Justification of the study: The current smartphone-based AI models require a clinician and an external attachment for assessment. Currently available smartphone-based applications for DED interpret the results based on blink rate and maximum blink interval, but not based on smartphone-based images. Limited prevalence data are available for the Karnataka region, which varies across different geographic areas and climates. The increasing prevalence of DED in younger individuals, fuelled by prolonged screen time and modern lifestyle habits, highlights the need for early detection strategies. It is essential to evaluate the prevalence of DED and explore its associations with occupational exposure, environmental factors, lifestyle patterns, and systemic comorbidities to better understand its occurrence and clinical severity. Many individuals with DED tend to seek clinical care only after symptoms have developed. This delay could be reduced through a smartphone-based, AI-integrated self-screening application that requires no clinician assistance. This tool would be cost-effective, minimally invasive, and capable of enabling rapid and early detection, facilitating timely management of DED. The ability of individuals to screen themselves conveniently via their smartphones can promote earlier ophthalmology consultations and support better ocular health and overall well-being.

Aim: To develop a smartphone-based artificial intelligence integrated screening tool for detecting dry eye disease

Objective: To develop and validate an AI model to detect dry eye disease and to assess the prevalence and associated factors of DED

Expected outcome of the study: A  smartphone-based self-screening AI application for dry eye detection