{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T15:04:02Z","timestamp":1794668642975,"version":"4.9.1"},"reference-count":27,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"1","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Oral cancer may develop from precursor lesions and conditions termed oral potentially malignant disorders (OPMD), although not all patients progress to cancer in their lifetime. Managing patients with OPMD is challenging due to lesion recurrence and uncertain malignant progression risk following surgical excision. This study developed a multitask AI-based model to predict the risk of treatment failure, malignant progression, and recurrence among patients with OPMD treated by surgery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>This study utilized multidimensional data from 366 retrospective patients with OPMD treated in 2 tertiary centers to construct an AI model to predict 3 treatment outcomes among patients with OPMD. Multifaceted prognostic variables were collected for the cohort and used to train four AI supervised learning models, followed by optimal model selection. Area under the receiver operating characteristic curve (AUC) and Brier scores (BSs) were used to assess model performance. External testing of the model was also performed, and metrics were compared to the WHO and binary dysplasia grading systems (current standards). We further assessed the net benefit and explainability of the final multitask model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The outperforming model (TabPFN) had good AUC values of 0.829 (0.729\u20130.929), 0.912 (0.836\u20130.988), and 0.791 (0.683\u20130.899) for predicting treatment failure, malignant progression, and lesion recurrence at external testing. The BSs of the model for all three treatment outcome predictive tasks were also optimal (0.085\u20130.147). Furthermore, the AI model had a superior net benefit than the WHO and binary epithelial dysplasia grading systems in assessing the need for close monitoring among patients with OPMD treated by surgery. The explainability of the model was also successfully implemented.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>The multitask AI-based model developed with multidimensional data has good discriminatory performance, calibration, and net benefit, showing potential for comprehensive risk assessment and clinical decision support in the surgical management of patients with OPMD to promote early detection of oral cancer.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/js9.0000000000003592","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T16:03:43Z","timestamp":1759853023000},"page":"1392-1401","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":5,"title":["Artificial intelligence for predicting post-excision recurrence and malignant progression in oral potentially malignant disorders: a retrospective cohort study"],"prefix":"10.1097","volume":"112","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3493-1463","authenticated-orcid":false,"given":"John","family":"Adeoye","sequence":"first","affiliation":[{"name":"Division of Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7143-3370","authenticated-orcid":false,"given":"Yu-Xiong","family":"Su","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Surgery, Faculty of Dentistry, University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"R1-20260518","first-page":"229\u201363","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"R2-20260518","doi-asserted-by":"crossref","first-page":"105451","DOI":"10.1016\/j.oraloncology.2021.105451","article-title":"Overview of oral cavity squamous cell carcinoma: risk factors, mechanisms, and diagnostics","volume":"121","author":"Chamoli","year":"2021","journal-title":"Oral Oncol"},{"key":"R3-20260518","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.3390\/cancers13061321","article-title":"Time-to-treatment in oral cancer: causes and implications for survival","volume":"13","author":"Saka-Herr\u00e1n","year":"2021","journal-title":"Cancers (Basel)"},{"key":"R4-20260518","doi-asserted-by":"crossref","first-page":"4967","DOI":"10.3390\/cancers14194967","article-title":"Challenges in the early diagnosis of oral cancer, evidence gaps and strategies for improvement: a scoping review of systematic reviews","volume":"14","author":"Gonz\u00e1lez-Moles","year":"2022","journal-title":"Cancers (Basel)"},{"key":"R6-20260518","doi-asserted-by":"crossref","first-page":"1862\u201380","DOI":"10.1111\/odi.13704","article-title":"Oral potentially malignant disorders: a consensus report from an international seminar on nomenclature and classification, convened by the WHO collaborating centre for oral cancer","volume":"27","author":"Warnakulasuriya","year":"2021","journal-title":"Oral Dis"},{"key":"R7-20260518","doi-asserted-by":"crossref","first-page":"104550","DOI":"10.1016\/j.oraloncology.2019.104550","article-title":"Oral potentially malignant disorders: a comprehensive review on clinical aspects and management","volume":"102","author":"Warnakulasuriya","year":"2020","journal-title":"Oral Oncol"},{"key":"R8-20260518","doi-asserted-by":"crossref","first-page":"442\u201353","DOI":"10.4103\/ijc.IJC_128_21","article-title":"Consensus guidelines on management of oral potentially malignant disorders","volume":"59","author":"Birur","year":"2022","journal-title":"Indian J Cancer"},{"key":"R9-20260518","doi-asserted-by":"crossref","first-page":"1066\u201375","DOI":"10.1177\/00220345241266519","article-title":"Recurrence in oral leukoplakia: a systematic review and meta-analysis","volume":"103","author":"Bhattarai","year":"2024","journal-title":"J Dent Res"},{"key":"R10-20260518","doi-asserted-by":"crossref","first-page":"252\u201357","DOI":"10.1007\/s12663-022-01764-9","article-title":"Occurrence of second oral potentially malignant disorder following excision of primary lesion: a prospective study of cases from a tertiary care centre","volume":"22","author":"Kudva","year":"2023","journal-title":"J. Maxillofac. Oral Surg"},{"key":"R11-20260518","doi-asserted-by":"crossref","first-page":"1947\u201376","DOI":"10.1111\/odi.13993","article-title":"Oral epithelial dysplasia: recognition, grading and clinical significance","volume":"27","author":"Odell","year":"2021","journal-title":"Oral Dis"},{"key":"R12-20260518","doi-asserted-by":"crossref","first-page":"1677\u201386","DOI":"10.1097\/JS9.0000000000000979","article-title":"Leveraging artificial intelligence for perioperative cancer risk assessment of oral potentially malignant disorders","volume":"110","author":"Adeoye","year":"2024","journal-title":"Int J Surg"},{"key":"R13-20260518","doi-asserted-by":"crossref","first-page":"788\u201399","DOI":"10.1016\/j.jobcr.2020.09.005","article-title":"Current challenges and the diagnostic pitfalls in the grading of epithelial dysplasia in oral potentially malignant disorders: a review","volume":"10","author":"Gupta","year":"2020","journal-title":"J Oral Biol Craniofac Res"},{"key":"R14-20260518","doi-asserted-by":"crossref","first-page":"4\u20139","DOI":"10.1038\/s41416-021-01633-1","article-title":"Artificial intelligence in oncology: current applications and future perspectives","volume":"126","author":"Luchini","year":"2022","journal-title":"Br. J. Cancer"},{"key":"R15-20260518","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1038\/s41746-021-00549-7","article-title":"Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review","volume":"5","author":"de Hond","year":"2022","journal-title":"Npj Digital Med"},{"key":"R16-20260518","first-page":"100082","article-title":"Transparency in the reporting of artificial INtelligence\u2013the TITAN guideline","volume":"10","author":"Agha","year":"2025","journal-title":"Prem J Sci"},{"key":"R17-20260518","first-page":"100081","article-title":"Revised Strengthening the reporting of cohort, cross-sectional and case-control studies in surgery (STROCSS) guideline: an update for the age of artificial Intelligence","volume":"10","author":"Agha","year":"2025","journal-title":"Prem J Sci"},{"key":"R18-20260518","doi-asserted-by":"crossref","first-page":"69\u201380","DOI":"10.1111\/odi.15140","article-title":"Malignant transformation of oral leukoplakia: systematic review and comprehensive meta-analysis","volume":"31","author":"Pimenta-Barros","year":"2025","journal-title":"Oral Dis"},{"key":"R19-20260518","doi-asserted-by":"crossref","first-page":"691\u2013700","DOI":"10.1111\/jop.13440","article-title":"Malignant transformation rate of oral leukoplakia in the past 20\u2009years: a systematic review and meta-analysis","volume":"52","author":"Guan","year":"2023","journal-title":"J Oral Pathol Med"},{"key":"R20-20260518","doi-asserted-by":"crossref","first-page":"1881\u201395","DOI":"10.1111\/odi.13810","article-title":"Malignant transformation of oral leukoplakia: systematic review and meta-analysis of the last 5 years","volume":"27","author":"Aguirre-Urizar","year":"2021","journal-title":"Oral Dis"},{"key":"R21-20260518","first-page":"573\u201387","article-title":"Clinical predictors of malignant transformation and recurrence in oral potentially malignant disorders: a systematic review and meta-analysis","volume":"134","author":"MdP","year":"2022","journal-title":"Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology"},{"key":"R22-20260518","doi-asserted-by":"crossref","first-page":"886404","DOI":"10.3389\/fonc.2022.886404","article-title":"Clinical and histological prognostic factors of recurrence and malignant transformation in a large series of oral potentially malignant disorders","volume":"12","author":"Lorini","year":"2022","journal-title":"Front Oncol"},{"key":"R26-20260518","doi-asserted-by":"crossref","first-page":"5\u201332","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"R28-20260518","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"R29-20260518","doi-asserted-by":"crossref","first-page":"872","DOI":"10.3390\/diagnostics11050872","article-title":"Recurrence in oral premalignancy: clinicopathologic and Immunohistochemical analysis","volume":"11","author":"Georgaki","year":"2021","journal-title":"Diagnostics"},{"key":"R30-20260518","doi-asserted-by":"crossref","first-page":"1151\u201359","DOI":"10.1038\/s41379-022-01067-x","article-title":"Prediction of malignant transformation and recurrence of oral epithelial dysplasia using architectural and cytological feature specific prognostic models","volume":"35","author":"Mahmood","year":"2022","journal-title":"Mod Pathol"},{"key":"R31-20260518","doi-asserted-by":"crossref","first-page":"105421","DOI":"10.1016\/j.ijmedinf.2024.105421","article-title":"Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: a systematic review","volume":"186","author":"Uppal","year":"2024","journal-title":"Int J Med Inform"},{"key":"R32-20260518","first-page":"807\u201314","article-title":"Surgical treatment compared with \u201cwait and see\u201d in patients affected by oral leukoplakia to prevent oral cancer: preliminary data from a multicenter randomized controlled trial","volume":"31","author":"Lombardi","year":"2025","journal-title":"Oral Dis"}],"container-title":["International Journal of Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/JS9.0000000000003592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:15:53Z","timestamp":1779110153000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/JS9.0000000000003592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/js9.0000000000003592","relation":{},"ISSN":["1743-9159"],"issn-type":[{"value":"1743-9159","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,7]]},"assertion":[{"value":"2025-06-12","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-21","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}