{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T21:14:23Z","timestamp":1790802863601,"version":"4.1.0"},"reference-count":34,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Periodontitis is a chronic gum disease affecting approximately 42% of adults aged 30 years and older in the United States. Training dental students to accurately diagnose and manage periodontitis is a critical component of dental education and clinical care. Recent advances in large language models offer new opportunities to support both domains, yet their performance in periodontal diagnosis remains largely unexplored, particularly for newer models such as GPT-5.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study conducted an exploratory evaluation of GPT-5\u2019s ability to stage and grade periodontitis.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A total of 25 publicly available clinical cases explicitly reporting periodontitis stage and grade were identified through Google and PubMed searches. Each case description was entered into GPT-5 using a zero-shot prompting approach to assess guideline-based reasoning without exemplar conditioning. The model\u2019s predictions were compared with the published reference diagnoses. Performance was measured using accuracy, 95% CI, unweighted Cohen \u03ba, and weighted Cohen \u03ba.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Across these cases, GPT-5 showed marked class-dependent performance and a tendency to overestimate disease severity. Grading performance was notably imbalanced, with high recall for grade C but substantially lower discrimination for grade B. GPT-5 achieved a staging accuracy of 68% (95% CI 48.4%-82.8%) and a grading accuracy of 77.3% (95% CI 56.6%-89.9%), with corresponding Cohen \u03ba values of 0.454 (95% CI 11.0%-75.6%) and 0.179 (95% CI \u221215.8% to 63.8%), respectively. While staging performance showed fair agreement beyond chance, the low \u03ba for grading indicates poor agreement and limited reliability in distinguishing periodontal disease severity.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n These findings suggest that although GPT-5 demonstrates potential for guideline-based periodontitis staging and grading, its current diagnostic performance, particularly for periodontitis grading, limits its use in clinical assessment and educational training. Meaningful application in periodontal diagnosis and training will require substantial improvements in reliability and rigorous validation in larger, more diverse, and prospectively collected datasets.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/88407","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:52:34Z","timestamp":1775508754000},"page":"e88407-e88407","source":"Crossref","is-referenced-by-count":5,"title":["Evaluation of GPT-5 in Periodontitis Staging and Grading: Retrospective Observational Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4087-7415","authenticated-orcid":false,"given":"Ihunna","family":"Amugo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9318-6535","authenticated-orcid":false,"given":"Katie Lee","family":"Frederickson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5264-2780","authenticated-orcid":false,"given":"Harshana","family":"Rajakaruna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1712-3256","authenticated-orcid":false,"given":"Hua","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7259-570X","authenticated-orcid":false,"given":"Pandu","family":"Gangula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6372-3669","authenticated-orcid":false,"given":"Anil","family":"Shanker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5125-3724","authenticated-orcid":false,"given":"Qingguo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"key":"R1","unstructured":"GPT-5 system card. OpenAI. 2025. URL: https:\/\/cdn.openai.com\/gpt-5-system-card.pdf [Accessed 21-03-2026]"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-43436-9","article-title":"Comparing ChatGPT and GPT-4 performance in USMLE soft skill assessments","volume":"13","author":"Brin","journal-title":"Sci Rep"},{"issue":"7972","key":"R3","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","journal-title":"Nature"},{"issue":"7","key":"R4","doi-asserted-by":"publisher","DOI":"10.1007\/s00784-024-05799-9","article-title":"Performance of ChatGPT in classifying periodontitis according to the 2018 classification of periodontal diseases","volume":"28","author":"Tastan Eroglu","journal-title":"Clin Oral Investig"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.26502\/droh.0069","article-title":"ChatGPT to enhance learning in dental education at a historically black medical college","volume":"7","author":"Rahad","journal-title":"Dent Res Oral Health"},{"key":"R6","doi-asserted-by":"crossref","unstructured":"Ahmad B Saleh K Alharbi S Alqaderi H Jeong YN . Artificial intelligence in periodontology: performance evaluation of ChatGPT, Claude, and Gemini on the in-service examination. medRxiv. Preprint posted online on May 31, 2024. [doi: 10.1101\/2024.05.29.24308155]","DOI":"10.1101\/2024.05.29.24308155"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","article-title":"Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models","volume":"2","author":"Kung","journal-title":"PLOS Digit Health"},{"issue":"5","key":"R8","doi-asserted-by":"publisher","DOI":"10.1056\/AIdbp2300192","article-title":"GPT versus resident physicians \u2014 a benchmark based on official board scores","volume":"1","author":"Katz","journal-title":"NEJM AI"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.2196\/47564","article-title":"User intentions to use ChatGPT for self-diagnosis and health-related purposes: cross-sectional survey study","volume":"10","author":"Shahsavar","journal-title":"JMIR Hum Factors"},{"key":"R10","unstructured":"Presiado M Montero A Lopes L Hamel L . KFF health misinformation tracking poll: artificial intelligence and health information. Kaiser Family Foundation. 2024. URL: https:\/\/www.kff.org\/public-opinion\/kff-health-misinformation-tracking-poll-artificial-intelligence-and-health-information\/ [Accessed 21-03-2026]"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/47621","article-title":"The potential of ChatGPT as a self-diagnostic tool in common orthopedic diseases: exploratory study","volume":"25","author":"Kuroiwa","journal-title":"J Med Internet Res"},{"key":"R12","unstructured":"Du D Paluch R Stevens G M\u00fcller C . Exploring patient trust in clinical advice from AI-driven LLMs like ChatGPT for self-diagnosis. arXiv. Preprint posted online on Feb 2, 2024. [doi: 10.48550\/arxiv.2402.07920]"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.2196\/56797","article-title":"ChatGPT use among pediatric health care providers: cross-sectional survey study","volume":"8","author":"Kisvarday","journal-title":"JMIR Form Res"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.2196\/58801","article-title":"Global health care professionals\u2019 perceptions of large language model use in practice: cross-sectional survey study","volume":"11","author":"Ozkan","journal-title":"JMIR Med Educ"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1016\/j.jaad.2023.12.062","article-title":"Can ChatGPT vision diagnose melanoma? An exploratory diagnostic accuracy study","volume":"90","author":"Shifai","journal-title":"J Am Acad Dermatol"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.2196\/67551","article-title":"Evaluating the diagnostic accuracy of ChatGPT-4 Omni and ChatGPT-4 Turbo in identifying melanoma: comparative study","volume":"8","author":"Sattler","journal-title":"JMIR Dermatol"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.2196\/55508","article-title":"Assessing the utility of multimodal large language models (GPT-4 Vision and Large Language and Vision Assistant) in identifying melanoma across different skin tones","volume":"7","author":"Cirone","journal-title":"JMIR Dermatol"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1177\/22925503251315489","article-title":"Beyond the surface: assessing GPT-4\u2019s accuracy in detecting melanoma and suspicious skin lesions from dermoscopic images","author":"Perlmutter","journal-title":"Plast Surg (Oakv)"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.2196\/51344","article-title":"Evaluation of ChatGPT\u2019s real-life implementation in undergraduate dental education: mixed methods study","volume":"10","author":"Kavadella","journal-title":"JMIR Med Educ"},{"issue":"7","key":"R20","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/j.adaj.2018.04.023","article-title":"Periodontitis in US adults: National Health and Nutrition Examination Survey 2009-2014","volume":"149","author":"Eke","journal-title":"J Am Dent Assoc"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1111\/jcpe.12945","article-title":"Staging and grading of periodontitis: framework and proposal of a new classification and case definition","volume":"45 Suppl 20","author":"Tonetti","journal-title":"J Clin Periodontol"},{"issue":"S1","key":"R22","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1002\/JPER.18-0157","article-title":"A new classification scheme for periodontal and peri-implant diseases and conditions - introduction and key changes from the 1999 classification","volume":"89 Suppl 1","author":"Caton","journal-title":"J Periodontol"},{"issue":"S1","key":"R23","doi-asserted-by":"publisher","first-page":"S74","DOI":"10.1002\/JPER.17-0719","article-title":"Periodontal health and gingival diseases and conditions on an intact and a reduced periodontium: consensus report of workgroup 1 of the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions","volume":"89 Suppl 1","author":"Chapple","journal-title":"J Periodontol"},{"issue":"23","key":"R24","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15233052","article-title":"Evaluating GPT-5 for melanoma detection using dermoscopic images","volume":"15","author":"Wang","journal-title":"Diagnostics (Basel)"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Liu Y Deng G Xu Z et al. A hitchhiker\u2019s guide to jailbreaking ChatGPT via prompt engineering. Presented at: SEA4DQ \u201924: 4th International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems\/Internet of Things; Jul 15, 2024; Porto de Galinhas, Brazil. [doi: 10.1145\/3663530.3665021]","DOI":"10.1145\/3663530.3665021"},{"key":"R26","unstructured":"Sahoo P Singh AK Saha S Jain V Mondal S Chadha A . A systematic survey of prompt engineering in large language models: techniques and applications. arXiv. Preprint posted online on Feb 5, 2024. [doi: 10.48550\/arXiv.2402.07927]"},{"key":"R27","unstructured":"Qi X Zeng Y Xie T et al. Fine-tuning aligned language models compromises safety, even when users do not intend to! Arxiv. Preprint posted online on Oct 5, 2023. [doi: 10.48550\/arXiv.2310.03693]"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","journal-title":"BMJ"},{"issue":"10","key":"R29","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","article-title":"The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","volume":"31","author":"Sounderajah","journal-title":"Nat Med"},{"key":"R30","unstructured":"Meyerson J . Perio classification for the INBDE. Bootcamp.com. 2025. URL: https:\/\/bootcamp.com\/blog\/bootcamp-coms-perio-classification-for-the-inbde [Accessed 21-03-2026]"},{"issue":"12","key":"R31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000692","article-title":"Classification of periodontitis stage and grade using natural language processing techniques","volume":"3","author":"Ameli","journal-title":"PLOS Digit Health"},{"issue":"2","key":"R32","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.crad.2022.09.131","article-title":"DECIDE-AI: a new reporting guideline and its relevance to artificial intelligence studies in radiology","volume":"78","author":"Vasey","journal-title":"Clin Radiol"},{"issue":"2","key":"R33","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41591-021-01229-5","article-title":"DECIDE-AI: new reporting guidelines to bridge the development-to-implementation gap in clinical artificial intelligence","volume":"27","author":"DECIDE-AI Steering Group","journal-title":"Nat Med"},{"issue":"4","key":"R34","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/j.jclinepi.2007.11.008","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"61","author":"von Elm","journal-title":"J Clin Epidemiol"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e88407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:15:03Z","timestamp":1782839703000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e88407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.2196\/88407","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,6]]},"article-number":"v10i1e88407"}}