{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T08:39:40Z","timestamp":1792571980127,"version":"4.5.0"},"reference-count":46,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Mhealth Uhealth"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n AI-based tools for oral cancer screening have shown promising performance in curated image datasets, but their performance in real-world mobile community screening workflows remains less clear.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study evaluated the prospective field performance of a parameter-locked, mobile AI-assisted oral lesion triage system embedded in a human-supervised community oral cancer screening workflow.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted a prospective community-based field evaluation in eastern Taiwan from June 17 to December 31, 2025. Trained nonspecialist personnel acquired standard white-light intraoral images using handheld mobile devices during routine screening. The AI system incorporated on-site image quality assessment and lesion-level risk stratification into green, yellow, and red triage categories. Technically inadequate images after repeated acquisition attempts were classified as ungradable and excluded from performance analysis. Three board-certified oral and maxillofacial specialists established an operational clinical reference standard through structured image review and consensus adjudication. The primary outcome was lesion-level identification of high-risk lesions requiring specialist referral, defined as red versus nonred triage. Diagnostic performance was estimated with Wilson 95% CIs; precision-recall performance and preconsensus specialist agreement were also assessed.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Among 602 screened participants, 4283 interpretable intraoral images were included in expert adjudication and lesion-level analysis. The AI system flagged 68 red lesions; 12 (17.6%) were confirmed as high risk, and 4 additional high-risk lesions were identified during expert review, yielding 16 high-risk events for the primary red-triage analysis. For high-risk lesion identification, sensitivity was 75% (12\/16; 95% CI 50.5%-89.8%) and positive predictive value was 17.6% (12\/68; 95% CI 10.4%-28.4%); specificity, negative predictive value, and accuracy were 98.6% (3928\/3984), 99.9% (3928\/3932), and 98.5% (3940\/4000), respectively. Area under the receiver operating characteristic curve values were 0.957 for red, 0.931 for yellow, and 0.964 for green triage; precision-recall analysis showed area under the precision-recall curve values of 0.8235, 0.9052, and 0.9476, respectively. Preconsensus specialist agreement was high, with a Fleiss \u03ba of 0.921 and a Gwet AC1 of 0.981.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This mobile AI-assisted oral lesion triage system was feasibly integrated into a real-world community screening workflow operated by trained nonspecialist personnel. In this low-prevalence field setting, red triage showed moderate sensitivity and modest positive predictive value, supporting its use as human-supervised referral-prioritization support rather than autonomous diagnosis. Further multicenter studies with blinded assessment, participant-level outcomes, workflow-efficiency measures, and longitudinal follow-up are needed before clinical impact and scalability can be determined.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/101721","type":"journal-article","created":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T02:00:07Z","timestamp":1787968807000},"page":"e101721-e101721","source":"Crossref","is-referenced-by-count":0,"title":["Mobile AI-Assisted Oral Lesion Triage for Community Oral Cancer Screening: Prospective Field Evaluation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6016-5059","authenticated-orcid":false,"given":"Hao-Yun","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0605-3085","authenticated-orcid":false,"given":"Yu-Cheng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9292-9427","authenticated-orcid":false,"given":"Si-Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1463-8027","authenticated-orcid":false,"given":"Ling-Ying","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5737-6960","authenticated-orcid":false,"given":"Cheng-Ying","family":"Chou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0964-0840","authenticated-orcid":false,"given":"Jang-Jaer","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3995-1083","authenticated-orcid":false,"given":"Shyh-Jye","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1243-2463","authenticated-orcid":false,"given":"Chien-Chang","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,10,20]]},"reference":[{"issue":"12","key":"R1","doi-asserted-by":"publisher","first-page":"e767","DOI":"10.1016\/S1470-2045(17)30460-6","article-title":"Defining a global research and policy agenda for betel quid and areca nut","volume":"18","author":"Mehrtash","journal-title":"Lancet Oncol"},{"issue":"8","key":"R2","doi-asserted-by":"publisher","first-page":"1862","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","journal-title":"Oral Dis"},{"issue":"5","key":"R3","doi-asserted-by":"publisher","first-page":"e555","DOI":"10.1016\/S2214-109X(18)30127-X","article-title":"Changing cancer survival in China during 2003-15: a pooled analysis of 17 population-based cancer registries","volume":"6","author":"Zeng","journal-title":"Lancet Glob Health"},{"issue":"11","key":"R4","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1001\/jamaoto.2019.2414","article-title":"Association of delayed time to treatment initiation with overall survival and recurrence among patients with head and neck squamous cell carcinoma in an underserved urban population","volume":"145","author":"Liao","journal-title":"JAMA Otolaryngol Head Neck Surg"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","DOI":"10.1088\/2050-6120\/acf6ac","article-title":"Multimodal fluorescence imaging and spectroscopic techniques for oral cancer screening: a real-time approach","volume":"11","author":"Thapa","journal-title":"Methods Appl Fluoresc"},{"issue":"9","key":"R6","doi-asserted-by":"publisher","first-page":"2253","DOI":"10.1002\/hed.27843","article-title":"Detection of oral cancer and oral potentially malignant disorders using artificial intelligence-based image analysis","volume":"46","author":"Kouketsu","journal-title":"Head Neck"},{"issue":"8","key":"R7","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.26.8.086007","article-title":"Automatic detection of oral cancer in smartphone-based images using deep learning for early diagnosis","volume":"26","author":"Lin","journal-title":"J Biomed Opt"},{"issue":"11","key":"R8","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13112766","article-title":"Automated detection and classification of oral lesions using deep learning to detect oral potentially malignant disorders","volume":"13","author":"Tanriver","journal-title":"Cancers (Basel)"},{"issue":"8","key":"R9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0273508","article-title":"AI-based analysis of oral lesions using novel deep convolutional neural networks for early detection of oral cancer","volume":"17","author":"Warin","journal-title":"PLoS One"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-024-05195-5","article-title":"Development of an oral cancer detection system through deep learning","volume":"24","author":"Li","journal-title":"BMC Oral Health"},{"issue":"12 Suppl 2","key":"R11","doi-asserted-by":"publisher","first-page":"101975","DOI":"10.1016\/j.jormas.2024.101975","article-title":"A deep learning approach to detection of oral cancer lesions from intra oral patient images: a preliminary retrospective study","volume":"125","author":"Keser","journal-title":"J Stomatol Oral Maxillofac Surg"},{"issue":"S1","key":"R12","doi-asserted-by":"publisher","first-page":"465","DOI":"10.3233\/THC-248041","article-title":"Intelligent deep learning supports biomedical image detection and classification of oral cancer","volume":"32","author":"Chen","journal-title":"Technol Health Care"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-85920-4","article-title":"Artificial intelligence for image recognition in diagnosing oral and oropharyngeal cancer and leukoplakia","volume":"15","author":"Schmidl","journal-title":"Sci Rep"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI251270","article-title":"Oral cancer surveillance in remote areas using a smartphone digital platform","volume":"329","author":"Wongsapai","journal-title":"Stud Health Technol Inform"},{"issue":"6","key":"R15","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1016\/j.jobcr.2025.10.017","article-title":"Development and validation of an AI-based application for early detection and risk stratification of oral potentially malignant disorders","volume":"15","author":"Prabhune","journal-title":"J Oral Biol Craniofac Res"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1177\/23800844251403962","article-title":"Artificial intelligence helps diagnose oral potentially malignant disorders: a systematic review and meta-analysis","author":"Horvath","journal-title":"JDR Clin Trans Res"},{"issue":"6","key":"R17","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1364\/OL.555254","article-title":"Smartphone-based bimodal device (SBBD) for oral precancer diagnosis and biopsy guidance in clinical settings","volume":"50","author":"Nemichand","journal-title":"Opt Lett"},{"issue":"6","key":"R18","doi-asserted-by":"publisher","first-page":"4358","DOI":"10.1007\/s10278-025-01455-0","article-title":"Smartphone-based oral lesion image segmentation using deep learning","volume":"38","author":"Thakuria","journal-title":"J Imaging Inform Med"},{"issue":"4","key":"R19","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1158\/1940-6207.CAPR-24-0253","article-title":"Development and evaluation of an automated multimodal mobile detection of oral cancer imaging system to aid in risk-based management of oral mucosal lesions","volume":"18","author":"Mitbander","journal-title":"Cancer Prev Res (Phila)"},{"issue":"7","key":"R20","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1016\/j.jfma.2024.07.010","article-title":"Oral mucosal lesions triage via YOLOv7 models","volume":"124","author":"Hsu","journal-title":"J Formos Med Assoc"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.3389\/froh.2025.1659323","article-title":"Two-step pipeline for oral diseases detection and classification: a deep learning approach","volume":"6","author":"Ara\u00fajo","journal-title":"Front Oral Health"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2025.106138","article-title":"A deep learning method for diagnosis of oral potentially malignant disorders","volume":"167","author":"Cao","journal-title":"J Dent"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1002\/hed.26992","article-title":"Diagnostic accuracy of conventional oral examination for detecting oral cavity cancer and potentially malignant disorders in patients with clinically evident oral lesions: systematic review and meta-analysis","volume":"44","author":"Essat","journal-title":"Head Neck"},{"issue":"6","key":"R24","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1016\/j.oooo.2017.12.011","article-title":"Oral potentially malignant disorders: risk of progression to malignancy","volume":"125","author":"Speight","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1002\/hed.26006","article-title":"Potentially malignant disorders of the oral cavity and oral dysplasia: a systematic review and meta-analysis of malignant transformation rate by subtype","volume":"42","author":"Iocca","journal-title":"Head Neck"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1002\/hed.25973","article-title":"Malignant development in patients with oral potentially malignant disorders detected through nationwide screening: outcomes of 5-year follow-up at a single hospital","volume":"42","author":"Chiang","journal-title":"Head Neck"},{"issue":"9","key":"R27","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000024934","article-title":"Malignant transformation of oral potentially malignant disorders in Taiwan: an observational nationwide population database study","volume":"100","author":"Chiu","journal-title":"Medicine (Baltimore)"},{"issue":"5","key":"R28","doi-asserted-by":"publisher","DOI":"10.3390\/ijms22052252","article-title":"New insights into oral squamous cell carcinoma: from clinical aspects to molecular tumorigenesis","volume":"22","author":"Chen","journal-title":"Int J Mol Sci"},{"issue":"12","key":"R29","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1373\/clinchem.2015.246280","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies","volume":"61","author":"Bossuyt","journal-title":"Clin Chem"},{"issue":"11","key":"R30","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-012799","article-title":"STARD 2015 guidelines for reporting diagnostic accuracy studies: explanation and elaboration","volume":"6","author":"Cohen","journal-title":"BMJ Open"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.2196\/90759","article-title":"Toward retrieval-grounded evaluation for conversational large language model-based risk assessment","volume":"5","author":"Hu","journal-title":"JMIR AI"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2026.110741","article-title":"Comment on \u201cClassifying the clinical significance of common breast pain symptoms using a large language model, ChatGPT (GPT-4)\u201d","volume":"132","author":"Hu","journal-title":"Clin Imaging"},{"issue":"13","key":"R33","doi-asserted-by":"publisher","first-page":"811","DOI":"10.3109\/08958378.2014.955932","article-title":"Screening tests: a review with examples","volume":"26","author":"Maxim","journal-title":"Inhal Toxicol"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2017.00307","article-title":"Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice","volume":"5","author":"Trevethan","journal-title":"Front Public Health"},{"issue":"6","key":"R35","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.bjae.2020.03.002","article-title":"Bayes\u2019 formula: a powerful but counterintuitive tool for medical decision-making","volume":"20","author":"Webb","journal-title":"BJA Educ"},{"issue":"3","key":"R36","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/s13181-023-00953-3","article-title":"Biostatistics and epidemiology principles for the toxicologist: the \u201ctesty\u201d test characteristics part II: positive predictive value and negative predictive value","volume":"19","author":"Williams","journal-title":"J Med Toxicol"},{"issue":"3","key":"R37","doi-asserted-by":"publisher","DOI":"10.5041\/RMMJ.10527","article-title":"Interpreting PPV and NPV of diagnostic tests with uncertain prevalence","volume":"15","author":"Ben-Haim","journal-title":"Rambam Maimonides Med J"},{"issue":"7","key":"R38","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1007\/s10620-024-08427-4","article-title":"Development and validation of a colorectal cancer prediction model: a nationwide cohort-based study","volume":"69","author":"Isakov","journal-title":"Dig Dis Sci"},{"issue":"1","key":"R39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-08790-w","article-title":"Predicting time-to-first cancer diagnosis across multiple cancer types","volume":"15","author":"Lau","journal-title":"Sci Rep"},{"issue":"16","key":"R40","doi-asserted-by":"publisher","first-page":"2943","DOI":"10.1002\/sim.8163","article-title":"Quantifying risk stratification provided by diagnostic tests and risk predictions: comparison to AUC and decision curve analysis","volume":"38","author":"Katki","journal-title":"Stat Med"},{"key":"R41","unstructured":"Principles for quality management of oral mucosal examination in preventive oral health services [Report in Chinese]. Ministry of Health and Welfare, Taiwan. URL: https:\/\/www.mohw.gov.tw\/dl-95288-76196c53-62cc-4831-835d-bd3dddf4375e.html [Accessed 05-05-2026]"},{"key":"R42","unstructured":"2017 hospital cancer screening quality improvement programme: tender briefing [106\u5e74\u91ab\u9662\u764c\u75c7\u7be9\u6aa2\u54c1\u8cea\u7cbe\u9032\u8a08\u756b\u62db\u6a19\u8aaa\u660e]. Health Promotion Administration, Ministry of Health and Welfare, Taiwan. 2017. URL: https:\/\/pfp.hpa.gov.tw\/News\/4d4859a6-b440-41c6-9ad3-8268a026e482\/106%E5%B9%B4%E9%86%AB%E9%99%A2%E7%99%8C%E7%97%87%E7%AF%A9%E6%AA%A2%E5%93%81%E8%B3%AA%E7%B2%BE%E9%80%B2%E8%A8%88%E7%95%AB%E6%8B%9B%E6%A8%99%E8%AA%AA%E6%98%8E_%E4%BF%AEP.13%E5%AD%90%E6%8A%B9%E9%A6%96%E7%AF%A9%E5%B9%B4%E9%BD%A1.pdf [Accessed 05-05-2026]"},{"issue":"23","key":"R43","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1001\/jama.2023.22557","article-title":"Automation bias and assistive AI: risk of harm from AI-driven clinical decision support","volume":"330","author":"Khera","journal-title":"JAMA"},{"issue":"1","key":"R44","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","journal-title":"BMC Med"},{"issue":"1","key":"R45","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","journal-title":"Nat Med"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1016\/j.lana.2025.101138","article-title":"Automated classification of oral potentially malignant disorders and oral squamous cell carcinoma using a convolutional neural network framework: a cross-sectional study","volume":"47","author":"Saldivia-Siracusa","journal-title":"Lancet Reg Health Am"}],"container-title":["JMIR mHealth and uHealth"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T07:54:49Z","timestamp":1792569289000},"score":1,"resource":{"primary":{"URL":"https:\/\/mhealth.jmir.org\/2026\/1\/e101721"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,20]]},"references-count":46,"URL":"https:\/\/doi.org\/10.2196\/101721","relation":{},"ISSN":["2291-5222"],"issn-type":[{"value":"2291-5222","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,20]]},"article-number":"v14i12e101721"}}