ISSN: 2578-465X
Authors: Carolyn Yu Tung Wong
Current Diagnostic Challenges in Dry Eye Disease Dry eye disease (DED) is a challenging condition to pin down, given the various probable aetiologies, signs, and symptoms. DED is characterised by its loss of tear-film homeostasis, ocular surface inflammation, hyperosmolarity, eye discomfort, and visual abnormalities [1]. However, the signs of DED are occasionally inconsistent with the symptoms stated by patients [1]. There is presently no one clinical test that can uniformly pinpoint DED [1]. DED is diagnosed using a variety of subjective tests and symptom questions, including tear breakup time (TBUT), Schirmer's test (ST), fluorescein and lissamine green staining of the corneal (CSS1) and conjunctival surface (CSS2), and the ocular surface disease index (OSDI) [1]. Furthermore, the differentiation of different tear film breakup patterns is thought to be at the centre of a tear film-oriented diagnosis, which helps elucidate the pathophysiology of DED (i.e., identify the insufficient component of the tear film or of the corneal surface epithelium responsible for TFBU), sub classify DED, and select the optimal topical therapy (decide on the most appropriate treatment) [2]. Additionally, although meibomian gland dysfunction (MGD) is the leading cause of evaporative DED and one of the most common conditions encountered in DED, diagnosing MGD can be difficult due to the non-specific nature of the symptoms and great inter-examiner variability in grading clinical variables associated with MGD [3]. As a result, standardised and universal diagnostic and decision-making tools in DED are highly valued. Artificial intelligence (AI) through machine learning (ML) and deep learning (DL) has garnered attention in the ophthalmological field, particularly in the screening and diagnosis of retinal and optic nerve conditions [4]. These AI algorithms perform imageintensive analyses on fundus or optical coherence tomography (OCT) images [4]. Similarly, in the current practices of DED, AI is expected to facilitate the data-intensive analysis of DED signs and symptoms when diagnosing, triaging, and managing DED patients
Keywords: Artificial Intelligence; Optical Coherence Tomography; Eye; Cornea
