Application and Validation of a Smartphone-based Deep Learning System for Oral Potentially Malignant Disorders and Oral Cancer Screening
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- The protocol lists: Smartphone-based deep learning system.
- Who it may be relevant to
- Registry conditions: Cancer Screening, Oral Cancer, Oral Potentially Malignant Disorders. Basic parameters: from 19 years · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- Taiwan
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
Official title
Application and Validation of a Smartphone-based Deep Learning System for Oral Potentially Malignant Disorders (OPMD) and Oral Cancer Screening
Overview
The goal of this clinical trial is to learn if smartphone-based deep learning system works to accurately detect oral potentially malignant disorders and oral cancer in adults. It will also learn about if it is as effective as assessments conducted by dentists and non-certified health provider. We expect that the deep learning system will have higher sensitivity in detecting oral potentially malignant disorders and oral cancer, where as the dentists and non-certified health providers will exhibit higher specificity in screening. Participants will be grouped into three arms: deep learning system (arm A) or board-certified dentist with deep learning system (arm B) or non-certified health providers (general practitioners) with deep learning system (arm C). Oral cancer risk factors, such as habits of smoking or having chewed betel nut or alcohol drinking, would be recorded by anonymous questionnaires.
Detailed description
Background:
Oral cancer remains one of the leading causes of cancer-related deaths in Taiwan and worldwide. Artificial intelligence has the potential to improve oral cancer screening, enabling early detection by addressing healthcare access issues with high-quality solutions.
Objective:
To validate the smartphone-based deep learning system's accuracy in detecting oral potentially malignant disorders (OPMD) and oral cancer, while also demonstrating it is as effective as assessments conducted by dentists and non-certified health providers.
Methods:
Design, Setting and Participants: An open, three-arm, randomized controlled trial will be done in a medical center in Northern Taiwan between Jan 2025 to Dec 2025. The trial will include subjects aged 18 years or older who visit the cancer screening center for all kinds of screening. Oral cancer risk factors, such as habits of smoking or having chewed betel nut or alcohol drinking, would be recorded by anonymous questionnaires.
Interventions: Eligible subjects would be randomized in a 1:1:1 ratio using a computer-generated randomization algorithm to deep learning system (arm A) or board-certified dentist with deep learning system (arm B) or non-certified health providers (general practitioners) with deep learning system (arm C). The deep learning system in arm B and C would only be used for subsequent comparison and would not assist manual interpretation.
Main Outcomes and Measures: The primary outcome is the sensitivity and specificity for the three referral grades (benign (green), potentially malignant (yellow), and malignant (red)) by the deep learning system, dentists and non-certified health providers. The area under the curve (AUC) for each receiver operating characteristic (ROC) curve will also be calculated. The secondary outcome is subjects' feedback of comfortability during exam and the time needed for assessment.
Anticipated Results:
We hypothesize that deep learning systems will have higher sensitivity in detecting OPMD and oral cancer, whereas dentists and general practitioners will exhibit higher specificity in screening. The results could assist us in enhancing the oral cancer screening promotion process.
Interventions
- Device Smartphone-based deep learning system
The smartphone-based deep learning system was trained using a dataset of over 50,000 white-light macroscopic images collected between 2006 and 2013 to develop the YOLOv7 model. Lesions were categorized into three referral grades: benign (green), potentially malignant (yellow), and malignant (red).
Primary outcome measures
- Effectiveness and accuracy [Time frame: Within 6 months]
Secondary outcome measures (1)
- Questionnaire [Time frame: Within 6 months]
Eligibility criteria
Inclusion criteria
- Adult patients (age ≥18) visiting cancer screening center
Exclusion criteria
- Unable to cooperate to fully open mouth/ navigate tongue
- Unable to cooperate for the assessment
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: Yes
Study design
- Allocation
- Randomized
- Model
- Parallel assignment
- Masking
- Open label
- Primary purpose
- Screening
Study locations
Taiwan · 1 center
- Department of Family Medicine, National Taiwan University Hospital — Taipei
Publications
- Hsu Y, Chou CY, Huang YC, Liu YC, Lin YL, Zhong ZP, Liao JK, Lee JC, Chen HY, Lee JJ, Chen SJ. Oral mucosal lesions triage via YOLOv7 models. J Formos Med Assoc. 2025 Jul;124(7):621-627. doi: 10.1016/j.jfma.2024.07.010. Epub 2024 Jul 12. PMID 39003230
- Tanriver G, Soluk Tekkesin M, Ergen O. Automated Detection and Classification of Oral Lesions Using Deep Learning to Detect Oral Potentially Malignant Disorders. Cancers (Basel). 2021 Jun 2;13(11):2766. doi: 10.3390/cancers13112766. PMID 34199471
- Hegde S, Ajila V, Zhu W, Zeng C. Artificial intelligence in early diagnosis and prevention of oral cancer. Asia Pac J Oncol Nurs. 2022 Aug 24;9(12):100133. doi: 10.1016/j.apjon.2022.100133. eCollection 2022 Dec. PMID 36389623
- Ng SW, Syamim Syed Mohd Sobri SN, Zain RB, Kallarakkal TG, Amtha R, Wiranata Wong FA, Rimal J, Durward C, Chea C, Jayasinghe RD, Vatanasapt P, Saleha Binti Ibrahim Tamin N, Cheng LC, Mazlipah Binti Ismail S, Tepirou C, Ariff Bin Abdul Rahman Z, Rajendran S, Kanapathy J, Liew CS, Cheong SC. Barriers to early detection and management of oral cancer in the Asia Pacific region. J Health Serv Res Polic PMID 35068209
- Khanagar SB, Naik S, Al Kheraif AA, Vishwanathaiah S, Maganur PC, Alhazmi Y, Mushtaq S, Sarode SC, Sarode GS, Zanza A, Testarelli L, Patil S. Application and Performance of Artificial Intelligence Technology in Oral Cancer Diagnosis and Prediction of Prognosis: A Systematic Review. Diagnostics (Basel). 2021 May 31;11(6):1004. doi: 10.3390/diagnostics11061004. PMID 34072804
- Gigliotti J, Madathil S, Makhoul N. Delays in oral cavity cancer. Int J Oral Maxillofac Surg. 2019 Sep;48(9):1131-1137. doi: 10.1016/j.ijom.2019.02.015. Epub 2019 Mar 13. PMID 30878273
- Peacock ZS, Pogrel MA, Schmidt BL. Exploring the reasons for delay in treatment of oral cancer. J Am Dent Assoc. 2008 Oct;139(10):1346-52. doi: 10.14219/jada.archive.2008.0046. PMID 18832270
- R VC, C R, Sridhar P, Ramachandra C, Kumar M. Barriers related to Oral Cancer Screening, Diagnosis and Treatment in Karnataka, India. Gulf J Oncolog. 2023 Sep;1(43):19-24. PMID 37732523
Identifiers
NCT: NCT06862414 · 202204032RIND