Abstract
Background: Celiac disease arises from gluten consumption and shares symptoms with other conditions, leading to delayed diagnosis. Untreated celiac disease heightens the risk of autoimmune disorders, neurological issues, and certain cancers like lymphoma while also impacting skin health due to intestinal disruptions.
Objective: This study uses facial photos to distinguish individuals with celiac disease from those without. Surprisingly, there is a lack of research involving transfer learning for this purpose despite its benefits such as faster training, enhanced performance, and reduced overfitting. While numerous studies exist on endoscopic intestinal photo classification and few have explored the link between facial morphology measurements and celiac disease, none has concentrated on diagnosing celiac disease through facial photo classification. Methods: This study aimed to utilize transfer learning techniques in this gap area of study to identify discernible facial differences between patients with celiac disease and healthy individuals to enable diagnosis using transfer learning. A dataset containing 100 adult facial images of individuals with or without celiac condition was utilized.
Results: By employing transfer learning techniques, the model achieved moderate accuracy (approximately 50%) when classifying facial images of patients during testing.
Conclusion: This promising outcome indicates the potential development of a diagnostic tool for celiac disease via transfer learning in medical image analysis absent prior studies in this field.