Accuracy Assessment of Chinese Large Language Models in Psoriasis Management: A Multicenter Expert Consensus Study

Accuracy Assessment of Chinese Large Language Models in Psoriasis Management: A Multicenter Expert Consensus Study | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Accuracy Assessment of Chinese Large Language Models in Psoriasis Management: A Multicenter Expert Consensus Study Chaofeng Chen, Hao Huang, Bo Yu, Xiaoping Hu, Jialiang Shi, Fangpei Wu, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8155599/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 16 You are reading this latest preprint version Abstract Background Psoriasis patients in China face significant challenges due to insufficient disease knowledge and limited access to medical resources, creating a need for reliable educational tools. Objectives This multicenter consensus study aimed to systematically evaluate the consultation quality of mainstream Chinese large language models (LLMs) for psoriasis patient education. Methods "365 Questions on Psoriasis" was jointly compiled by 109 Chinese psoriasis experts. Using an expert assessment methodology, nine dermatologists curated 40 high-frequency clinical questions from the book across five domains (etiology, triggers, treatment, management, psychosocial impact). Four Chinese LLMs (DeepSeek-R1, DeepSeek-V3, GLM-4, Qwen-3) were evaluated through double-blind scoring on a 10-point Likert scale assessing accuracy, completeness, clarity, and safety. Results Performance varied significantly, with mean scores ranging from 5.95 to 9.88 (SD: 0-3.05). Qwen-3 achieved the highest average score (9.12), while GLM-4 showed the greatest inconsistency. All responses avoided dangerous content, and 87.5% proactively emphasized the necessity of consulting a physician. However, 12.5% of responses deviated from evidence-based guidelines, particularly on complex topics like biologics and management. Conclusions Chinese LLMs show substantial potential for psoriasis education by providing generally safe information and appropriately directing users to doctors. However, current limitations exist, including performance inconsistency and occasional deviations from guidelines on specialized topics, indicating they are not yet replacements for professional medical. Health sciences/Diseases Health sciences/Health care Health sciences/Medical research psoriasis artificial intelligence large language models patient education medical dermatology Figures Figure 1 Figure 2 Figure 3 Figure 4 Background Psoriasis is a common chronic inflammatory skin disease affecting millions worldwide, characterized by erythema, scaling, and itching. Despite advancements in treatments—including topical medications, phototherapy, and biologics—patients still face reduced quality of life and low treatment satisfaction. Studies show that over 50% of moderate-to-severe psoriasis patients report poor disease control [ 1 ], impacting both physical health and psychosocial functioning. Effective psoriasis management requires collaborative doctor-patient efforts, involving complex knowledge about etiology, recurrence mechanisms, treatment options, and lifestyle adjustments [ 2 ]. Patient education is crucial in psoriasis management. Adequate understanding of the disease, triggers, and treatment options can significantly improve adherence and self-management, enhancing quality of life. However, traditional education methods, such as in-person consultations or printed materials, are time-consuming and burdensome for clinicians [ 3 ]. With the rise of digital health, patients increasingly seek medical information online, further straining healthcare providers [ 4 ]. Recent advances in artificial intelligence (AI) offer new possibilities for medical communication [ 5 ]. Large language models, as advanced natural language processing tools, can generate human-like responses and are widely used in education, customer service, and medical consultations [ 6 ]. In healthcare, LLMs hold promise for delivering quick, accessible information, particularly in non-English contexts like Chinese. However, their application requires rigorous evaluation to ensure accuracy, reliability, and safety [ 7 ]. This study evaluates four mainstream Chinese closed-source LLMs in addressing common psoriasis patient queries. By systematically analyzing response quality, we aim to guide clinicians and patients in using AI tools and inform future research and development. Methods Study Design This multicenter expert consensus study assessed the performance of four Chinese LLMs in responding to psoriasis-related questions. The study comprised three phases: question collection, model testing, and expert evaluation. Model Selection Four mainstream Chinese closed-source LLMs were selected: DeepSeek-R1 [ 8 ], DeepSeek-V3 [ 9 ], Qwen-3 [ 10 ], and GLM-4 [ 11 ]. These models were chosen for their strong performance in Chinese natural language processing tasks and widespread use. Question Collection Nine dermatologists from multiple hospitals contributed 40 high-frequency psoriasis-related questions. Each expert provided up to 10 questions, ensuring coverage of five key domains: Disease etiology and pathophysiology Triggers and recurrence mechanisms Treatment options, including biologics Disease management and lifestyle adjustments Psychosocial impact and quality of life All questions were formulated in Chinese, reflecting real-world patient inquiries, and were reviewed for relevance and representativeness. Data Collection The 40 questions were input into the four LLMs, and responses were recorded for evaluation. Evaluation Method Nine dermatologists independently assessed response quality using a 10-point Likert scale (1 = lowest, 10 = highest). Criteria included: Accuracy: Alignment with evidence-based medicine Completeness: Coverage of necessary information Clarity: Ease of understanding Safety: Absence of dangerous or misleading content Experts also noted deviations from evidence-based guidelines and whether responses included recommendations to consult a physician. Data Analysis Scores from the nine experts were aggregated to calculate mean scores and standard deviations for each model. Representative responses and score distributions are presented in Table 1 and Figs. 1 – 4 . Table 1 A question 'What are the side effects of long-term topical steroid use in psoriasis patients?' answered by Deepseek-R1, Deepseek-V3, Qwen-3, and Glm-4. Model Answer Mean score Standard deviation Deepseek-R1 Although long-term use of topical corticosteroids (such as hydrocortisone, halobetasol, etc.) by psoriasis patients can effectively relieve inflammation and itching, it may cause the following side effects and should be used cautiously under the guidance of a doctor: …… 8.7 0.58 Deepseek-V3 Long-term use of topical corticosteroids (hereinafter referred to as "steroids") by psoriasis patients may lead to various side effects, particularly evident with improper use (such as overdose, excessive area, long-term continuous use). The following are the main categories of side effects: …… 8.81 0.44 Qwen-3 Although long-term topical use of corticosteroids (commonly known as "steroids") in psoriasis patients has good short-term efficacy in controlling the condition, reducing inflammation, and scaling, improper or prolonged use may lead to a series of side effects. The following are common topical corticosteroid side effects: …… 9.12 0.59 Glm-4 Psoriasis is a chronic skin disease often characterized by red patches and scales on the skin. Corticosteroids (such as glucocorticoids) are common topical medications for treating psoriasis, but long-term use may bring some side effects. Here are some common side effects: …… 7.53 1.08 Results Overall Scores The four LLMs achieved mean scores ranging from 5.95 to 9.88 (SD: 0–3.05), indicating high expert satisfaction. Table 1 displays responses to a representative question: "What are the side effects of long-term topical steroid use in psoriasis patients?" Score Distribution Figures 1 – 4 illustrate score distributions for each model. DeepSeek-R1 and DeepSeek-V3 scores clustered between 7–9, while Qwen-3 showed more consistent high ratings. GLM-4 exhibited greater variability, reflecting uneven performance. Response Characteristics All models avoided dangerous or misleading information, a key positive finding. Most responses included disclaimers like "consult a physician," enhancing safety. However, some answers scored lower due to incomplete or non-evidence-based content, particularly for complex topics like biologics. Discussion This multicenter expert consensus study represents the first comprehensive evaluation of Chinese large language models in the context of psoriasis patient education. The findings reveal a dual narrative of notable promise alongside critical limitations, offering valuable insights for both clinical practice and AI development. The observed performance variation across models—with mean scores ranging from 5.95 to 9.88—clearly demonstrates that not all commercially available LLMs are equally suited for specialized medical consultation. Among the evaluated models, Qwen-3 emerged as the top performer, achieving a mean score of 9.12. This success underscores the technical feasibility of developing LLMs capable of delivering high-quality, patient-centered responses. In contrast, GLM-4 exhibited significant inconsistency in its responses, with a standard deviation of up to 3.05, highlighting the ongoing challenges in ensuring clinical reliability across diverse medical queries. A key strength identified in this study was the universal adherence of all models to fundamental safety protocols. Notably, every evaluated LLM successfully avoided generating dangerous or misleading content, and an overwhelming majority (87.5%) proactively emphasized the necessity of consulting a physician. This represents a substantial improvement over traditional online health information sources, which often lack rigorous oversight and may propagate misinformation. Furthermore, the models excelled in providing clear, structured explanations for foundational topics such as the side effects of topical steroids. By distilling complex medical concepts into patient-friendly language, these LLMs demonstrated their potential to serve as valuable educational tools. Such capabilities could significantly reduce the burden on clinicians by addressing routine patient inquiries, allowing healthcare providers to allocate more time to complex cases and personalized care. Despite these strengths, the study also uncovered persistent gaps in the models' performance, particularly in specialized areas of psoriasis management. Approximately 12.5% of responses deviated from evidence-based guidelines, with notable inaccuracies arising in discussions of biologics' mechanisms of action, combination therapy sequencing, and complex management scenarios. These inconsistencies likely stem from inadequate domain-specific training data and insufficient clinical validation processes. While the models performed well in identifying common psoriasis triggers—such as stress and infections—their management advice often lacked depth and personalization. The tendency to provide generalized responses represents a critical limitation, as it fails to account for the heterogeneous nature of psoriasis, which manifests in diverse phenotypes and requires tailored treatment approaches. These findings resonate with broader observations in the literature regarding the limitations of LLMs in medical applications. Prior studies have noted that current models often struggle with context-dependent reasoning, a capability essential for managing chronic conditions like psoriasis, where individualized care is paramount. Our study extends these observations to the Chinese-language dermatology context, where linguistic nuances and regional treatment preferences introduce additional layers of complexity. For instance, while the models occasionally referenced traditional Chinese medicine, these mentions were not systematically integrated into evidence-based recommendations, reflecting a gap in culturally relevant training data. In summary, this study highlights both the potential and the current limitations of Chinese LLMs in psoriasis patient education. While they excel in safety and foundational knowledge dissemination, their performance in specialized and personalized care remains inconsistent. Addressing these gaps will require enhanced collaboration between AI developers and clinical experts, as well as the incorporation of more robust, domain-specific training datasets. Until these improvements are realized, LLMs should be viewed as supplementary tools—valuable for basic education but insufficient for guiding complex treatment decisions without clinician oversight. Conclusions Chinese LLMs demonstrate substantial potential as supplementary tools for psoriasis patient education, particularly in improving health literacy regarding disease fundamentals, medication safety, and basic self-management. Qwen-3 currently delivers the most clinically reliable performance among evaluated models. However, significant limitations persist in handling specialized therapeutic areas (notably biologics and complex management scenarios) and providing individualized recommendations. Key implications for practice: ​ ​Selective Implementation​ ​: Healthcare systems should prioritize rigorously validated models like Qwen-3 for delivering standardized educational content about topical therapies and lifestyle management. ​ ​Mandatory Human Oversight​ ​: All LLM-generated advice regarding systemic treatments, biologics, or treatment modifications must undergo clinician verification before dissemination to patients. ​ ​Clear Scope Definition​ ​: Patient-facing interfaces should explicitly state model limitations, particularly regarding treatment individualization and complex case management. ​ ​Continuous Validation Framework​ ​: Developers must establish ongoing clinical evaluation mechanisms, especially for rapidly evolving therapeutic domains like biologics. Future development should focus on enhancing evidence-based reasoning through curated dermatology datasets, implementing specialist review protocols, and developing hybrid human-AI education systems. Until these advancements are realized, LLMs should be positioned strictly as informational supplements for clinician-guided psoriasis education. Declarations Ethics approval and consent to participate : Not applicable. Consent for publication : Not applicable. Competing interests: The authors have no conflict of interest to declare. Funding: This work was supported by Natural Science Foundation of Guangdong Province (No.2025A1515010947) and Shenzhen Sanming Project (No. SZSM202311029). Author Contribution BY, XH, JS, FW, KZ, YY, XZ, JW, ZC collected questions and LLM scores. JW collected data. CC, HH conducted data statistics and analysis, and CC was a major contributor in writing the manuscript. JH, XL designed and guided the experiments, and provided supervision. All authors read and approved the final manuscript. Acknowledgements: The study was supported by Shenzhen Research Grants(200901013). We thank Shenzhen Public Service Platform of Biomedical Technology for the technical support. Data Availability All data supporting the findings of this study are available within the paper and its Supplementary Information. References Raharja, A., Mahil, S. K. & Barker, J. N. Psoriasis: a brief overview[J]. Clin. Med. 21 (3), 170–173 (2021). Li, T. et al. Potential effects and mechanisms of Chinese herbal medicine in the treatment of psoriasis[J]. J. Ethnopharmacol. 294 , 115275 (2022). Dressler, C. et al. Therapeutic patient education and self-management support for patients with psoriasis–a systematic review[J]. JDDG: J. der Deutschen Dermatologischen Gesellschaft . 17 (7), 685–695 (2019). Jiang, Y. et al. Patients’ and healthcare providers’ perceptions and experiences of telehealth use and online health information use in chronic disease management for older patients with chronic obstructive pulmonary disease: a qualitative study[J]. BMC Geriatr. 22 (1), 9 (2022). Alowais, S. A. et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice[J]. BMC Med. Educ. 23 (1), 689 (2023). Lucas, H. C., Upperman, J. S. & Robinson, J. R. A systematic review of large language models and their implications in medical education[J]. Med. Educ. 58 (11), 1276–1285 (2024). Yang, R. et al. Large language models in health care: Development, applications, and challenges[J]. Health Care Sci. 2 (4), 255–263 (2023). Guo, D. et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning[J]. (2025). arXiv preprint arXiv:2501.12948. Liu, A. et al. Deepseek-v3 technical report[J]. arXiv preprint arXiv:2412.19437, (2024). Yang, A. et al. Qwen3 technical report[J]. arXiv preprint arXiv:2505.09388, (2025). GLM, T. et al. Chatglm: A family of large language models from glm-130b to glm-4 all tools[J]. (2024). arXiv preprint arXiv:2406.12793. Additional Declarations No competing interests reported. Supplementary Files PsoriasisHighFrequencyQuestions.pdf Rating.rar LargeModelResponseResults.rar Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 20 Mar, 2026 Reviews received at journal 19 Mar, 2026 Reviews received at journal 12 Mar, 2026 Reviewers agreed at journal 12 Mar, 2026 Reviews received at journal 10 Mar, 2026 Reviews received at journal 09 Mar, 2026 Reviews received at journal 05 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 05 Mar, 2026 Reviewers agreed at journal 03 Mar, 2026 Reviewers agreed at journal 03 Mar, 2026 Reviewers invited by journal 19 Jan, 2026 Editor assigned by journal 05 Jan, 2026 Editor invited by journal 03 Dec, 2025 Submission checks completed at journal 02 Dec, 2025 First submitted to journal 02 Dec, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8155599","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":578041386,"identity":"d6f40890-3d78-4b07-b9ea-1e99b5246631","order_by":0,"name":"Chaofeng Chen","email":"","orcid":"","institution":"Department of Dermatology, the Second Affiliated Hospital of Xi’an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Chaofeng","middleName":"","lastName":"Chen","suffix":""},{"id":578041388,"identity":"71f385f3-efea-4ca1-b23e-bac52660309b","order_by":1,"name":"Hao Huang","email":"","orcid":"","institution":"College of Electronics and Information Engineering, Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Huang","suffix":""},{"id":578041390,"identity":"443ba1dc-246d-494c-ae3f-820e4bd158d0","order_by":2,"name":"Bo Yu","email":"","orcid":"","institution":"Department of Dermatology, Peking University Shenzhen Hospital","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Yu","suffix":""},{"id":578041394,"identity":"bd25f8b0-215d-4cf1-8d0b-b6a8e4402ca8","order_by":3,"name":"Xiaoping Hu","email":"","orcid":"","institution":"Department of Dermatology, Peking University Shenzhen Hospital","correspondingAuthor":false,"prefix":"","firstName":"Xiaoping","middleName":"","lastName":"Hu","suffix":""},{"id":578041395,"identity":"0363007b-4c3c-4be3-8187-4cbdbdbed7b5","order_by":4,"name":"Jialiang Shi","email":"","orcid":"","institution":"Department of Dermatology, Shenzhen University General Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jialiang","middleName":"","lastName":"Shi","suffix":""},{"id":578041396,"identity":"3c8c2210-2dcc-4e09-bd63-e5c1f57750cb","order_by":5,"name":"Fangpei Wu","email":"","orcid":"","institution":"Department of Dermatology, Changsha Central Hospital","correspondingAuthor":false,"prefix":"","firstName":"Fangpei","middleName":"","lastName":"Wu","suffix":""},{"id":578041397,"identity":"85bec5f0-a51e-4ef4-a9d5-a625f0322910","order_by":6,"name":"Keren Zhou","email":"","orcid":"","institution":"Department of Dermatology, Peking University Shenzhen Hospital","correspondingAuthor":false,"prefix":"","firstName":"Keren","middleName":"","lastName":"Zhou","suffix":""},{"id":578041398,"identity":"03b256ea-a4a8-4dc7-9a32-b8faf45e1072","order_by":7,"name":"Yufang Yao","email":"","orcid":"","institution":"Department of Dermatology, Aerospace Central Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yufang","middleName":"","lastName":"Yao","suffix":""},{"id":578041399,"identity":"7024c82b-10be-4346-9146-7b1c72cd93f1","order_by":8,"name":"Xingyun Zhao","email":"","orcid":"","institution":"Affiliated Hangzhou First People's Hospital, School of Medicine, Westlake University, Hangzhou","correspondingAuthor":false,"prefix":"","firstName":"Xingyun","middleName":"","lastName":"Zhao","suffix":""},{"id":578041400,"identity":"4488dea6-f474-4c16-a8ef-3c5fc5a1e498","order_by":9,"name":"Jieyi Wang","email":"","orcid":"","institution":"Department of Dermatology, Peking University Shenzhen Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jieyi","middleName":"","lastName":"Wang","suffix":""},{"id":578041401,"identity":"0d39a532-11c7-4708-8394-86c4350d0047","order_by":10,"name":"Zhuoxuan Chen","email":"","orcid":"","institution":"Department of Dermatology, Peking University Shenzhen Hospital","correspondingAuthor":false,"prefix":"","firstName":"Zhuoxuan","middleName":"","lastName":"Chen","suffix":""},{"id":578041402,"identity":"5bdcc72f-fb3a-4912-96df-7d51b77cfdaf","order_by":11,"name":"Jingwen Wu","email":"","orcid":"","institution":"Department of Dermatology, Peking University Shenzhen Hospital","correspondingAuthor":false,"prefix":"","firstName":"Jingwen","middleName":"","lastName":"Wu","suffix":""},{"id":578041403,"identity":"1b0cdb29-d93d-47e8-bfec-60e22e63d8fc","order_by":12,"name":"Jianjun Huang","email":"","orcid":"","institution":"College of Electronics and Information Engineering, Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Jianjun","middleName":"","lastName":"Huang","suffix":""},{"id":578041404,"identity":"7886749c-44dd-4cb3-9918-0a29b7786549","order_by":13,"name":"Xiaoli Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtklEQVRIiWNgGAWjYHCCBIYHDDY8/PwNpGhJYEiTkZxxgDR7DtsYNCQQqZp/dsPDDwk153kMGA4wfviYQ4QWiTsHkiUSjt3mMWduYJacuY0Ya24kJEgksN3msWw4wMbMS4wW+RsJyT8S/p3jMTiQQKQWgxsJaRKJbQdI0GII1GKR2JfMIznjYDNxfpG7kZN848M3O3t+/uaDHz4S5X0GngQog7GBKPVAwH6AWJWjYBSMglEwUgEAAHA5BhNyF04AAAAASUVORK5CYII=","orcid":"","institution":"Department of Dermatology, the Second Affiliated Hospital of Xi’an Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Xiaoli","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-11-19 13:08:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8155599/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8155599/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100952206,"identity":"0f4efdc7-6b9a-4714-ac41-997810e61bb2","added_by":"auto","created_at":"2026-01-23 07:12:13","extension":"jpg","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74529,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/b11338947a4effda2ce2ef41.jpg"},{"id":100928843,"identity":"00d3c8e6-6997-4914-bc13-683b0d56755e","added_by":"auto","created_at":"2026-01-23 00:31:59","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":164848,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/3ab85ee24131c3398907a493.docx"},{"id":100951699,"identity":"e436d420-045c-4134-9fb2-fb246dc41b4e","added_by":"auto","created_at":"2026-01-23 07:11:06","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76540,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/c69f8fa95f7c5abd7a7a134b.jpg"},{"id":100928841,"identity":"884c4546-87e5-4152-a2fb-2cf8678f2704","added_by":"auto","created_at":"2026-01-23 00:31:59","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31617,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/0ee07867b8ba7c5a8e070ec2.docx"},{"id":100951349,"identity":"c5fdf682-a405-4559-96eb-848efa701002","added_by":"auto","created_at":"2026-01-23 07:10:31","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75329,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/f6816e17c0be2ec8722929e2.jpg"},{"id":100952174,"identity":"e343affb-7a72-44c7-b666-9ea7c24a894a","added_by":"auto","created_at":"2026-01-23 07:12:07","extension":"jpg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69561,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/f8f48f41a017df5019a806a5.jpg"},{"id":100928846,"identity":"36f93de3-a120-40d9-a6b8-006e60d01f32","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"json","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13372,"visible":true,"origin":"","legend":"","description":"","filename":"c3072b4a0613411393368bdbccb48947.json","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/9be9cad18b372b4f492da487.json"},{"id":100950897,"identity":"5c1f60a2-6cbd-4e56-ae91-071465436dc4","added_by":"auto","created_at":"2026-01-23 07:09:28","extension":"rar","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1713785,"visible":true,"origin":"","legend":"","description":"","filename":"LargeModelResponseResults.rar","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/0201e6538137241b1dd3aef7.rar"},{"id":100951185,"identity":"34a50a71-6366-45c2-be3f-16f2266915a2","added_by":"auto","created_at":"2026-01-23 07:10:09","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92185,"visible":true,"origin":"","legend":"","description":"","filename":"PsoriasisHighFrequencyQuestions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/6dc07eca8008865b142f6c99.pdf"},{"id":101202592,"identity":"cca232ff-968c-4490-aa73-1980de6a4dd2","added_by":"auto","created_at":"2026-01-27 09:36:35","extension":"rar","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30369,"visible":true,"origin":"","legend":"","description":"","filename":"Rating.rar","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/ee418184a6de01deb2ff53ab.rar"},{"id":101296563,"identity":"abcb08db-920b-4ed1-a9d4-d9482b11de03","added_by":"auto","created_at":"2026-01-28 09:15:43","extension":"xml","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67396,"visible":true,"origin":"","legend":"","description":"","filename":"c3072b4a0613411393368bdbccb489471enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/4fd1c88e56d5e0d0138cbdd2.xml"},{"id":100952122,"identity":"76f93da8-f3de-4424-8d2d-8dae20a81aa4","added_by":"auto","created_at":"2026-01-23 07:11:58","extension":"jpg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74529,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/91d65914ef2b7fc6aab6177c.jpg"},{"id":100951626,"identity":"ad3cee36-5dfc-4da8-b335-316d898e2fb7","added_by":"auto","created_at":"2026-01-23 07:11:00","extension":"jpg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76540,"visible":true,"origin":"","legend":"","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/5e89f476c9463ce32671057f.jpg"},{"id":100928856,"identity":"0ea57c33-4fd7-4c1c-834a-82183cb5d49a","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"jpg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75329,"visible":true,"origin":"","legend":"","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/91bd4daa860e7bb869a243d6.jpg"},{"id":100950891,"identity":"7a3c6cec-655f-4f33-8276-06b20fc8a721","added_by":"auto","created_at":"2026-01-23 07:09:28","extension":"jpg","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69561,"visible":true,"origin":"","legend":"","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/8663ce88fcad62e23843b0df.jpg"},{"id":100952232,"identity":"45b8920e-e1fc-4c90-8138-51eec0b1e20f","added_by":"auto","created_at":"2026-01-23 07:12:17","extension":"eps","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/defd1f72af7afa42cc06b62b.eps"},{"id":100951682,"identity":"d68a7a2d-7399-4531-84c4-13f83f2bdf76","added_by":"auto","created_at":"2026-01-23 07:11:05","extension":"eps","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/674cf37e1a3514df42f1defd.eps"},{"id":100951579,"identity":"10ebeb28-5703-48de-8fab-97a22e40d544","added_by":"auto","created_at":"2026-01-23 07:10:53","extension":"eps","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/8521e50ac9d4fbd15027eee7.eps"},{"id":100951904,"identity":"352a34e0-2c16-48e6-b796-07154b51eec9","added_by":"auto","created_at":"2026-01-23 07:11:24","extension":"eps","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/fc8c08c1ae8154c7317c0fe9.eps"},{"id":100951604,"identity":"40df6a1f-0a5c-4d29-80a4-8f49c55ebaac","added_by":"auto","created_at":"2026-01-23 07:10:57","extension":"eps","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/722b5a3d7a56ed7a49e3a24c.eps"},{"id":100928850,"identity":"1a254193-4911-4b29-a550-486856de3204","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"eps","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/8f0962665e425d7c3d4967a6.eps"},{"id":100951920,"identity":"e4b49f58-7758-47c8-92a8-e61e09422478","added_by":"auto","created_at":"2026-01-23 07:11:32","extension":"eps","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/623285c54ee6ea830758cb51.eps"},{"id":100928872,"identity":"66c6c72d-f4de-4011-ab8c-469711d36b82","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"eps","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/6a33839c7869b5cdd9c123c1.eps"},{"id":100951701,"identity":"a990720d-dd86-4c38-a1e1-c6888e89e994","added_by":"auto","created_at":"2026-01-23 07:11:06","extension":"eps","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/037a893e5b508e3288dd992e.eps"},{"id":100928855,"identity":"48059cb8-ffcf-48b7-acaa-dcca5fe347c8","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"eps","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/fad1150d628b6f2914a9eea1.eps"},{"id":100928863,"identity":"4041b202-07cb-4135-8f43-b1b78e496e9c","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"eps","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/fc2d1a0869f72e9fed7b1bf3.eps"},{"id":100928865,"identity":"2d008916-4d6b-437f-ba29-60304932d942","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"eps","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/e4c65e7966ffae52434b0b88.eps"},{"id":101202515,"identity":"64aabc77-3040-49fc-91b7-b57a6ce776cb","added_by":"auto","created_at":"2026-01-27 09:35:37","extension":"eps","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/98fdb2542b632c54eccb4778.eps"},{"id":100951756,"identity":"fd1bc3c9-0a6d-4b4e-9d41-3d8931101d5e","added_by":"auto","created_at":"2026-01-23 07:11:12","extension":"eps","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/52d084e50653e4bc87bd56e5.eps"},{"id":100951114,"identity":"54dcf456-1950-4c4a-ae1e-6a3fdef703b5","added_by":"auto","created_at":"2026-01-23 07:10:00","extension":"eps","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/b9dd2aa815837edc42704d6e.eps"},{"id":100951738,"identity":"ab53dbc7-3a3c-4137-bd39-235847c0a4ff","added_by":"auto","created_at":"2026-01-23 07:11:10","extension":"eps","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/c7da32d7b937691de5697e94.eps"},{"id":100928869,"identity":"b65fd5e7-11be-4ad5-b073-1f39f1eacf17","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"eps","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":423,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/022a26ded45566151996940d.eps"},{"id":100928861,"identity":"e2cf79ce-8aae-42fb-8579-26ab62efa43e","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37607,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/c99ad4143edc7d2de711f8df.png"},{"id":100952035,"identity":"7e6d967a-8bf5-4ac8-90b8-a1957828a6e5","added_by":"auto","created_at":"2026-01-23 07:11:43","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38468,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/ef1d326ccbd2ecfd5bd3b6f4.png"},{"id":100928870,"identity":"6d1de62f-d644-48d8-8d9c-428d21d04b6c","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35436,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/cdd73c422e28c1486093cc40.png"},{"id":100928868,"identity":"69b32473-0d11-402e-8c48-afca7bd694bc","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34747,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/14c4abf88fafabc855d8cc86.png"},{"id":100928864,"identity":"f9ecd60a-8bf7-4a8a-b074-6c7995c16927","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17591,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/d62377f4a909807e4017606a.png"},{"id":101202645,"identity":"a5e29153-fbbe-4f1c-a22c-8385d4b0e272","added_by":"auto","created_at":"2026-01-27 09:36:54","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17637,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/564c29b3d71acbf8798dc72d.png"},{"id":100928866,"identity":"21a7041d-95b2-474b-bf54-a23dc9aed873","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18601,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/961bd0bf6b067e6dc2ff7997.png"},{"id":100928874,"identity":"b9d44f05-17a8-4175-aa0c-d46dec681749","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14853,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/4fb2ff29041710755483a0a3.png"},{"id":100928873,"identity":"5d87973f-a91c-4420-9dca-2c1cf3b0c654","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12725,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/93601c145b61dd6d44c1f5a9.png"},{"id":100928867,"identity":"3c3b2f42-a78c-440b-bf32-0905c3cfb48a","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13060,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/fec5315a8010018a91c22697.png"},{"id":100928871,"identity":"eab909b5-6906-4756-9298-affe770445c0","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12766,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/e54f7c81d11a21b6f253e332.png"},{"id":100928877,"identity":"810545eb-216a-4161-99ba-dded66028cb6","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11922,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/62885b746b4e4bd6d88c3832.png"},{"id":100928858,"identity":"11a008b2-8c49-4347-86a0-b780d4640df1","added_by":"auto","created_at":"2026-01-23 00:32:00","extension":"xml","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66612,"visible":true,"origin":"","legend":"","description":"","filename":"c3072b4a0613411393368bdbccb489471structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/6a289d1911b8d653e92ec747.xml"},{"id":100928876,"identity":"f66c0f53-90a4-4f6c-9416-c2f66a04369a","added_by":"auto","created_at":"2026-01-23 00:32:01","extension":"html","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79618,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/dcb135c8bd4687f5d6a1a27a.html"},{"id":100928835,"identity":"3429961a-0c4c-4da5-a582-29fa4ddc042b","added_by":"auto","created_at":"2026-01-23 00:31:59","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":74529,"visible":true,"origin":"","legend":"\u003cp\u003eEvaluation scores of Deepseek-R1's responses given by each dermatologist.\u003c/p\u003e","description":"","filename":"Figure1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/b3a300b688b74b18a2d081ef.jpg"},{"id":100928837,"identity":"f32ded9d-a9d2-429c-99b8-d5db55f9c8fe","added_by":"auto","created_at":"2026-01-23 00:31:59","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":76540,"visible":true,"origin":"","legend":"\u003cp\u003eEvaluation scores of Deepseek-V3's responses given by each dermatologist.\u003c/p\u003e","description":"","filename":"Figure2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/e2dd6b2e5456906b33848c8e.jpg"},{"id":100928844,"identity":"356ba92f-2d33-4ab7-9e33-a39126100936","added_by":"auto","created_at":"2026-01-23 00:31:59","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":75329,"visible":true,"origin":"","legend":"\u003cp\u003eEvaluation scores of Qwen-3's responses given by each dermatologist.\u003c/p\u003e","description":"","filename":"Figure3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/9241d5b17e7263862f7fe691.jpg"},{"id":101296649,"identity":"206027fc-cac1-46a2-a0cc-1179a42ac153","added_by":"auto","created_at":"2026-01-28 09:18:02","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":69561,"visible":true,"origin":"","legend":"\u003cp\u003eEvaluation scores of Glm-4's responses given by each dermatologist.\u003c/p\u003e","description":"","filename":"Figure4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/57a70397eb67affc6ed36e11.jpg"},{"id":101298938,"identity":"6fedea0b-0854-498b-8ebc-23ea4d336a16","added_by":"auto","created_at":"2026-01-28 09:37:55","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":898365,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/82e22d84-d5a5-4c94-be83-0c649cf62bd4.pdf"},{"id":100951274,"identity":"24f8c34d-a1b4-439c-b448-214d89493f9f","added_by":"auto","created_at":"2026-01-23 07:10:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":92185,"visible":true,"origin":"","legend":"","description":"","filename":"PsoriasisHighFrequencyQuestions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/fd0c50b48506d904dd4cd88e.pdf"},{"id":100951570,"identity":"d4ec87b6-6fbe-4cf6-9e2b-e07ec0928ff1","added_by":"auto","created_at":"2026-01-23 07:10:53","extension":"rar","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":30369,"visible":true,"origin":"","legend":"","description":"","filename":"Rating.rar","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/ed260dabf42658dd90b6db6a.rar"},{"id":100928842,"identity":"09681e9a-3374-4efd-8a3e-a6b08d5a075a","added_by":"auto","created_at":"2026-01-23 00:31:59","extension":"rar","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":1713785,"visible":true,"origin":"","legend":"","description":"","filename":"LargeModelResponseResults.rar","url":"https://assets-eu.researchsquare.com/files/rs-8155599/v1/395b6a95f3ebf8cee144e38a.rar"}],"financialInterests":"No competing interests reported.","formattedTitle":"Accuracy Assessment of Chinese Large Language Models in Psoriasis Management: A Multicenter Expert Consensus Study","fulltext":[{"header":"Background","content":"\u003cp\u003ePsoriasis is a common chronic inflammatory skin disease affecting millions worldwide, characterized by erythema, scaling, and itching. Despite advancements in treatments\u0026mdash;including topical medications, phototherapy, and biologics\u0026mdash;patients still face reduced quality of life and low treatment satisfaction. Studies show that over 50% of moderate-to-severe psoriasis patients report poor disease control [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e], impacting both physical health and psychosocial functioning. Effective psoriasis management requires collaborative doctor-patient efforts, involving complex knowledge about etiology, recurrence mechanisms, treatment options, and lifestyle adjustments [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e \u003cp\u003ePatient education is crucial in psoriasis management. Adequate understanding of the disease, triggers, and treatment options can significantly improve adherence and self-management, enhancing quality of life. However, traditional education methods, such as in-person consultations or printed materials, are time-consuming and burdensome for clinicians [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. With the rise of digital health, patients increasingly seek medical information online, further straining healthcare providers [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eRecent advances in artificial intelligence (AI) offer new possibilities for medical communication [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Large language models, as advanced natural language processing tools, can generate human-like responses and are widely used in education, customer service, and medical consultations [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. In healthcare, LLMs hold promise for delivering quick, accessible information, particularly in non-English contexts like Chinese. However, their application requires rigorous evaluation to ensure accuracy, reliability, and safety [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThis study evaluates four mainstream Chinese closed-source LLMs in addressing common psoriasis patient queries. By systematically analyzing response quality, we aim to guide clinicians and patients in using AI tools and inform future research and development.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy Design\u003c/h2\u003e \u003cp\u003eThis multicenter expert consensus study assessed the performance of four Chinese LLMs in responding to psoriasis-related questions. The study comprised three phases: question collection, model testing, and expert evaluation.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eModel Selection\u003c/h3\u003e\n\u003cp\u003eFour mainstream Chinese closed-source LLMs were selected: DeepSeek-R1 [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e], DeepSeek-V3 [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e], Qwen-3 [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e], and GLM-4 [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. These models were chosen for their strong performance in Chinese natural language processing tasks and widespread use.\u003c/p\u003e\n\u003ch3\u003eQuestion Collection\u003c/h3\u003e\n\u003cp\u003eNine dermatologists from multiple hospitals contributed 40 high-frequency psoriasis-related questions. Each expert provided up to 10 questions, ensuring coverage of five key domains:\u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eDisease etiology and pathophysiology\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eTriggers and recurrence mechanisms\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eTreatment options, including biologics\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eDisease management and lifestyle adjustments\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003ePsychosocial impact and quality of life\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\u003e \u003c/p\u003e \u003cp\u003eAll questions were formulated in Chinese, reflecting real-world patient inquiries, and were reviewed for relevance and representativeness.\u003c/p\u003e\n\u003ch3\u003eData Collection\u003c/h3\u003e\n\u003cp\u003eThe 40 questions were input into the four LLMs, and responses were recorded for evaluation.\u003c/p\u003e\n\u003ch3\u003eEvaluation Method\u003c/h3\u003e\n\u003cp\u003eNine dermatologists independently assessed response quality using a 10-point Likert scale (1\u0026thinsp;=\u0026thinsp;lowest, 10\u0026thinsp;=\u0026thinsp;highest). Criteria included:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eAccuracy: Alignment with evidence-based medicine\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eCompleteness: Coverage of necessary information\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eClarity: Ease of understanding\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eSafety: Absence of dangerous or misleading content\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eExperts also noted deviations from evidence-based guidelines and whether responses included recommendations to consult a physician.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eData Analysis\u003c/h2\u003e \u003cp\u003eScores from the nine experts were aggregated to calculate mean scores and standard deviations for each model. Representative responses and score distributions are presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e and Figs.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eA question 'What are the side effects of long-term topical steroid use in psoriasis patients?' answered by Deepseek-R1, Deepseek-V3, Qwen-3, and Glm-4.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAnswer\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMean score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eStandard deviation\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeepseek-R1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAlthough long-term use of topical corticosteroids (such as hydrocortisone, halobetasol, etc.) by psoriasis patients can effectively relieve inflammation and itching, it may cause the following side effects and should be used cautiously under the guidance of a doctor: \u0026hellip;\u0026hellip;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.58\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeepseek-V3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLong-term use of topical corticosteroids (hereinafter referred to as \"steroids\") by psoriasis patients may lead to various side effects, particularly evident with improper use (such as overdose, excessive area, long-term continuous use). The following are the main categories of side effects: \u0026hellip;\u0026hellip;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.44\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eQwen-3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAlthough long-term topical use of corticosteroids (commonly known as \"steroids\") in psoriasis patients has good short-term efficacy in controlling the condition, reducing inflammation, and scaling, improper or prolonged use may lead to a series of side effects. The following are common\u0026nbsp;topical corticosteroid side effects: \u0026hellip;\u0026hellip;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9.12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.59\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGlm-4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePsoriasis is a chronic skin disease often characterized by red patches and scales on the skin. Corticosteroids (such as glucocorticoids) are common topical medications for treating psoriasis, but long-term use may bring some side effects. Here are some common side effects: \u0026hellip;\u0026hellip;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.08\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003eOverall Scores\u003c/h2\u003e \u003cp\u003eThe four LLMs achieved mean scores ranging from 5.95 to 9.88 (SD: 0\u0026ndash;3.05), indicating high expert satisfaction. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e displays responses to a representative question: \"What are the side effects of long-term topical steroid use in psoriasis patients?\"\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eScore Distribution\u003c/h2\u003e \u003cp\u003eFigures \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e illustrate score distributions for each model. DeepSeek-R1 and DeepSeek-V3 scores clustered between 7\u0026ndash;9, while Qwen-3 showed more consistent high ratings. GLM-4 exhibited greater variability, reflecting uneven performance.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eResponse Characteristics\u003c/h2\u003e \u003cp\u003eAll models avoided dangerous or misleading information, a key positive finding. Most responses included disclaimers like \"consult a physician,\" enhancing safety. However, some answers scored lower due to incomplete or non-evidence-based content, particularly for complex topics like biologics.\u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis multicenter expert consensus study represents the first comprehensive evaluation of Chinese large language models in the context of psoriasis patient education. The findings reveal a dual narrative of notable promise alongside critical limitations, offering valuable insights for both clinical practice and AI development. The observed performance variation across models\u0026mdash;with mean scores ranging from 5.95 to 9.88\u0026mdash;clearly demonstrates that not all commercially available LLMs are equally suited for specialized medical consultation. Among the evaluated models, Qwen-3 emerged as the top performer, achieving a mean score of 9.12. This success underscores the technical feasibility of developing LLMs capable of delivering high-quality, patient-centered responses. In contrast, GLM-4 exhibited significant inconsistency in its responses, with a standard deviation of up to 3.05, highlighting the ongoing challenges in ensuring clinical reliability across diverse medical queries.\u003c/p\u003e \u003cp\u003eA key strength identified in this study was the universal adherence of all models to fundamental safety protocols. Notably, every evaluated LLM successfully avoided generating dangerous or misleading content, and an overwhelming majority (87.5%) proactively emphasized the necessity of consulting a physician. This represents a substantial improvement over traditional online health information sources, which often lack rigorous oversight and may propagate misinformation. Furthermore, the models excelled in providing clear, structured explanations for foundational topics such as the side effects of topical steroids. By distilling complex medical concepts into patient-friendly language, these LLMs demonstrated their potential to serve as valuable educational tools. Such capabilities could significantly reduce the burden on clinicians by addressing routine patient inquiries, allowing healthcare providers to allocate more time to complex cases and personalized care.\u003c/p\u003e \u003cp\u003eDespite these strengths, the study also uncovered persistent gaps in the models' performance, particularly in specialized areas of psoriasis management. Approximately 12.5% of responses deviated from evidence-based guidelines, with notable inaccuracies arising in discussions of biologics' mechanisms of action, combination therapy sequencing, and complex management scenarios. These inconsistencies likely stem from inadequate domain-specific training data and insufficient clinical validation processes. While the models performed well in identifying common psoriasis triggers\u0026mdash;such as stress and infections\u0026mdash;their management advice often lacked depth and personalization. The tendency to provide generalized responses represents a critical limitation, as it fails to account for the heterogeneous nature of psoriasis, which manifests in diverse phenotypes and requires tailored treatment approaches.\u003c/p\u003e \u003cp\u003eThese findings resonate with broader observations in the literature regarding the limitations of LLMs in medical applications. Prior studies have noted that current models often struggle with context-dependent reasoning, a capability essential for managing chronic conditions like psoriasis, where individualized care is paramount. Our study extends these observations to the Chinese-language dermatology context, where linguistic nuances and regional treatment preferences introduce additional layers of complexity. For instance, while the models occasionally referenced traditional Chinese medicine, these mentions were not systematically integrated into evidence-based recommendations, reflecting a gap in culturally relevant training data.\u003c/p\u003e \u003cp\u003eIn summary, this study highlights both the potential and the current limitations of Chinese LLMs in psoriasis patient education. While they excel in safety and foundational knowledge dissemination, their performance in specialized and personalized care remains inconsistent. Addressing these gaps will require enhanced collaboration between AI developers and clinical experts, as well as the incorporation of more robust, domain-specific training datasets. Until these improvements are realized, LLMs should be viewed as supplementary tools\u0026mdash;valuable for basic education but insufficient for guiding complex treatment decisions without clinician oversight.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eChinese LLMs demonstrate substantial potential as supplementary tools for psoriasis patient education, particularly in improving health literacy regarding disease fundamentals, medication safety, and basic self-management. Qwen-3 currently delivers the most clinically reliable performance among evaluated models. However, significant limitations persist in handling specialized therapeutic areas (notably biologics and complex management scenarios) and providing individualized recommendations.\u003c/p\u003e \u003cp\u003eKey implications for practice:\u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e​\u003cb\u003e​Selective Implementation​\u003c/b\u003e​: Healthcare systems should prioritize rigorously validated models like Qwen-3 for delivering standardized educational content about topical therapies and lifestyle management.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e​\u003cb\u003e​Mandatory Human Oversight​\u003c/b\u003e​: All LLM-generated advice regarding systemic treatments, biologics, or treatment modifications must undergo clinician verification before dissemination to patients.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e​\u003cb\u003e​Clear Scope Definition​\u003c/b\u003e​: Patient-facing interfaces should explicitly state model limitations, particularly regarding treatment individualization and complex case management.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e​\u003cb\u003e​Continuous Validation Framework​\u003c/b\u003e​: Developers must establish ongoing clinical evaluation mechanisms, especially for rapidly evolving therapeutic domains like biologics.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\u003e \u003c/p\u003e \u003cp\u003eFuture development should focus on enhancing evidence-based reasoning through curated dermatology datasets, implementing specialist review protocols, and developing hybrid human-AI education systems. Until these advancements are realized, LLMs should be positioned strictly as informational supplements for clinician-guided psoriasis education.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003cstrong\u003e \u003cb\u003eEthics approval and consent to participate\u003c/b\u003e:\u003c/strong\u003e \u003cp\u003eNot applicable.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003e \u003cb\u003eConsent for publication\u003c/b\u003e:\u003c/strong\u003e \u003cp\u003eNot applicable.\u003c/p\u003e \u003c/p\u003e\u003cp\u003e \u003ch2\u003eCompeting interests:\u003c/h2\u003e \u003cp\u003eThe authors have no conflict of interest to declare.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding:\u003c/h2\u003e \u003cp\u003eThis work was supported by Natural Science Foundation of Guangdong Province (No.2025A1515010947) and Shenzhen Sanming Project (No. SZSM202311029).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eBY, XH, JS, FW, KZ, YY, XZ, JW, ZC collected questions and LLM scores. JW collected data. CC, HH conducted data statistics and analysis, and CC was a major contributor in writing the manuscript. JH, XL designed and guided the experiments, and provided supervision. All authors read and approved the final manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgements:\u003c/h2\u003e \u003cp\u003eThe study was supported by Shenzhen Research Grants(200901013). We thank Shenzhen Public Service Platform of Biomedical Technology for the technical support.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eAll data supporting the findings of this study are available within the paper and its Supplementary Information.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eRaharja, A., Mahil, S. K. \u0026amp; Barker, J. N. Psoriasis: a brief overview[J]. \u003cem\u003eClin. Med.\u003c/em\u003e \u003cb\u003e21\u003c/b\u003e (3), 170\u0026ndash;173 (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, T. et al. Potential effects and mechanisms of Chinese herbal medicine in the treatment of psoriasis[J]. \u003cem\u003eJ. Ethnopharmacol.\u003c/em\u003e \u003cb\u003e294\u003c/b\u003e, 115275 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDressler, C. et al. Therapeutic patient education and self-management support for patients with psoriasis\u0026ndash;a systematic review[J]. \u003cem\u003eJDDG: J. der Deutschen Dermatologischen Gesellschaft\u003c/em\u003e. \u003cb\u003e17\u003c/b\u003e (7), 685\u0026ndash;695 (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJiang, Y. et al. Patients\u0026rsquo; and healthcare providers\u0026rsquo; perceptions and experiences of telehealth use and online health information use in chronic disease management for older patients with chronic obstructive pulmonary disease: a qualitative study[J]. \u003cem\u003eBMC Geriatr.\u003c/em\u003e \u003cb\u003e22\u003c/b\u003e (1), 9 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlowais, S. A. et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice[J]. \u003cem\u003eBMC Med. Educ.\u003c/em\u003e \u003cb\u003e23\u003c/b\u003e (1), 689 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLucas, H. C., Upperman, J. S. \u0026amp; Robinson, J. R. A systematic review of large language models and their implications in medical education[J]. \u003cem\u003eMed. Educ.\u003c/em\u003e \u003cb\u003e58\u003c/b\u003e (11), 1276\u0026ndash;1285 (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang, R. et al. Large language models in health care: Development, applications, and challenges[J]. \u003cem\u003eHealth Care Sci.\u003c/em\u003e \u003cb\u003e2\u003c/b\u003e (4), 255\u0026ndash;263 (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo, D. et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning[J]. (2025). arXiv preprint arXiv:2501.12948.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu, A. et al. Deepseek-v3 technical report[J]. arXiv preprint arXiv:2412.19437, (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang, A. et al. Qwen3 technical report[J]. arXiv preprint arXiv:2505.09388, (2025).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGLM, T. et al. Chatglm: A family of large language models from glm-130b to glm-4 all tools[J]. (2024). arXiv preprint arXiv:2406.12793.\u003c/span\u003e\u003c/li\u003e \u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"psoriasis, artificial intelligence, large language models, patient education, medical dermatology","lastPublishedDoi":"10.21203/rs.3.rs-8155599/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8155599/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003ePsoriasis patients in China face significant challenges due to insufficient disease knowledge and limited access to medical resources, creating a need for reliable educational tools.\u003c/p\u003e\u003ch2\u003eObjectives\u003c/h2\u003e \u003cp\u003eThis multicenter consensus study aimed to systematically evaluate the consultation quality of mainstream Chinese large language models (LLMs) for psoriasis patient education.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003e\"365 Questions on Psoriasis\" was jointly compiled by 109 Chinese psoriasis experts. Using an expert assessment methodology, nine dermatologists curated 40 high-frequency clinical questions from the book across five domains (etiology, triggers, treatment, management, psychosocial impact). Four Chinese LLMs (DeepSeek-R1, DeepSeek-V3, GLM-4, Qwen-3) were evaluated through double-blind scoring on a 10-point Likert scale assessing accuracy, completeness, clarity, and safety.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003ePerformance varied significantly, with mean scores ranging from 5.95 to 9.88 (SD: 0-3.05). Qwen-3 achieved the highest average score (9.12), while GLM-4 showed the greatest inconsistency. All responses avoided dangerous content, and 87.5% proactively emphasized the necessity of consulting a physician. However, 12.5% of responses deviated from evidence-based guidelines, particularly on complex topics like biologics and management.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eChinese LLMs show substantial potential for psoriasis education by providing generally safe information and appropriately directing users to doctors. However, current limitations exist, including performance inconsistency and occasional deviations from guidelines on specialized topics, indicating they are not yet replacements for professional medical.\u003c/p\u003e","manuscriptTitle":"Accuracy Assessment of Chinese Large Language Models in Psoriasis Management: A Multicenter Expert Consensus Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-23 00:31:54","doi":"10.21203/rs.3.rs-8155599/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-20T06:20:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-20T02:19:01+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-12T17:13:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201264561318986694098468363538864942549","date":"2026-03-12T06:13:02+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-10T15:49:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-09T16:31:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-05T22:31:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"251593346757920488542937377589869713592","date":"2026-03-05T22:22:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"329811286100884653186772442048073197809","date":"2026-03-05T16:35:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"86077495885628653464990938920561799166","date":"2026-03-03T15:06:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"171169820645460813765720160566773135429","date":"2026-03-03T06:27:30+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-20T04:58:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-05T11:10:09+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-03T06:00:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-02T14:21:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-02T14:14:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bb32977c-6a9e-4808-9ee1-fe45094effe3","owner":[],"postedDate":"January 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":61500827,"name":"Health sciences/Diseases"},{"id":61500828,"name":"Health sciences/Health care"},{"id":61500829,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-05-02T14:23:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-23 00:31:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8155599","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8155599","identity":"rs-8155599","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}