A pilot study on diabetes detection using handheld fundus camera and mobile app development

Background: Diabetes, affecting more than 500 million individuals worldwide, is the most widespread non-communicable disease, globally. The early identification and effective management of diabetes are crucial for controlling its spread. Currently, the HbA1c test is the gold standard for the detection of diabetes with high confidence. But this is an invasive, expensive pathology test. Therefore, alternative non-invasive and inexpensive methods have been proposed in the literature for the early detection of diabetes. Methods: In this pilot study, we used a handheld fundus camera that simplifies the accessibility issue for doctors and patients in underprivileged communities, remote areas, enabling a quick and reasonably accurate diabetes diagnosis process. We invited participants from the community to share their demographic information, history of diabetes, and captured their retinal fundus images using the oDocs Nun IR handheld non-mydriatic fundus camera in a non-invasive manner (no dilation is required). Subsequently, we developed a deep learning model for early diagnosis of diabetes based on fundus image only. Moreover, we created an Android-based mobile application, DMPred, which utilizes the fundus images to predict the onset of diabetes. Results: The proposed model achieved an 86.4% accuracy rate in diabetes detection showing that handheld cameras can be effective and provide comparable results like tabletop cameras in the early diagnosis of diabetes. We also provide a comprehensive guideline, including necessary steps for transforming deep learning models into Android-based mobile applications for tech transfer. Conclusions: To the best of our knowledge, this article is the first demonstration of diabetes diagnosis using handheld fundus camera and mobile app. We believe that this pilot study and the proposed tech solution will support the larger community with limited clinical facilities and enhance the accessibility of technology for diabetes detection.