AbstractDespite the promising capacity of large language model (LLM)-powered chatbots to diagnose diseases, they have not been tested for obsessive-compulsive disorder (OCD). We assessed the diagnostic accuracy of LLMs in OCD using vignettes and found that LLMs outperformed medical and mental health professionals.

摘要尽管大型语言模型（LLM）支持的聊天机器人具有诊断疾病的良好能力，但尚未对其进行强迫症（OCD）测试。。

This highlights the potential benefit of LLMs in assisting in the timely and accurate diagnosis of OCD, which usually entails a long delay in diagnosis and treatment..

这突出了LLM在帮助及时准确诊断强迫症方面的潜在益处，强迫症通常会导致诊断和治疗的长期延迟。。

Large language model (LLM)-powered artificial intelligence (AI) chatbots exhibit professional-level knowledge across multiple medical specialty areas1,2 and have been evaluated for disease detection, treatment suggestions, medical education, and triage assistance3,4. Moreover, their ability in advanced clinical reasoning holds promise in assisting in a physician’s diagnosis and treatment planning5,6,7.

大型语言模型（LLM）支持的人工智能（AI）聊天机器人在多个医学专业领域表现出专业水平的知识1,2，并已被评估用于疾病检测，治疗建议，医学教育和分流辅助3,4。此外，他们在高级临床推理方面的能力有望帮助医生的诊断和治疗计划5,6,7。

In a statement from the American Psychiatric Association (APA), caution was urged in the use of LLM tools in clinical decision-making8; yet a recent survey revealed that many psychiatrists use LLMs in answering clinical questions and documenting notes, and they believe that LLMs would improve diagnostic accuracy in psychiatry9.

在美国精神病学协会（APA）的一份声明中，敦促在临床决策中使用LLM工具时要谨慎8；然而，最近的一项调查显示，许多精神病医生使用LLM来回答临床问题和记录笔记，他们认为LLM可以提高精神病学的诊断准确性9。

Given the interest and current usage, rigorous study of these tools is urgently needed, especially with respect to awareness of potential bias, compliance with HIPAA, and the use of LLM to augment decision-making.Obsessive-compulsive disorder (OCD) is a common mental health condition, doing repetitive behaviors (compulsions) to avoid unwanted thoughts or sensations (obsessions), which significantly disrupt the daily lives of a person and the family10.

鉴于人们的兴趣和当前的使用情况，迫切需要对这些工具进行严格的研究，特别是在意识到潜在的偏见，遵守HIPAA以及使用LLM来增强决策方面。强迫症（OCD）是一种常见的心理健康状况，通过重复行为（强迫）来避免不必要的想法或感觉（强迫），这会严重扰乱一个人和家庭的日常生活10。

It affects approximately 1 in 40 adults in the United States11, and among adults with OCD, nearly one-half experience serious disability12. Unfortunately, there is, on average, a 17-year delay between the onset of symptoms and treatment initiation13. Longer duration of untreated illness has a negative impact on the long-term outcome of patients with OCD in terms of inferior treatment response and increased symptom severity14.

它影响了美国大约40名成年人中的1名11，在患有强迫症的成年人中，近一半患有严重残疾12。不幸的是，症状发作与治疗开始之间平均延迟了17年13。未经治疗的疾病持续时间较长，在治疗反应较差和症状严重程度增加方面，对强迫症患者的长期预后产生负面影响14。

Although there have been efforts to detect mental disorders through social media and online languages, exploration of LLMs in OCD identification has been limited despite their po.

尽管已经努力通过社交媒体和在线语言来检测精神障碍，但尽管他们的po，但在强迫症识别中对LLM的探索仍然有限。

Data availability

数据可用性

The vignettes used in this study were publicly available from published literature, and the vignette information is provided in a footnote of Supplementary Table 3. The data generated from this study, including OCD and control vignettes and LLMs’ responses to them, will be made available through Supplemental Material upon publication of this study..

本研究中使用的小插曲可从已发表的文献中公开获得，小插曲信息在补充表3的脚注中提供。本研究产生的数据，包括强迫症和控制小插曲以及法学硕士对它们的回应，将在本研究发表后通过补充材料提供。。

ReferencesBeam, K. et al. Performance of a large language model on practice questions for the neonatal board examination. JAMA Pediatr. 177, 977–979 (2023).Article

ReferencesBeam，K.等人。新生儿委员会考试实践问题的大型语言模型的表现。JAMA儿科。177977-979（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Cai, Z. R. et al. Assessment of correctness, content omission, and risk of harm in large language model responses to dermatology continuing medical education questions. J. Invest. Dermatol. https://doi.org/10.1016/J.JID.2024.01.015 (2024).Lyons, R. J., Arepalli, S. R., Fromal, O., Choi, J.

Cai，Z.R.等人。对皮肤病学继续医学教育问题的大型语言模型反应的正确性，内容遗漏和伤害风险的评估。J、 投资。皮肤病。https://doi.org/10.1016/J.JID.2024.01.015（2024年）。里昂，R.J.，阿雷帕利，S.R.，弗洛马尔，O.，崔，J。

D. & Jain, N. Artificial intelligence chatbot performance in triage of ophthalmic conditions. Can. J. Ophthalmol. https://doi.org/10.1016/J.JCJO.2023.07.016 (2023).Chen, S. et al. Use of artificial intelligence chatbots for cancer treatment information. JAMA Oncol. 9, 1459–1462 (2023).Article .

D、 ＆Jain，N。人工智能聊天机器人在眼科疾病分类中的表现。可以。J、 眼科。https://doi.org/10.1016/J.JCJO.2023.07.016（2023年）。Chen，S.等人。使用人工智能聊天机器人获取癌症治疗信息。。91459-1462（2023）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Strong, E. et al. Chatbot vs medical student performance on free-response clinical reasoning examinations. JAMA Intern. Med. 183, 1028–1030 (2023).Article

Strong，E。等人。Chatbot与医学生在自由反应临床推理考试中的表现。JAMA实习生。医学1831028-1030（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172–180 (2023).Article

Singhal，K。等人。大型语言模型编码临床知识。。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Sallam, M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare 11, 887 (2023).Article

Sallam，M。ChatGPT在医疗保健教育，研究和实践中的实用性：对有希望的观点和有效关注的系统评价。医疗保健11887（2023）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Psychiatry.org. The basics of augmented intelligence: some factors psychiatrists need to know now. https://www.psychiatry.org/News-room/APA-Blogs/The-Basics-of-Augmented-Intelligence (2023).Blease, C., Worthen, A. & Torous, J. Psychiatrists’ experiences and opinions of generative artificial intelligence in mental healthcare: An online mixed methods survey.

Psychiatry.org。增强智力的基础：精神病医生现在需要知道的一些因素。https://www.psychiatry.org/News-room/APA-Blogs/The-Basics-of-Augmented-Intelligence（2023年）。Blease，C.，Worthen，A。＆Torous，J。精神病医生在心理保健中对生成人工智能的经验和观点：一项在线混合方法调查。

Psychiatry Res. 333, 115724 (2024).Article .

精神病学研究333115724（2024）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

APA. What is obsessive-compulsive disorder? https://www.psychiatry.org:443/patients-families/obsessive-compulsive-disorder/what-is-obsessive-compulsive-disorder (2022).National Institute of Mental Health (NIMH). Obsessive-compulsive disorder (OCD). https://www.nimh.nih.gov/health/statistics/obsessive-compulsive-disorder-ocd (2022).National Comorbidity Survey (NCSSC).

APA。什么是强迫症？https://www.psychiatry.org:443/patients-家庭/强迫症/什么是强迫症（2022）。国家心理健康研究所（NIMH）。。https://www.nimh.nih.gov/health/statistics/obsessive-compulsive-disorder-ocd（2022年）。国家合并症调查（NCSSC）。

Harvard Medical School. https://www.hcp.med.harvard.edu/ncs/index.php (2007)Pinto, A., Mancebo, M. C., Eisen, J. L., Pagano, M. E. & Rasmussen, S. A. The brown longitudinal obsessive compulsive study: clinical features and symptoms of the sample at intake. J. Clin. Psychiatry 67, 703–711 (2006).Article .

哈佛医学院。https://www.hcp.med.harvard.edu/ncs/index.php（2007）Pinto，A.，Mancebo，M.C.，Eisen，J.L.，Pagano，M.E。和Rasmussen，S.A。布朗纵向强迫症研究：摄入时样本的临床特征和症状。J、 临床。精神病学67703-711（2006）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Perris, F. et al. Duration of untreated illness in patients with obsessive–compulsive disorder and its impact on long-term outcome: a systematic review. J. Pers. Med. 13, 1453 (2023).Article

Perris，F.等人，《强迫症患者未治疗疾病的持续时间及其对长期预后的影响：系统综述》。J、 《医学杂志》第131453页（2023年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Galido, P. V., Butala, S., Chakerian, M. & Agustines, D. A case study demonstrating applications of ChatGPT in the clinical management of treatment-resistant schizophrenia. Cureus 15, e38166 (2023).Cohan, A. et al. SMHD: a large-scale resource for exploring online language usage for multiple mental health conditions.

Galido，P.V.，Butala，S.，Chakerian，M。＆Agustines，D。一项案例研究，展示了ChatGPT在难治性精神分裂症临床管理中的应用。Cureus 15，e38166（2023）。SMHD：探索多种心理健康状况下在线语言使用的大规模资源。

In Proc. 27th International Conference on Computational Linguistics (eds. Bender, E. M., Derczynski, L. & Isabelle, P.) 1485–1497 (Association for Computational Linguistics, 2018).Xu, X. et al. Leveraging large language models for mental health prediction via online text data. In Proc. ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (Association for Computing Machinery, 2023).Galatzer-Levy, I.

在过程中。第27届国际计算语言学会议（eds.Bender，E.M.，Derczynski，L.＆Isabelle，P.）1485-1497（计算语言学协会，2018）。Xu，X.等人。通过在线文本数据利用大型语言模型进行心理健康预测。在过程中。关于交互式、移动、可穿戴和无处不在技术的ACM（计算机械协会，2023年）。加拉泽-列维，I。

R., McDuff, D., Natarajan, V., Karthikesalingam, A. & Malgaroli, M. The capability of large language models to measure psychiatric functioning. Preprint at https://doi.org/10.48550/ARXIV.2308.01834 (2023).Levkovich, I. & Elyoseph, Z. Identifying depression and its determinants upon initiating treatment: ChatGPT versus primary care physicians.

R、 ，McDuff，D.，Natarajan，V.，Karthikesalingam，A。＆Malgaroli，M。大型语言模型测量精神功能的能力。预印于https://doi.org/10.48550/ARXIV.2308.01834（2023年）。Levkovich，I。＆Elyoseph，Z。在开始治疗时识别抑郁症及其决定因素：ChatGPT与初级保健医生。

Fam. Med. Community Health 11, e002391 (2023).Article .

家庭。医学社区卫生11，e002391（2023）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Usage policies. https://openai.com/policies/usage-policies (2024).Lucas, G. M., Gratch, J., King, A. & Morency, L. P. It’s only a computer: virtual humans increase willingness to disclose. Comput. Hum. Behav. 37, 94–100 (2014).Article

使用策略。https://openai.com/policies/usage-policies（2024年）。Lucas，G.M.，Gratch，J.，King，A.＆Morency，L.P。它只是一台计算机：虚拟人增加了披露的意愿。计算机。。37,94-100（2014）。文章

Google Scholar

谷歌学者

Elyoseph, Z., Hadar-Shoval, D., Asraf, K. & Lvovsky, M. ChatGPT outperforms humans in emotional awareness evaluations. Front. Psychol. 14, 1199058 (2023).House, T. W. FACT SHEET: President Biden issues executive order on safe, secure, and trustworthy artificial intelligence. The White House https://www.whitehouse.gov/briefing-room/statements-releases/2023/10/30/fact-sheet-president-biden-issues-executive-order-on-safe-secure-and-trustworthy-artificial-intelligence/ (2023).Glazier, K., Swing, M.

Elyoseph，Z.，Hadar Shoval，D.，Asraf，K。＆Lvovsky，M。ChatGPT在情绪意识评估中优于人类。正面。心理学。14119058（2023）。众议院，T.W.简报：拜登总统发布了关于安全、可靠和值得信赖的人工智能的行政命令。白宫https://www.whitehouse.gov/briefing-room/statements-releases/2023/10/30/fact-sheet-president-biden-issues-executive-order-on-safe-secure-and-trustworthy-artificial-intelligence/（2023年）。。

& McGinn, L. K. Half of obsessive-compulsive disorder cases misdiagnosed: vignette-based survey of primary care physicians. J. Clin. Psychiatry 76, e761–e767 (2015).Article .

&McGinn，L.K。一半被误诊的强迫症病例：基于小插图的初级保健医生调查。J、 临床。精神病学76，e761–e767（2015）。文章。

PubMed

PubMed

Google Scholar

谷歌学者

Gouniai, J. M., Smith, K. D. & Leonte, K. G. Do clergy recognize and respond appropriately to the many themes in obsessive-compulsive disorder?: data from a Pacific Island community. Ment. Health Relig. Cult. 25, 33–46 (2022).Article

Gouniai，J.M.，Smith，K.D。和Leonte，K.G。神职人员是否认识到强迫症的许多主题并做出适当的反应来自太平洋岛屿社区的数据。元素。保健品。崇拜。25，33-46（2022）。文章

Google Scholar

谷歌学者

Gouniai, J. M., Smith, K. D. & Leonte, K. G. Many common presentations of obsessive-compulsive disorder unrecognized by medical providers in a Pacific Island community. J. Ment. Health Train. Educ. Pract. 17, 419–428 (2022).Article

Gouniai，J.M.，Smith，K.D。＆Leonte，K.G。太平洋岛屿社区的医疗服务提供者无法识别强迫症的许多常见表现。J、 元素。健康列车。教育。实践。17419-428（2022）。文章

Google Scholar

谷歌学者

Glazier, K., Calixte, R. M., Rothschild, R. & Pinto, A. High rates of OCD symptom misidentification by mental health professionals. Ann. Clin. Psychiatry 25, 201–209.Glazier, K. & McGinn, L. K. Non-contamination and non-symmetry OCD obsessions are commonly not recognized by clinical, counseling and school psychology doctoral students.

Glazier，K.，Calixte，R.M.，Rothschild，R。＆Pinto，A。心理健康专业人员对强迫症症状的错误识别率很高。安。克林。精神病学25201–209.Glazier，K.＆McGinn，L.K。临床，咨询和学校心理学博士生通常不认识非污染和非对称强迫症。

J. Depress. Anxiety 04 (2015).Kim, J., Cai, Z. R., Chen, M. L., Simard, J. F. & Linos, E. Assessing biases in medical decisions via clinician and AI Chatbot responses to patient vignettes. JAMA Netw. Open 6, E2338050 (2023).Article .

J、 按下按钮。焦虑04（2015）。Kim，J.，Cai，Z.R.，Chen，M.L.，Simard，J.F。＆Linos，E。通过临床医生和AI Chatbot对患者小插曲的反应评估医疗决策中的偏见。JAMA网络。打开6，E2338050（2023）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wang, J. et al. Prompt engineering for healthcare: methodologies and applications. Preprint at https://doi.org/10.48550/arXiv.2304.14670 (2024).Savage, T., Nayak, A., Gallo, R., Rangan, E. & Chen, J. H. Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine.

Wang，J.等人。医疗保健的快速工程：方法和应用。预印于https://doi.org/10.48550/arXiv.2304.14670（2024年）。Savage，T.，Nayak，A.，Gallo，R.，Rangan，E。＆Chen，J.H。诊断推理提示揭示了医学中大型语言模型可解释性的潜力。

Npj Digit. Med. 7, 1–7 (2024).Article .

Npj数字。《医学》7，1-7（2024）。第条。

Google Scholar

谷歌学者

Download referencesAcknowledgementsE.L. was supported by the National Institutes of Health: Mid-career Investigator Award in Patient-Oriented Research (K24AR075060). The funders of this study had no role in the design and conduct of the study, collection, management, analysis, and interpretation of the data, preparation, review, or approval of the manuscript, nor a decision to submit the manuscript for publication.Author informationAuthor notesThese authors contributed equally: Jiyeong Kim, Kimberly G.

下载referencesAcknowledgementsE。五十、 获得了美国国立卫生研究院（National Institutes of Health）的支持：职业中期研究者奖（K24AR075060）。这项研究的资助者在研究的设计和进行，数据的收集，管理，分析和解释，稿件的准备，审查或批准方面没有任何作用，也没有决定提交稿件出版。作者信息作者注意到这些作者做出了同样的贡献：Jiyeong Kim，Kimberly G。

Leonte.These authors jointly supervised this work: Eleni Linos, Anthony Pinto, Carolyn I. Rodriguez.Authors and AffiliationsStanford Center for Digital Health, Department of Medicine, Stanford University, Palo Alto, CA, USAJiyeong Kim, Michael L. Chen & Eleni LinosClearview Horizons, North Andover, MA, USAKimberly G.

莱昂特。这些作者共同监督了这项工作：Eleni Linos，Anthony Pinto，Carolyn I.Rodriguez。作者和附属机构斯坦福大学医学系斯坦福数字健康中心，加利福尼亚州帕洛阿尔托，USAJiyeong Kim，Michael L.Chen＆Eleni LinosClearview Horizons，马萨诸塞州北安多佛，USAKimberly G。

LeonteDivision of Digital Psychiatry, Department of Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA, USAJohn B. TorousDepartment of Psychiatry, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, NY, USAAnthony PintoNorthwell, New Hyde Park, NY, USAAnthony PintoDepartment of Psychiatry and Behavioral Sciences, School of Medicine, Stanford University, Palo Alto, CA, USACarolyn I.

美国马萨诸塞州波士顿贝斯以色列女执事医学中心精神病学系数字精神病学系John B.Torous精神病学系，纽约州亨普斯特德Hofstra/Northwell的Donald和Barbara Zucker医学院，美国纽约州新海德公园的Anthony PintoNorthwell，美国加利福尼亚州帕洛阿尔托斯坦福大学医学院精神病学和行为科学系Anthony PintoDepartment of Psychiatry and Behavior Sciences，USACarolyn I。

RodriguezVeterans Affairs Palo Alto Health Care System, Palo Alto, CA, USACarolyn I. RodriguezAuthorsJiyeong KimView author publicationsYou can also search for this author in.

罗德里格斯·维特兰（RodriguezVeterans Affairs Palo Alto Health Care System），美国加利福尼亚州帕洛阿尔托（Palo Alto），Carolyn I.RodriguezAuthorsJiyeong KimView作者出版物您也可以在中搜索这位作者。

PubMed Google ScholarKimberly G. LeonteView author publicationsYou can also search for this author in

PubMed Google ScholarKimberly G.LeonteView作者出版物您也可以在

PubMed Google ScholarMichael L. ChenView author publicationsYou can also search for this author in

PubMed谷歌Scholarmamichael L.ChenView作者出版物您也可以在

PubMed Google ScholarJohn B. TorousView author publicationsYou can also search for this author in

PubMed谷歌学者John B.TorousView作者出版物您也可以在

PubMed Google ScholarEleni LinosView author publicationsYou can also search for this author in

PubMed Google ScholarEleni LinosView作者出版物您也可以在

PubMed Google ScholarAnthony PintoView author publicationsYou can also search for this author in

PubMed Google ScholarAnthony PintoView作者出版物您也可以在

PubMed Google ScholarCarolyn I. RodriguezView author publicationsYou can also search for this author in

PubMed Google ScholarCarolyn I.RodriguezView作者出版物您也可以在

PubMed Google ScholarContributionsJ.K. and K.G.L. contributed equally as joint first authors. E.L., A.P., and C.I.R. contributed equally as joint senior authors. Concept and design: J.K., J.B.T., and C.I.R. Acquisition, analysis, or interpretation of data: J.K., K.G.L., A.P., and C.I.R.

PubMed谷歌学术贡献。K、 和K.G.L.作为联合第一作者做出了同样的贡献。E、 L.，A.P。和C.I.R.作为联合资深作者做出了同样的贡献。概念和设计：J.K.，J.B.T。和C.I.R.数据的采集，分析或解释：J.K.，K.G.L.，A.P。和C.I.R。

Drafting of the manuscript: J.K., K.G.L., A.P., and C.I.R. Critical review of the manuscript for important intellectual content: J.K., K.G.L., M.L.C., J.B.T., E.L., A.P., and C.I.R. Statistical analysis: J.K. and K.G.L. Administrative, technical, or material support: M.L.C., E.L., and C.I.R. Supervision: E.L., A.P., and C.I.R.Corresponding authorsCorrespondence to.

手稿的起草：J.K.，K.G.L.，A.P。和C.I.R。对重要知识内容手稿的批判性审查：J.K.，K.G.L.，M.L.C.，J.B.T.，E.L.，A.P。和C.I.R.统计分析：J.K.和K.G.L.行政，技术或物质支持：M.L.C.，E.L。和C.I.R.监督：E.L.，A.P。和C.I.R.相应的作者通信。

Jiyeong Kim or Carolyn I. Rodriguez.Ethics declarations

Jiyeong Kim或Carolyn I.Rodriguez。道德宣言

Competing interests

相互竞争的利益

In the last 3 years, C.I.R. has served as a consultant for Biohaven Pharmaceuticals, Osmind, and Biogen; and receives research grant support from Biohaven Pharmaceuticals, a stipend from American Psychiatric Association Publishing for her role as Deputy Editor at The American Journal of Psychiatry, and book royalties from American Psychiatric Association Publishing.

在过去的3年中，C.I.R.曾担任Biohaven Pharmaceuticals，Osmind和Biogen的顾问；并获得了Biohaven Pharmaceuticals的研究资助，这是美国精神病学协会出版公司为她担任《美国精神病学杂志》副编辑而提供的津贴，以及美国精神病学协会出版公司的书籍版税。

J.B.T. is an associated editor for npj Digital Medicine. He was not involved in the review of this paper. The remaining authors declare no competing financial or non-financial interests or other relationships relevant to the subject of this manuscript..

J、 B.T.是npj数字医学的联合编辑。他没有参与本文的审查。其余作者声明没有与本手稿主题相关的竞争性财务或非财务利益或其他关系。。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary informationSupplemental MaterialRights and permissions

Additional informationPublisher的注释Springer Nature在已发布的地图和机构隶属关系中的管辖权主张方面保持中立。补充信息补充材料权利和权限

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

开放获取本文是根据知识共享署名4.0国际许可证授权的，该许可证允许以任何媒体或格式使用，共享，改编，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出是否进行了更改。

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

本文中的图像或其他第三方材料包含在文章的知识共享许可中，除非在材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by/4.0/..

Reprints and permissionsAbout this articleCite this articleKim, J., Leonte, K.G., Chen, M.L. et al. Large language models outperform mental and medical health care professionals in identifying obsessive-compulsive disorder.

转载和许可本文引用本文Kim，J.，Leonte，K.G.，Chen，M.L.等人。大型语言模型在识别强迫症方面优于心理和医疗保健专业人员。

npj Digit. Med. 7, 193 (2024). https://doi.org/10.1038/s41746-024-01181-xDownload citationReceived: 15 March 2024Accepted: 28 June 2024Published: 19 July 2024DOI: https://doi.org/10.1038/s41746-024-01181-xShare this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

npj数字。医学杂志7193（2024）。https://doi.org/10.1038/s41746-024-01181-xDownload引文接收日期：2024年3月15日接受日期：2024年6月28日发布日期：2024年7月19日OI：https://doi.org/10.1038/s41746-024-01181-xShare本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供