{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T08:31:33Z","timestamp":1786609893131,"version":"build-2736575974"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Galala University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>To evaluate the performance of a multimodal large language model (LLM) for longitudinal trajectory classification and risk stratification of oral lichen planus (OLP), compared with expert panel consensus. This retrospective diagnostic accuracy study included 300 patients with histopathologically confirmed OLP and at least 24 months of follow-up. Multimodal longitudinal case profiles (serial clinical records, intraoral photographs, and histopathology reports) were independently assessed by (ChatGPT, OpenAI) and an expert panel (the reference standard), both blinded to the results. The primary outcome was sensitivity for the detecting expert-defined high-risk cases (one-versus-rest). Secondary outcomes included overall trajectory classification and three-level risk stratification. Expert consensus classified 156 cases (52.0%) as stable benign, 92 (30.7%) as inflammatory progression, and 52 (17.3%) as suspicious malignant evolution. Risk stratification was 73 low (24.3%), 161 moderate (53.7%), and 66 high (22.0%). For high-risk detection, sensitivity was 78.8% (95% CI 67.2\u201387.5), and specificity was 99.6% (95% CI 97.6\u2013100.0). Overall trajectory classification accuracy was 94.7%. Three-level risk stratification accuracy was 76.3%, with most errors representing downward shifts (98.6%). The multimodal LLM showed high concordance with expert consensus for longitudinal OLP surveillance, with high accuracy of trajectory classification and high specificity for high-risk identification. These findings suggest that multimodal LLMs may support trajectory-based assessment through integration of longitudinal clinical information, although prospective external validation remains necessary.<\/jats:p>","DOI":"10.1038\/s41598-026-65667-2","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T08:04:58Z","timestamp":1786608298000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Trajectory-aware risk stratification of oral lichen planus using a multimodal large language model: a longitudinal diagnostic accuracy study"],"prefix":"10.1038","volume":"16","author":[{"given":"Fatma E. A.","family":"Hassanein","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salma M.","family":"Saad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radwa R.","family":"Hussein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5069-8257","authenticated-orcid":false,"given":"Asmaa","family":"Abou-Bakr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"issue":"2","key":"65667_CR1","doi-asserted-by":"publisher","first-page":"130","DOI":"10.4103\/ijdr.IJDR_802_20","volume":"34","author":"AA Ras","year":"2023","unstructured":"Ras, A. A., Kheir El Din, N. H., Talaat, A. M., Hussein, R. R. & Khalil, E. Mucocutaneous changes in end-stage renal disease under regular hemodialysis - A cross-sectional study. Indian J. Dent. Res. 34 (2), 130\u2013135 (2023).","journal-title":"Indian J. Dent. Res."},{"issue":"4","key":"65667_CR2","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1111\/odi.13323","volume":"27","author":"M Gonz\u00e1lez-Moles","year":"2021","unstructured":"Gonz\u00e1lez-Moles, M. et al. Worldwide prevalence of oral lichen planus: A systematic review and meta-analysis. Oral Dis. 27 (4), 813\u2013828 (2021).","journal-title":"Oral Dis."},{"issue":"8","key":"65667_CR3","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1111\/odi.13704","volume":"27","author":"S Warnakulasuriya","year":"2021","unstructured":"Warnakulasuriya, S. et al. Oral potentially malignant disorders: A consensus report from an international seminar on nomenclature and classification, convened by the WHO Collaborating Centre for Oral Cancer. Oral Dis. 27 (8), 1862\u20131880 (2021).","journal-title":"Oral Dis."},{"key":"65667_CR4","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.oraloncology.2017.03.012","volume":"68","author":"SMH Aghbari","year":"2017","unstructured":"Aghbari, S. M. H. et al. Malignant transformation of oral lichen planus and oral lichenoid lesions: A meta-analysis of 20095 patient data. Oral Oncol. 68, 92\u2013102 (2017).","journal-title":"Oral Oncol."},{"issue":"1","key":"65667_CR5","doi-asserted-by":"publisher","first-page":"43279","DOI":"10.1038\/s41598-025-28862-1","volume":"15","author":"FEA Hassanein","year":"2025","unstructured":"Hassanein, F. E. A. et al. Vision-based diagnostic gain of ChatGPT-5 and gemini 2.5 pro compared with human experts in oral lesion assessment. Sci. Rep. 15 (1), 43279 (2025).","journal-title":"Sci. Rep."},{"key":"65667_CR6","doi-asserted-by":"crossref","unstructured":"Abou-Bakr, A., El Barbary, A. & Hassanein, F. E. A. ChatGPT-5 vs oral medicine experts for rank-based differential diagnosis of oral lesions: a prospective, biopsy-validated comparison. Odontology (2025).","DOI":"10.1007\/s10266-025-01242-x"},{"key":"65667_CR7","doi-asserted-by":"crossref","unstructured":"Hassanein, F. et al. Diagnostic performance of ChatGPT-4o and DeepSeek-3 differential diagnosis of complex oral lesions: A multimodal imaging and case difficulty analysis. Oral Dis. 1\u201311 (2025).","DOI":"10.1111\/ODI.70007\/v2\/response1"},{"issue":"1","key":"65667_CR8","doi-asserted-by":"publisher","first-page":"109357","DOI":"10.1016\/j.identj.2025.109357","volume":"76","author":"A Robaian","year":"2026","unstructured":"Robaian, A., Hassanein, F. E. A., Hassan, M. T., Alqahtani, A. S. & Abou-Bakr, A. A multimodal large language model framework for clinical subtyping and malignant transformation risk prediction in oral Lichen Planus: A paired comparison with expert clinicians. Int. Dent. J. 76 (1), 109357 (2026).","journal-title":"Int. Dent. J."},{"issue":"6","key":"65667_CR9","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1016\/j.tripleo.2009.02.020","volume":"107","author":"M Rad","year":"2009","unstructured":"Rad, M. et al. Correlation between clinical and histopathologic diagnoses of oral lichen planus based on modified WHO diagnostic criteria. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endod. 107 (6), 796\u2013800 (2009).","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endod"},{"issue":"1","key":"65667_CR10","doi-asserted-by":"publisher","first-page":"37932","DOI":"10.1038\/s41598-025-22979-z","volume":"15","author":"FEA Hassanein","year":"2025","unstructured":"Hassanein, F. E. A., Ahmed, Y., Maher, S., Barbary, A. E. & Abou-Bakr, A. Prompt-dependent performance of multimodal AI model in oral diagnosis: a comprehensive analysis of accuracy, narrative quality, calibration, and latency versus human experts. Sci. Rep. 15 (1), 37932 (2025).","journal-title":"Sci. Rep."},{"issue":"4","key":"65667_CR11","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1055\/s-0042-1760300","volume":"17","author":"P Achararit","year":"2023","unstructured":"Achararit, P. et al. Artificial intelligence-based diagnosis of oral Lichen Planus using deep convolutional neural networks. Eur. J. Dent. 17 (4), 1275\u20131282 (2023).","journal-title":"Eur. J. Dent."},{"key":"65667_CR12","doi-asserted-by":"publisher","first-page":"e70566","DOI":"10.2196\/70566","volume":"4","author":"S AlFarabi Ali","year":"2025","unstructured":"AlFarabi Ali, S. et al. The diagnostic performance of large language models and oral medicine consultants for identifying oral lesions in text-based clinical scenarios: Prospective comparative study. JMIR AI. 4, e70566 (2025).","journal-title":"JMIR AI"},{"issue":"2","key":"65667_CR13","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1111\/odi.15169","volume":"31","author":"M Diniz-Freitas","year":"2025","unstructured":"Diniz-Freitas, M., Lago-M\u00e9ndez, L., Limeres-Posse, J. & Diz-Dios, P. Challenging ChatGPT-4V for the diagnosis of oral diseases and conditions. Oral Dis. 31 (2), 701\u2013706 (2025).","journal-title":"Oral Dis."},{"issue":"2","key":"65667_CR14","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.identj.2025.02.005","volume":"75","author":"L Samaranayake","year":"2025","unstructured":"Samaranayake, L. et al. The transformative role of artificial intelligence in dentistry: A comprehensive overview. Part 1: Fundamentals of AI, and its contemporary applications in dentistry. Int. Dent. J. 75 (2), 383\u2013396 (2025).","journal-title":"Int. Dent. J."},{"issue":"1","key":"65667_CR15","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1186\/s12903-021-01652-7","volume":"21","author":"F Tsushima","year":"2021","unstructured":"Tsushima, F. et al. Malignant transformation of oral lichen planus: a retrospective study of 565 Japanese patients. BMC Oral Health. 21 (1), 298 (2021).","journal-title":"BMC Oral Health"},{"key":"65667_CR16","doi-asserted-by":"crossref","unstructured":"Arduino, P. G. et al. Risk of malignant transformation in 3173 subjects with histopathologically confirmed oral Lichen Planus: A 33-year cohort study in Northern Italy. Cancers (Basel) 13 (22). (2021).","DOI":"10.3390\/cancers13225740"},{"issue":"11","key":"65667_CR17","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R. et al. Shortcut learning in deep neural networks. Nat. Mach. Intell. 2 (11), 665\u2013673 (2020).","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"65667_CR18","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","volume":"10","author":"S Lapuschkin","year":"2019","unstructured":"Lapuschkin, S. et al. Unmasking Clever Hans predictors and assessing what machines really learn. Nat. Commun. 10 (1), 1096 (2019).","journal-title":"Nat. Commun."},{"issue":"1","key":"65667_CR19","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1038\/s41405-025-00388-8","volume":"11","author":"H Yang","year":"2025","unstructured":"Yang, H., Li, G. & Zhao, C. Artificial intelligence in the study of oral lichen planus characteristics: a review. BDJ Open 11 (1), 91 (2025).","journal-title":"BDJ Open."},{"key":"65667_CR20","doi-asserted-by":"crossref","unstructured":"Yu, S. et al. Artificial intelligence diagnosing of oral Lichen Planus: A comparative study. Bioengineering (Basel) 11 (11). (2024).","DOI":"10.3390\/bioengineering11111159"},{"issue":"6","key":"65667_CR21","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1016\/j.oooo.2025.07.009","volume":"140","author":"A Pakfetrat","year":"2025","unstructured":"Pakfetrat, A. et al. Deep learning in oral lichen planus diagnosis: a systematic review of clinical image-based detection approaches. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. 140 (6), 696\u2013707 (2025).","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"65667_CR22","doi-asserted-by":"crossref","unstructured":"Bharti, A. et al. YOLOv8 powered deep learning framework for detection and classification of oral potentially malignant disorders and oral cancer using intraoral images. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. (2026).","DOI":"10.1016\/j.oooo.2026.04.028"},{"issue":"7","key":"65667_CR23","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/s00784-024-05762-8","volume":"28","author":"S Vinayahalingam","year":"2024","unstructured":"Vinayahalingam, S. et al. Advancements in diagnosing oral potentially malignant disorders: leveraging Vision transformers for multi-class detection. Clin. Oral Investig. 28 (7), 364 (2024).","journal-title":"Clin. Oral Investig"},{"issue":"11","key":"65667_CR24","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.17219\/acem\/104524","volume":"28","author":"K Jurczyszyn","year":"2019","unstructured":"Jurczyszyn, K. & Kozakiewicz, M. Differential diagnosis of leukoplakia versus lichen planus of the oral mucosa based on digital texture analysis in intraoral photography. Adv. Clin. Exp. Med. 28 (11), 1469\u20131476 (2019).","journal-title":"Adv. Clin. Exp. Med."},{"issue":"5","key":"65667_CR25","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1016\/j.ijom.2021.09.001","volume":"51","author":"K Warin","year":"2022","unstructured":"Warin, K., Limprasert, W., Suebnukarn, S., Jinaporntham, S. & Jantana, P. Performance of deep convolutional neural network for classification and detection of oral potentially malignant disorders in photographic images. Int. J. Oral Maxillofac. Surg. 51 (5), 699\u2013704 (2022).","journal-title":"Int. J. Oral Maxillofac. Surg."},{"issue":"8","key":"65667_CR26","doi-asserted-by":"publisher","first-page":"e0273508","DOI":"10.1371\/journal.pone.0273508","volume":"17","author":"K Warin","year":"2022","unstructured":"Warin, K. et al. AI-based analysis of oral lesions using novel deep convolutional neural networks for early detection of oral cancer. PLoS One. 17 (8), e0273508 (2022).","journal-title":"PLoS One"},{"key":"65667_CR27","doi-asserted-by":"crossref","unstructured":"Parola, M. et al. Image-Based Screening of Oral Cancer via Deep Ensemble Architecture. In: 2023 IEEE Symposium Series on Computational Intelligence (SSCI): 5\u20138 Dec. 2023 2023 1572\u20131578. (2023).","DOI":"10.1109\/SSCI52147.2023.10371865"},{"key":"65667_CR28","doi-asserted-by":"publisher","first-page":"102433","DOI":"10.1016\/j.compmedimag.2024.102433","volume":"117","author":"M Parola","year":"2024","unstructured":"Parola, M. et al. Towards explainable oral cancer recognition: Screening on imperfect images via Informed Deep Learning and Case-Based Reasoning. Comput. Med. Imaging Graph. 117, 102433 (2024).","journal-title":"Comput. Med. Imaging Graph."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-65667-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-65667-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-65667-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T08:16:12Z","timestamp":1786608972000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-65667-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["65667"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-65667-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"assertion":[{"value":"27 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study protocol was reviewed and approved by the Institutional Review Board of King Salman International University (approval number: [IRB014-2025]). Given the retrospective design and use of de-identified archival data, the requirement for informed consent was waived. The study was conducted in accordance with the Declaration of Helsinki.","order":2,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25294"}}