Abstract

Dry eye disease (DED) is a prevalent condition causing discomfort, visual disturbances, and tear film instability. The iDEA tool combines ocular thermography, meibography, infrared imaging, and tear break-up time analysis using machine learning. This study aims to investigate thermographic changes in individuals with and without dry eye symptoms under different temperature conditions. 24 subjects were studied, with 14 having normal scores and 10 experiencing symptoms. Both groups showed increased severity scores on ocular surface thermography with lower room temperature and humidity. However, there was no statistically significant difference in severity scores between normal and DED individuals at different conditions. A significant difference was observed in severity scores on the environmental subscore. In conclusion, severity scores derived from OST help understand and interpret DED symptoms and reduce the symptom-sign mismatch.