Non-Invasive Dry Eye Disease Detection using Infrared Thermography Images

Background/Objectives: Dry eye disease (DED) is a condition that affects quality of life due to the loss of tear film stability and reduced tear production. The limited availability of eye care professionals, along with traditional diagnostic methods that are invasive, non-portable, and time-consuming, leads to delayed detection and interferes with timely treatment. This study aimed to develop a screening method for DED using a smartphone equipped with an infrared thermal camera (IRT). Methods: This study included infrared thermography (IRT) images of 40 subjects (22 normal and 58 DED). Ocular surface temperature changes at three regions of interest (ROIs): nasal cornea, center cornea, and temporal cornea, were compared with Tear Film Break-up Time (TBUT) and Ocular Surface Disease Index (OSDI) scores. Statistical correlations and independent t-tests were performed, while machine learning (ML) models classified normal vs. DED eyes. Results: In these preliminary results, DED eyes exhibited a significantly faster cooling rate (p < .001). TBUT showed a negative correlation with OSDI (r = -0.802, p < .001) and positive correlations with cooling rates in the nasal cornea (r = 0.717, p < .001), center cornea (r = 0.764, p < .001), and temporal cornea (r = 0.669, p < .001) regions. Independent t-tests confirmed significant differences between normal and DED eyes across all parameters (p < .001). The Quadratic Support Vector Machine (SVM) achieved the highest accuracy among SVM models (90.54%), while the k-Nearest Neighbours (k-NN) model using Euclidean distance (k = 3) outperformed overall with 91.89% accuracy, demonstrating strong potential for DED classification. Conclusions: IRT offers a fast, portable, and non-invasive screening tool for DED. The high classification accuracy of SVM and k-NN models supports IRT’s potential for early DED detection with excellent sensitivity and specificity.