1. What data in particular will be shared?
   Response - All of the individual participant data collected during the trial, after de-identification.
   


2. What additional supporting information will be shared?
   Response -  Study Protocol
   Response -  Statistical Analysis Plan
   Response - Informed Consent Form
   Response - Clinical Study Report
   Response -  Analytic Code
   
   
3. Who will be able to view these files?
   Response - Researchers whose proposed use of the data has been approved by an independent review committee identified for this purpose.
   


4. For what types of analyses will this data be available?
   Response - To achieve aims in the approved proposal.
   


5. By what mechanism will data be made available?
   Response - Proposals should be directed to [punitr007@gmail.com].
   


6. For how long will this data be available start date provided 01-01-2027 and end date provided 01-12-2030?
   Response - Beginning 9 months and ending 36 months following article publication.
   


7. Any URL or additional information regarding plan/policy for sharing IPD? 
   Additional Information - Nil

Title of the proposed research project: Development of point of care cytology screening tool for Oral potentially malignant disorders and Oral squamous cell carcinoma using Deep learning Convolutional Neural Network

Screening of oral potentially malignant disorders (OPMDs) such as Leukoplakia and oral squamous cell carcinoma (OSCC) in remote areas often rely on traditional techniques which can be time consuming, costly and inaccessible. There is also a shortage of trained healthcare professionals in these regions, leading to delays in screening and initiation of treatment. These limitations highlight the need for innovative, accessible and accurate screening tool that can be deployed in remote settings for early screening of oral cancer.

Novelty

The novelty lies in the convergence of mobile technology, AI-based screening, and portable microscopy to create a user-friendly screening tool for OPMDs and OSCC in low resourced remote setting. This approach enables real-time analysis of PAP smears directly on a smartphone, facilitating screening accuracy and timely intervention in low resourced areas given the doctor patient ratio is relatively poor.

 Objectives

1. To develop Deep learning convolutional neural network algorithm for screening of papanicoloau (PAP) stained smears of OPMDs and OSCC.

2. Training of dataset and validation of model

3. To Develop point of care cytology screening tool for screening of OPMDs and OSCC.

4. Clinical validation of the screening tool

Methods

1. Data Collection and Pre-processing

2. Training and Validation

3. Deployment and Integration

4. Clinical Validation

Expected Outcome: Development of point of care cytology screening tool and deep learning model for screening of OPMDs and OSCC.