Device can distinguish between patients with and without dry eyes

An artificial intelligence (AI) tool developed in Italy can be used to distinguish patients with dry eye disease (DED) from patients with healthy eyes. According to a study published in diagnosis.¹

Millions of people worldwide are affected by DED, a common disease of the ocular surface. DED can cause burning, a foreign body sensation in the eye, eye discomfort and dryness, all of which can lead to eye pain.² Accelerated tear film breakage, reduced tear volume and increased tear evaporation are some of the symptoms that constitute DED. To give patients a clear diagnosis of DED, at least one pathological sign must be assessed. DEvice, an AI developed in Italy, is a wearable prototype of an eye hygrometer that can assess the tear film. The aim of this study was to assess how effective the tool is in achieving adequate diagnostic accuracy for patients with DED.

Patients with a confirmed diagnosis of DED who attended the ocular surface clinic of Magna Crecia University in Catanzaro, Italy, were enrolled in this study between January and June 2023, along with healthy controls. Patients who had active ocular inflammation, had a history of contact lens wear, had recently undergone ocular surgery, or had used anti-inflammatory eye drops in the last month were excluded. Patients with DED were included if they had a noninvasive keratography breakup time (NIKBUT) of less than 10 seconds and an Ocular Surface Disease Index (OSDI) survey score of 13 or higher.

Tear meniscus height (TMH), meibomian gland loss (MGL), NIKBUT-First, NIKBUT-Average and bulbar redness were calculated. NIKBUT-First was defined as the time to first tear film disruption and NIKBUT-Average was defined as the mean duration of rupture cases. All patients were examined 30 minutes after a keratography examination using the device to measure relative humidity (RH) and temperature around the ocular surface. All participants completed the OSDI questionnaire to rate their eye pain during the past week.

The study included 40 eyes of 40 patients, of whom 23 were female and the mean age (SD) was 38 (17.14) years. Eyes with DED and healthy eyes each made up 50% of the cohort and were compared. Age and gender did not differ significantly between the two groups.

No significant difference was found between the mean (SD) TMH value in patients with DED (0.27 (0.10) mm) and patients with healthy eyes (0.26 (0.10) mm), as well as for bulbar redness (1.04 (0.34) in patients with DED vs. 0.99 (0.45) in patients without) and MGL (1.00 (95% CI, 1.00-2.00) in patients with DED vs. 1.00 (95% CI, 0.00-1.00) in patients without DED).

However, a statistically significantly higher relative humidity value was observed in patients with DED after using DEvice than in patients without DED (85.93% (10.63%) vs. 73.05% (12.84%)). This did not hold for the relationship with mean temperature values, which were not statistically significant between the two groups (27.12 (1.75) °C in patients with DED vs. 27.08 (1.72) °C in patients without DED).

The accuracy of relative humidity as a predictive factor for DED was calculated using the area under the curve (AUC). The sensitivity was determined to be 60%, the specificity to be 95%, and the AUC to be 0.782 (95% CI, 0.6401–0.9249). The mean OSDI scores also differed significantly between patients with DED (42.15 (19.04)) and those without (13.45 (7.61)).

This study had some limitations. The samples included in the study were smaller, which may have resulted in a lack of statistical significance. DED was not separated by subtype, severity, or treatment, which may have led to ambiguous results. The discriminatory power may have been limited due to the small sample size.

DEvice was able to distinguish patients with DED from patients with healthy eyes by assessing the relative humidity in all eyes examined. The noninvasive test could help with patient screening in the future. To confirm this result, future studies with larger sample sizes should be conducted.

References

1. Vaccaro S, Borselli M, Scalia G et al. A novel noninvasive screening tool for dry eyes. diagnosis. 2024;14:1209. doi:10.3390/diagnostics14121209
2. Dry eye. National Eye Institute. Updated November 15, 2023. Accessed June 28, 2024. https://www.nei.nih.gov/learn-about-eye-health/eye-conditions-and-diseases/dry-eye