplements in combating muscle atrophy in chronic diseases. It focuses on the importance of protein intake, supplements rich in essential amino acids and omega-3, as well as sufficient vitamin D to prevent muscle atrophy. Combining exercise with dietary supplements appears to be an effective strategy for preventing sarcopenia, although the optimal dosage and type of supplement remain unclear. Furthermore, the article explores the potential benefits of intestinal microecology in sarcopenia. Probiotics, prebiotics, and bacterial products are suggested as new treatment options for sarcopenia. Additionally, emerging therapies such as whole body vibration training, blood flow restriction, and electrical stimulation show promise in treating sarcopenia with limited limb movement. Overall, this article provides valuable insights into non-pharmacological strategies for managing sarcopenia in individuals with chronic diseases. It emphasizes the importance of a holistic and integrated approach that incorporates exercise, nutrition, and multidisciplinary interventions, which have the potential to promote health in the elderly population. Future research should prioritize high-quality randomized controlled trials and utilize wearable devices, smartphone applications, and other advanced surveillance methods to investigate the most effective intervention strategies for sarcopenia associated with different chronic diseases.
- Open Access
- 1 February 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Assessing and Optimizing Large Language Models on Spondyloarthritis Multi-Choice Question Answering: Protocol for Enhancement and Assessment (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Spondyloarthritis (SpA), a chronic inflammatory disorder, predominantly impacts the sacroiliac joints and spine, significantly escalating the risk of disability. SpA’s complexity, as evidenced by its diverse clinical presentations and symptoms that often mimic other diseases, presents substantial challenges in its accurate diagnosis and differentiation. This complexity becomes even more pronounced in nonspecialist health care environments due to limited resources, resulting in delayed referrals, increased misdiagnosis rates, and exacerbated disability outcomes for patients with SpA. The emergence of large language models (LLMs) in medical diagnostics introduces a revolutionary potential to overcome these diagnostic hurdles. Despite recent advancements in artificial intelligence and LLMs demonstrating effectiveness in diagnosing and treating various diseases, their application in SpA remains underdeveloped. Currently, there is a notable absence of SpA-specific LLMs and an established benchmark for assessing the performance of such models in this particular field. Objective: Our objective is to develop a foundational medical model, creating a comprehensive evaluation benchmark tailored to the essential medical knowledge of SpA and its unique diagnostic and treatment protocols. The model, post-pretraining, will be subject to further enhancement through supervised fine-tuning. It is projected to significantly aid physicians in SpA diagnosis and treatment, especially in settings with limited access to specialized care. Furthermore, this initiative is poised to promote early and accurate SpA detection at the primary care level, thereby diminishing the risks associated with delayed or incorrect diagnoses. Methods: A rigorous benchmark, comprising 222 meticulously formulated multiple-choice questions on SpA, will be established and developed. These questions will be extensively revised to ensure their suitability for accurately evaluating LLMs’ performance in real-world diagnostic and therapeutic scenarios. Our methodology involves selecting and refining top foundational models using public data sets. The best-performing model in our benchmark will undergo further training. Subsequently, more than 80,000 real-world inpatient and outpatient cases from hospitals will enhance LLM training, incorporating techniques such as supervised fine-tuning and low-rank adaptation. We will rigorously assess the models’ generated responses for accuracy and evaluate their reasoning processes using the metrics of fluency, relevance, completeness, and medical proficiency. Results: Development of the model is progressing, with significant enhancements anticipated by early 2024. The benchmark, along with the results of evaluations, is expected to be released in the second quarter of 2024. Conclusions: Our trained model aims to capitalize on the capabilities of LLMs in analyzing complex clinical data, thereby enabling precise detection, diagnosis, and treatment of SpA. This innovation is anticipated to play a vital role in diminishing the disabilities arising from delayed or incorrect SpA diagnoses. By promoting this model across diverse health care settings, we anticipate a significant improvement in SpA management, culminating in enhanced patient outcomes and a reduced overall burden of the disease.
- 1 February 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAssessing and Optimizing Large Language Models on Spondyloarthritis Multi-Choice Question Answering: Protocol for Enhancement and Assessment (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Spondyloarthritis (SpA), a chronic inflammatory disorder, predominantly impacts the sacroiliac joints and spine, significantly escalating the risk of disability. SpA’s complexity, as evidenced by its diverse clinical presentations and symptoms that often mimic other diseases, presents substantial challenges in its accurate diagnosis and differentiation. This complexity becomes even more pronounced in nonspecialist health care environments due to limited resources, resulting in delayed referrals, increased misdiagnosis rates, and exacerbated disability outcomes for patients with SpA. The emergence of large language models (LLMs) in medical diagnostics introduces a revolutionary potential to overcome these diagnostic hurdles. Despite recent advancements in artificial intelligence and LLMs demonstrating effectiveness in diagnosing and treating various diseases, their application in SpA remains underdeveloped. Currently, there is a notable absence of SpA-specific LLMs and an established benchmark for assessing the performance of such models in this particular field. Objective: Our objective is to develop a foundational medical model, creating a comprehensive evaluation benchmark tailored to the essential medical knowledge of SpA and its unique diagnostic and treatment protocols. The model, post-pretraining, will be subject to further enhancement through supervised fine-tuning. It is projected to significantly aid physicians in SpA diagnosis and treatment, especially in settings with limited access to specialized care. Furthermore, this initiative is poised to promote early and accurate SpA detection at the primary care level, thereby diminishing the risks associated with delayed or incorrect diagnoses. Methods: A rigorous benchmark, comprising 222 meticulously formulated multiple-choice questions on SpA, will be established and developed. These questions will be extensively revised to ensure their suitability for accurately evaluating LLMs’ performance in real-world diagnostic and therapeutic scenarios. Our methodology involves selecting and refining top foundational models using public data sets. The best-performing model in our benchmark will undergo further training. Subsequently, more than 80,000 real-world inpatient and outpatient cases from hospitals will enhance LLM training, incorporating techniques such as supervised fine-tuning and low-rank adaptation. We will rigorously assess the models’ generated responses for accuracy and evaluate their reasoning processes using the metrics of fluency, relevance, completeness, and medical proficiency. Results: Development of the model is progressing, with significant enhancements anticipated by early 2024. The benchmark, along with the results of evaluations, is expected to be released in the second quarter of 2024. Conclusions: Our trained model aims to capitalize on the capabilities of LLMs in analyzing complex clinical data, thereby enabling precise detection, diagnosis, and treatment of SpA. This innovation is anticipated to play a vital role in diminishing the disabilities arising from delayed or incorrect SpA diagnoses. By promoting this model across diverse health care settings, we anticipate a significant improvement in SpA management, culminating in enhanced patient outcomes and a reduced overall burden of the disease.