{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T18:58:34Z","timestamp":1793213914245,"version":"4.5.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009827","name":"Alexandria University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009827","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["OBES SURG"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The rapid integration of Large Language Models (LLMs) into healthcare necessitates a rigorous evaluation of their performance in specialized medical fields. In metabolic bariatric surgery (MBS), LLMs have the potential to revolutionize education and clinical support, yet their accuracy and reliability are not well-established. This study provides a critical assessment of the capabilities of current LLMs in the context of MBS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This cross-sectional validation study assessed the performance of six LLMs (ChatGPT-3.5, ChatGPT-4o, Gemini, Copilot, GROK, and DeepSeek) in answering 100 evidence-based binary and multiple-choice questions related to MBS. Questions were constructed from international guidelines and categorized into six thematic domains. Expert consensus answers served as the reference standard, with inter-rater reliability measured using Fleiss\u2019 \u03ba. Model outputs were scored for accuracy. Comparisons across LLMs were first assessed using an overall test for differences between multiple related groups. Pairwise comparisons were then conducted between LLMs to identify specific differences in performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Across the dataset, the mean number of correct LLM responses per question was 3.9 (SD\u2009=\u20091.8). ChatGPT-4o achieved the highest accuracy (66.0%), while DeepSeek recorded the lowest (60.0%). Accuracy varied across domains, highest for indications\/contraindications (78.7%) and complications\/management (68.0%), and lowest for preoperative preparation (52.0%) and postoperative care (58.4%). Binary questions yielded higher accuracy (69.1%) than multiple-choice questions (62.0%). Inter-expert reliability was substantial (\u03ba\u2009=\u20090.742, 95% CI: 0.71\u20130.77). Agreement between LLMs and experts ranged from fair (DeepSeek \u03ba\u2009=\u20090.349) to moderate (ChatGPT-4o \u03ba\u2009=\u20090.446). No significant accuracy differences were detected across models (Friedman test,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.662).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>LLMs represent a promising, yet imperfect, adjunct in MBS education. Their utility is currently limited by inconsistencies in accuracy, particularly in areas requiring nuanced clinical judgment. While these models can supplement traditional learning resources, they are not yet a substitute for expert clinical guidance. This study underscores the need for continued refinement and validation of LLMs to ensure their safe and effective integration into clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11695-025-08418-y","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:42:44Z","timestamp":1765413764000},"page":"538-545","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Performance of Large Language Models in Metabolic Bariatric Surgery: a Comparative Study"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6177-3697","authenticated-orcid":false,"given":"Hassan","family":"El-Masry","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2117-9515","authenticated-orcid":false,"given":"Mohamed Yasser","family":"El-mezayen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bothaina","family":"Farouk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0914-7669","authenticated-orcid":false,"given":"Abdelrahman M.","family":"Tawfik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2917-7909","authenticated-orcid":false,"given":"Passant Saeed","family":"Sharsher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Basma Hesham","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4428-3310","authenticated-orcid":false,"given":"Ahmed","family":"Abo Elmagd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Khammas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelrahman","family":"Nimeri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8779-3055","authenticated-orcid":false,"given":"Ricardo","family":"V Cohen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-0904","authenticated-orcid":false,"given":"Ahmed","family":"Abokhozima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"issue":"10","key":"8418_CR1","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1007\/s10462-024-10888-y","volume":"57","author":"P Kumar","year":"2024","unstructured":"Kumar P. Large Language models (LLMs): survey, technical frameworks, and future challenges. Artif Intell Rev. 2024;57(10):260.","journal-title":"Artif Intell Rev"},{"issue":"6","key":"8418_CR2","doi-asserted-by":"publisher","first-page":"192","DOI":"10.3390\/fi15060192","volume":"15","author":"KI Roumeliotis","year":"2023","unstructured":"Roumeliotis KI, Tselikas ND. Chatgpt and open-ai models: A preliminary review. Future Internet. 2023;15(6):192.","journal-title":"Future Internet"},{"issue":"1","key":"8418_CR3","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","volume":"3","author":"J Clusmann","year":"2023","unstructured":"Clusmann J, Kolbinger FR, Muti HS, Carrero ZI, Eckardt J-N, Laleh NG, et al. The future landscape of large Language models in medicine. Commun Med. 2023;3(1):141.","journal-title":"Commun Med"},{"key":"8418_CR4","doi-asserted-by":"crossref","unstructured":"Adetayo AJ, Aborisade MO, Sanni BA. Microsoft copilot and anthropic Claude AI in education and library service. Library Hi Tech News; 2024.","DOI":"10.1108\/LHTN-01-2024-0002"},{"key":"8418_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03727-2","author":"S Sandmann","year":"2025","unstructured":"Sandmann S, Hegselmann S, Fujarski M, Bickmann L, Wild B, Eils R, et al. Benchmark evaluation of deepseek large Language models in clinical decision-making. Nat Med. 2025. https:\/\/doi.org\/10.1038\/s41591-025-03727-2.","journal-title":"Nat Med"},{"issue":"1","key":"8418_CR6","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.59400\/cai.v2i1.1378","volume":"2","author":"ZB Akhtar","year":"2024","unstructured":"Akhtar ZB. From bard to gemini: an investigative exploration journey through google\u2019s evolution in conversational AI and generative AI. Comput Artif Intell. 2024;2(1):1378.","journal-title":"Comput Artif Intell"},{"issue":"13","key":"8418_CR7","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","volume":"388","author":"P Lee","year":"2023","unstructured":"Lee P, Bubeck S, Petro J, Benefits. Limits, and risks of GPT-4 as an AI chatbot for medicine. N Engl J Med. 2023;388(13):1233\u20139. https:\/\/doi.org\/10.1056\/NEJMsr2214184.","journal-title":"N Engl J Med"},{"issue":"10377","key":"8418_CR8","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/S0140-6736(23)00216-7","volume":"401","author":"A Arora","year":"2023","unstructured":"Arora A, Arora A. The promise of large Language models in health care. Lancet. 2023;401(10377):641.","journal-title":"Lancet"},{"issue":"11","key":"8418_CR9","doi-asserted-by":"publisher","first-page":"3041","DOI":"10.3390\/jcm13113041","volume":"13","author":"SM Pressman","year":"2024","unstructured":"Pressman SM, Borna S, Gomez-Cabello CA, Haider SA, Haider CR, Forte AJ. Clinical and surgical applications of large Language models: A systematic review. J Clin Med. 2024;13(11):3041.","journal-title":"J Clin Med"},{"issue":"6","key":"8418_CR10","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1007\/s11695-023-06603-5","volume":"33","author":"JS Samaan","year":"2023","unstructured":"Samaan JS, Yeo YH, Rajeev N, Hawley L, Abel S, Ng WH, et al. Assessing the accuracy of responses by the Language model ChatGPT to questions regarding bariatric surgery. Obes Surg. 2023;33(6):1790\u20136.","journal-title":"Obes Surg"},{"issue":"5","key":"8418_CR11","doi-asserted-by":"publisher","first-page":"2522","DOI":"10.1007\/s00464-024-10720-2","volume":"38","author":"N Srinivasan","year":"2024","unstructured":"Srinivasan N, Samaan JS, Rajeev ND, Kanu MU, Yeo YH, Samakar K. Large Language models and bariatric surgery patient education: a comparative readability analysis of GPT-3.5, GPT-4, Bard, and online institutional resources. Surg Endosc. 2024;38(5):2522\u201332.","journal-title":"Surg Endosc"},{"key":"8418_CR12","doi-asserted-by":"publisher","unstructured":"Davis FD. Perceived usefulness, perceived ease of use, and user acceptance of information technology. MIS Q. 1989:319\u201340. https:\/\/doi.org\/10.2307\/249008","DOI":"10.2307\/249008"},{"key":"8418_CR13","doi-asserted-by":"crossref","unstructured":"De Luca M, Angrisani L, Himpens J, Busetto L, Scopinaro N, Weiner R, et al. Indications for surgery for obesity and weight-related diseases: position statements from the international federation for the surgery of obesity and metabolic disorders (IFSO). Springer; 2016.","DOI":"10.1007\/s11695-016-2271-4"},{"key":"8418_CR14","doi-asserted-by":"crossref","unstructured":"Eisenberg D, Shikora SA, Aarts E, Aminian A, Angrisani L, Cohen RV, et al. 2022 American society of metabolic and bariatric surgery (ASMBS) and international federation for the surgery of obesity and metabolic disorders (IFSO) indications for metabolic and bariatric surgery. Springer; 2023.","DOI":"10.1007\/s11695-022-06332-1"},{"key":"8418_CR15","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s11695-014-1214-1","volume":"24","author":"L Busetto","year":"2014","unstructured":"Busetto L, Dixon J, De Luca M, Shikora S, Pories W, Angrisani L. Bariatric surgery in class I obesity: a position statement from the international federation for the surgery of obesity and metabolic disorders (IFSO). Obes Surg. 2014;24:487\u2013519.","journal-title":"Obes Surg"},{"issue":"9","key":"8418_CR16","doi-asserted-by":"publisher","first-page":"2065","DOI":"10.1007\/s00268-016-3492-3","volume":"40","author":"A Thorell","year":"2016","unstructured":"Thorell A, MacCormick A, Awad S, Reynolds N, Roulin D, Demartines N, et al. Guidelines for perioperative care in bariatric surgery: enhanced recovery after surgery (ERAS) society recommendations. World J Surg. 2016;40(9):2065\u201383.","journal-title":"World J Surg"},{"issue":"3","key":"8418_CR17","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1111\/cob.12145","volume":"6","author":"M O\u2019Kane","year":"2016","unstructured":"O\u2019Kane M, Parretti HM, Hughes CA, Sharma M, Woodcock S, Puplampu T, et al. Guidelines for the follow-up of patients undergoing bariatric surgery. Clin Obes. 2016;6(3):210\u201324.","journal-title":"Clin Obes"},{"key":"8418_CR18","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1007\/s11695-015-1657-z","volume":"25","author":"L Angrisani","year":"2015","unstructured":"Angrisani L, Santonicola A, Iovino P, Formisano G, Buchwald H, Scopinaro N. Bariatric surgery worldwide 2013. Obes Surg. 2015;25:1822\u201332.","journal-title":"Obes Surg"},{"issue":"2","key":"8418_CR19","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.soard.2019.10.025","volume":"16","author":"JI Mechanick","year":"2020","unstructured":"Mechanick JI, Apovian C, Brethauer S, Garvey WT, Joffe AM, Kim J, et al. Clinical practice guidelines for the perioperative nutrition, metabolic, and nonsurgical support of patients undergoing bariatric procedures\u20132019 update: cosponsored by American association of clinical Endocrinologists\/American college of Endocrinology, the obesity society, American society for metabolic & bariatric Surgery, obesity medicine association, and American society of anesthesiologists. Surg Obes Relat Dis. 2020;16(2):175\u2013247.","journal-title":"Surg Obes Relat Dis"},{"issue":"11","key":"8418_CR20","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1002\/bjs.10236","volume":"103","author":"H Maertens","year":"2016","unstructured":"Maertens H, Madani A, Landry T, Vermassen F, Van Herzeele I, Aggarwal R. Systematic review of e-learning for surgical training. J Br Surg. 2016;103(11):1428\u201337.","journal-title":"J Br Surg"},{"issue":"3","key":"8418_CR21","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1111\/j.1445-2197.2008.04828.x","volume":"79","author":"M Larvin","year":"2009","unstructured":"Larvin M. E-Learning in surgical education and training. ANZ J Surg. 2009;79(3):133\u20137. https:\/\/doi.org\/10.1111\/j.1445-2197.2008.04828.x.","journal-title":"ANZ J Surg"},{"issue":"6","key":"8418_CR22","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1007\/s11695-023-06603-5","volume":"33","author":"JS Samaan","year":"2023","unstructured":"Samaan JS, Yeo YH, Rajeev N, Hawley L, Abel S, Ng WH, et al. Assessing the accuracy of responses by the Language model ChatGPT to questions regarding bariatric surgery. Obes Surg. 2023;33(6):1790\u20136. https:\/\/doi.org\/10.1007\/s11695-023-06603-5.","journal-title":"Obes Surg"},{"issue":"7","key":"8418_CR23","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/j.soard.2024.03.011","volume":"20","author":"Y Lee","year":"2024","unstructured":"Lee Y, Shin T, Tessier L, Javidan A, Jung J, Hong D, et al. Harnessing artificial intelligence in bariatric surgery: comparative analysis of ChatGPT-4, Bing, and bard in generating clinician-level bariatric surgery recommendations. Surg Obes Relat Dis. 2024;20(7):603\u20138.","journal-title":"Surg Obes Relat Dis"},{"issue":"6","key":"8418_CR24","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1159\/000481825","volume":"10","author":"L Busetto","year":"2018","unstructured":"Busetto L, Dicker D, Azran C, Batterham RL, Farpour-Lambert N, Fried M, et al. Practical recommendations of the obesity management task force of the European association for the study of obesity for the post-bariatric surgery medical management. Obes Facts. 2018;10(6):597\u2013632.","journal-title":"Obes Facts"},{"issue":"12","key":"8418_CR25","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1016\/j.soard.2022.08.013","volume":"18","author":"D Eisenberg","year":"2022","unstructured":"Eisenberg D, Shikora SA, Aarts E, Aminian A, Angrisani L, Cohen RV, et al. 2022 American society for metabolic and bariatric surgery (ASMBS) and international federation for the surgery of obesity and metabolic disorders (IFSO): indications for metabolic and bariatric surgery. Surg Obes Relat Dis. 2022;18(12):1345\u201356. https:\/\/doi.org\/10.1016\/j.soard.2022.08.013.","journal-title":"Surg Obes Relat Dis"},{"issue":"11","key":"8418_CR26","doi-asserted-by":"publisher","first-page":"3963","DOI":"10.1007\/s11695-024-07370-7","volume":"34","author":"M De Luca","year":"2024","unstructured":"De Luca M, Shikora S, Eisenberg D, Angrisani L, Parmar C, Alqahtani A, et al. Scientific evidence for the updated guidelines on indications for metabolic and bariatric surgery (IFSO\/ASMBS). Obes Surg. 2024;34(11):3963\u20134096. https:\/\/doi.org\/10.1007\/s11695-024-07370-7.","journal-title":"Obes Surg"},{"issue":"8","key":"8418_CR27","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large Language models in medicine. Nat Med. 2023;29(8):1930\u201340.","journal-title":"Nat Med"},{"key":"8418_CR28","first-page":"22066","volume-title":"Is large Language model performance on reasoning tasks impacted by different ways questions are asked?","author":"SH Song","year":"2025","unstructured":"Song SH, Chakraborty M, Li Q, Tavanapong W. Is large Language model performance on reasoning tasks impacted by different ways questions are asked? Vienna, Austria: Association for Computational Linguistics; 2025. pp. 22066\u201381."},{"issue":"2","key":"8418_CR29","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1007\/s11695-024-07653-z","volume":"35","author":"M Mahjoubi","year":"2025","unstructured":"Mahjoubi M, Shahabi S, Sheikhbahaei S, Jazi AHD. Evaluating AI capabilities in bariatric surgery: A study on ChatGPT-4 and DALL\u00b7E 3\u2019s recognition and illustration accuracy. Obes Surg. 2025;35(2):638\u201341. https:\/\/doi.org\/10.1007\/s11695-024-07653-z.","journal-title":"Obes Surg"},{"key":"8418_CR30","first-page":"7388","volume-title":"Unveiling factual recall behaviors of large Language models through knowledge neurons","author":"Y Wang","year":"2024","unstructured":"Wang Y, Chen Y, Wen W, Sheng Y, Li L, Zeng DD. Unveiling factual recall behaviors of large Language models through knowledge neurons. Miami, Florida, USA: Association for Computational Linguistics; 2024. pp. 7388\u2013402."},{"issue":"12","key":"8418_CR31","doi-asserted-by":"publisher","first-page":"3971","DOI":"10.1007\/s11695-023-06903-w","volume":"33","author":"AHD Jazi","year":"2023","unstructured":"Jazi AHD, Mahjoubi M, Shahabi S, Alqahtani AR, Haddad A, Pazouki A, et al. Bariatric evaluation through AI: a survey of expert opinions versus ChatGPT-4 (BETA-SEOV). Obes Surg. 2023;33(12):3971\u201380. https:\/\/doi.org\/10.1007\/s11695-023-06903-w.","journal-title":"Obes Surg"},{"issue":"2","key":"8418_CR32","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s11695-025-07683-1","volume":"35","author":"A Abokhozima","year":"2025","unstructured":"Abokhozima A, El-Masry H, Hany M, Zidan MH. The utilization of bloom\u2019s taxonomy in bariatric surgery training: A comprehensive approach to mastery in surgery. Obes Surg. 2025;35(2):383\u20136. https:\/\/doi.org\/10.1007\/s11695-025-07683-1.","journal-title":"Obes Surg"}],"container-title":["Obesity Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11695-025-08418-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11695-025-08418-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11695-025-08418-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:24:18Z","timestamp":1781627058000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11695-025-08418-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,11]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["8418"],"URL":"https:\/\/doi.org\/10.1007\/s11695-025-08418-y","relation":{},"ISSN":["0960-8923","1708-0428"],"issn-type":[{"value":"0960-8923","type":"print"},{"value":"1708-0428","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,11]]},"assertion":[{"value":"28 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}