Cancer ScreeningNCT06862414
Application and Validation of a Smartphone-based Deep Learning System for Oral Potentially Malignant Disorders and Oral Cancer Screening
A study testing Smartphone-based deep learning system in people with Cancer Screening and Oral Cancer, run by National Taiwan University Hospital at 1 site in Taiwan.
Trial summary
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. Read more about this study
- Who is it for?
- Ages 19 years and olderHealthy volunteers can take part
- Conditions the study is for
- Cancer Screening, Oral Cancer, Oral Potentially Malignant Disorders
- What is being tested?
- Smartphone-based deep learning system
- Type of treatment
- Medical device
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 954 participants
- Where
- 1 siteTaiwan
- Study dates
- Mar 2025to Dec 2025
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 19 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Adult patients (age ≥18) visiting cancer screening center
Who cannot join
- Unable to cooperate to fully open mouth/ navigate tongue
- Unable to cooperate for the assessment
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
Taiwan1 site
Department of Family Medicine, National Taiwan University Hospital
Taipei, 100229
Shao-Yi Cheng, MD, MSc, DrPH, +886-2-23123456 ext. 266823, scheng2140@gmail.com
I Ann Hsiao, MD, +886-2-23123456 ext. 266634, iamiannhsiao@gmail.com
About this study
Official title: Application and Validation of a Smartphone-based Deep Learning System for Oral Potentially Malignant Disorders (OPMD) and Oral Cancer Screening
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.
Read more
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.
Read the 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.
- Being tested
- Smartphone-based deep learning system
- Keywords
- Deep learning systems, Artificial Intelligence
- Medical subject headings
- Mouth Neoplasms
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Smartphone-based deep learning systemDevice
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).
| Study group | Role | What they receive |
|---|---|---|
| A | Experimental | Deep learning system Receives: Device: Smartphone-based deep learning system |
| B | Active comparator | Board-certified dentist with deep learning system Receives: Device: Smartphone-based deep learning system |
| C | Active comparator | non-certified health providers (general practitioners) with deep learning system Receives: Device: Smartphone-based deep learning system |
What is being measured
The primary outcome is the main question the study is designed to answer.
Effectiveness and accuracy
The primary outcome is the sensitivity and specificity for the three referral grades (green, yellow and 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.
Measured: Within 6 months
Secondary outcomes (1)
Questionnaire
The secondary outcome is subjects' feedback of comfortability during exam evaluated by the visual analog scale (VAS) (a score out of 10). The time needed for screening will also be recorded for the assessment of efficiency.
Measured: Within 6 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted6 Mar 2025
- Study startMar 2025 (estimated)
- Primary completionOct 2025 (estimated)
- Study completionDec 2025 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (11)Papers the sponsor has linked to this study.
- Other trials for Cancer ScreeningStudies of the same condition, open and under way.
- More trials run by National Taiwan University HospitalThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Screening
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- An open, three-arm, randomized controlled trial will be done in a medical center in Northern Taiwan between Jan 2025 to Dec 2025
- Masking
- None (open label)
- Enrolment
- 954 participants (estimated)
Sponsor and investigators
- Lead sponsor
- National Taiwan University Hospital
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
- Investigators
- Shao-Yi Cheng, MD, MSc, DrPH, Study chair, Department of Family Medicine, College of Medicine and Hospital, National Taiwan University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT06862414
- Sponsor's protocol ID
- 202204032RIND
- Status last verified
- Feb 2025
- First submitted
- 2 Mar 2025
- Last updated
- 6 Mar 2025
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Undecided
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.
PubMed 39003230Tanriver 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.
PubMed 34199471Hegde 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.
PubMed 36389623Ng 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 Policy. 2022 Apr;27(2):133-140. doi: 10.1177/13558196211053110. Epub 2022 Jan 22.
PubMed 35068209Khanagar 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.
PubMed 34072804Gigliotti 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.
PubMed 30878273Peacock 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.
PubMed 18832270R 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.
PubMed 37732523Gonzalez-Moles MA, Aguilar-Ruiz M, Ramos-Garcia P. Challenges in the Early Diagnosis of Oral Cancer, Evidence Gaps and Strategies for Improvement: A Scoping Review of Systematic Reviews. Cancers (Basel). 2022 Oct 10;14(19):4967. doi: 10.3390/cancers14194967.
PubMed 36230890Warnakulasuriya S, Kujan O, Aguirre-Urizar JM, Bagan JV, Gonzalez-Moles MA, Kerr AR, Lodi G, Mello FW, Monteiro L, Ogden GR, Sloan P, Johnson NW. 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. 2021 Nov;27(8):1862-1880. doi: 10.1111/odi.13704. Epub 2020 Nov 26.
PubMed 33128420Stathopoulos P, Smith WP. Analysis of Survival Rates Following Primary Surgery of 178 Consecutive Patients with Oral Cancer in a Large District General Hospital. J Maxillofac Oral Surg. 2017 Jun;16(2):158-163. doi: 10.1007/s12663-016-0937-z. Epub 2016 Jul 8.
PubMed 28439154
Study at a glance
From the registry record, last updated by the sponsor on 6 Mar 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Application and Validation of a Smartphone-based Deep Learning System for Oral Potentially Malignant Disorders (OPMD) and Oral Cancer Screening
- ClinicalTrials.gov ID
- NCT06862414
- Acronym / sponsor ID
- 202204032RIND
- Keywords
- Deep learning systems, Artificial Intelligence
- Study type
- Interventional
- Recruitment status
- Not yet recruiting
- Enrolment
- 954 participants (estimated)
- Lead sponsor
- National Taiwan University HospitalUniversity, hospital or other
- Study start
- Mar 2025 (estimated)
- Primary completion
- Oct 2025 (estimated)
- Study completion
- Dec 2025 (estimated)
- First posted
- 6 Mar 2025 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Study design
- Primary purpose
- Screening
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Masking
- None (open label)
- Number of arms
- 3
- Model description
- An open, three-arm, randomized controlled trial will be done in a medical center in Northern Taiwan between Jan 2025 to Dec 2025
| Arm | Type | Receives |
|---|---|---|
| A | Experimental | Device: Smartphone-based deep learning systemDeep learning system |
| B | Active comparator | Device: Smartphone-based deep learning systemBoard-certified dentist with deep learning system |
| C | Active comparator | Device: Smartphone-based deep learning systemnon-certified health providers (general practitioners) with deep learning system |
Who may qualify
- Ages
- 19 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (1 listed)
- Adult patients (age ≥18) visiting cancer screening center
Key exclusion criteria (2 listed)
- Unable to cooperate to fully open mouth/ navigate tongue
- Unable to cooperate for the assessment
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Smartphone-based deep learning systemThe 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). | Device | A, B, C |
Primary outcome
Effectiveness and accuracy
Time frame: Within 6 months
The primary outcome is the sensitivity and specificity for the three referral grades (green, yellow and 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.
1 secondary outcome
Questionnaire
Time frame: Within 6 months
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 6 Mar 2025.
- Background: PubMed 39003230Hsu 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.
- Background: PubMed 34199471Tanriver 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.
- Background: PubMed 36389623Hegde 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.
- Background: PubMed 35068209Ng 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 Policy. 2022 Apr;27(2):133-140. doi: 10.1177/13558196211053110. Epub 2022 Jan 22.
- Background: PubMed 34072804Khanagar 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.
- Background: PubMed 30878273Gigliotti 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.
- Background: PubMed 18832270Peacock 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.
- Background: PubMed 37732523R 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.
- Background: PubMed 36230890Gonzalez-Moles MA, Aguilar-Ruiz M, Ramos-Garcia P. Challenges in the Early Diagnosis of Oral Cancer, Evidence Gaps and Strategies for Improvement: A Scoping Review of Systematic Reviews. Cancers (Basel). 2022 Oct 10;14(19):4967. doi: 10.3390/cancers14194967.
- Background: PubMed 33128420Warnakulasuriya S, Kujan O, Aguirre-Urizar JM, Bagan JV, Gonzalez-Moles MA, Kerr AR, Lodi G, Mello FW, Monteiro L, Ogden GR, Sloan P, Johnson NW. 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. 2021 Nov;27(8):1862-1880. doi: 10.1111/odi.13704. Epub 2020 Nov 26.
- Background: PubMed 28439154Stathopoulos P, Smith WP. Analysis of Survival Rates Following Primary Surgery of 178 Consecutive Patients with Oral Cancer in a Large District General Hospital. J Maxillofac Oral Surg. 2017 Jun;16(2):158-163. doi: 10.1007/s12663-016-0937-z. Epub 2016 Jul 8.
- Individual participant dataSharing planned: Undecided
Related trials for Cancer Screening
Active, not recruiting
Addressing Stigma in Screening and Diagnostic Delay for Cervical Cancer
Cervical Cancer Screening
Active, not recruiting
Master Protocol for Basket Clinical Trials of Targeted Therapies Based on Proteome and Whole Exome Sequencing Screening in Patients With Advanced Solid Tumors
Advanced Solid Tumors, Metastatic Solid Tumors
Recruiting
Developing and Implementing HPV SCREENED
Cervical Cancer Screening, Human Papilloma Virus
Not yet recruiting
Young Adult-Mediated Intervention to Increase Colorectal Cancer Screening
Young Adult-Mediated Intervention to Increase Colorectal Cancer Screening
Not yet recruiting
Screening and the Future of Enhanced MRI for Early Breast Cancer Detection
Breast Cancer Detection, Breast Cancer
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Shao-Yi Cheng, MD, MSc, DrPH study chair
Department of Family Medicine, College of Medicine and Hospital, National Taiwan University
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Smartphone-based deep learning system in people with Cancer Screening and Oral Cancer, run by National Taiwan University Hospital at 1 site in Taiwan.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 1 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: opening soon, as of the sponsor's last update on 6 Mar 2025. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Taiwan. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Shao-Yi Cheng, MD, MSc, DrPH (+886-2312-3456 ext. 266823, scheng2140@gmail.com), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Effectiveness and accuracy (time frame: Within 6 months). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT06862414, which also lists 11 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 6 Mar 2025; AzTrials last refreshed its copy on 26 Oct 2026.