Feasibility of Tear Meniscus Height Measurements Obtained with a Smartphone-Attachable Portable Device and Agreement of the Results with Standard Slit Lamp Examination

Borselli, Massimiliano; Toro, Mario Damiano; Rossi, Costanza; Taloni, Andrea; Khemlani, Rohan; Nakayama, Shintato; Nishimura, Hiroki; Shimizu, Eisuke; Scorcia, Vincenzo; Giannaccare, Giuseppe

doi:10.3390/diagnostics14030316

Cited by 6 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Portable and inexpensive devices could help with the wider adoption of DED screening in healthcare settings with limited access to hightech imaging. For instance, a recent study proposed the use of a smartphone-attachable device for TMH calculation, whose results were in good agreement with the measurements obtained with conventional slit lamp examination [41].…”

Section: Discussionsupporting

confidence: 73%

A Novel Noninvasive Screening Tool for Dry Eye Disease

Vaccaro,

Borselli,

Scalia

et al. 2024

Diagnostics

Self Cite

View full text Add to dashboard Cite

Purpose: To assess the feasibility and the diagnostic accuracy of the new tool, DEvice© (AI, Rome, Italy), for screening patients with dry eye disease (DED). Methods: This study was performed at the University Magna Græcia of Catanzaro. Enrolled patients were classified as affected by DED (group 1) or not (group 2) using an already validated tool (Keratograph 5M, Oculus, Germany), evaluating the noninvasive keratograph breakup time (NIKBUT), tear meniscus height (TMH), meibomian gland loss (MGL), and bulbar redness. All the patients were then examined by means of DEvice©, which allowed the measurement of the relative humidity (RH) and temperature of the ocular surface. Symptoms were scored using the Ocular Surface Disease Index (OSDI) questionnaire. Results: Overall, 40 patients (17 males and 23 females, mean age 38.0 ± 17.1 years) were included: of these, 20 belonged to group 1 and the remaining 20 to group 2. Using Keratograph 5M, significant differences between groups 1 and 2 were detected for NIKBUT-first (respectively, 4.97 ± 1.85 vs. 13.95 ± 4.8 s; p < 0.0001) and for NIKBUT-average (10.55 ± 4.39 vs. 15.96 ± 4.08 s; p = 0.0003). No statistically significant changes were detected for TMH (p = 0.565), MGL (p = 0.051), and bulbar redness (p = 0.687). Using Device©, a statistically significant higher value of RH was found in group 1 compared to group 2 (respectively, 85.93 ± 10.63 vs. 73.05 ± 12.84%; p = 0.0049). A statistically significant correlation was found between RH and OSDI (r = 0.406; p = 0.009). The value RH showed a discriminating power to detect DED with an AUC = 0.782 (standard error 0.07264; 95% CI 0.6401–0.9249; p = 0.0022). Conclusions: The DEvice© can effectively discriminate DED patients from healthy subjects. The parameter RH showed good sensitivity, making this tool ideal for a fast and noninvasive DED screening.

show abstract

Section: Discussionsupporting

confidence: 73%

A Novel Noninvasive Screening Tool for Dry Eye Disease

Vaccaro,

Borselli,

Scalia

et al. 2024

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

Epidemiological survey of anterior segment diseases in Japanese isolated island using a portable slit-lamp device in home-based cases in Miyako Island

Shimizu,

Hisajima,

Nakayama

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The ophthalmic diseases often affect the elderly and require proper diagnosis, treatments, and follow ups. However, many cases lack adequate eye care due to limited resources and decreased daily living activities among individuals. Despite the importance of ophthalmic home care, epidemiological research in this area has been lacking. This study utilized portable ophthalmological equipment to conduct an epidemiological research of anterior segment diseases in patients receiving home-based medical care in Japanese isolated island “Miyako island”. A retrospective examination was conducted on home visit cases from a single facility in Miyako island (Dr. Gon Clinic). Data from 147 cases were collected and analyzed which the data are all recorded by the home care doctors and send the data to the cloud in order to make a diagnosis by the ophthalmologists. Findings included various anterior segment eye diseases such as Ptosis, meibomian gland dysfunction, conjunctival chalasis, corneal opacity, conjunctival hyperemia, pterygium, and cataract. Notably, over half of the cases (51.67%) had not undergone cataract surgery although the average age are notably high (85.69 ± 12.11 age of years). Among those without surgery, all showed signs of moderate to severe cataracts, with severity increasing with age. Additionally, a shallow anterior chamber depth was observed in one-third of these cases (33.63%) which considerable to receive a surgery to prevent the acute glaucoma attack. From our study, to ensure that patients in remote islands as Miyako island do not miss opportunities for eye care, there is an urgent need for the establishment of a supportive medical system.

show abstract

The Use of Artificial Intelligence for Estimating Anterior Chamber Depth from Slit-Lamp Images Developed Using Anterior-Segment Optical Coherence Tomography

Shimizu,

Tanaka,

Nishimura

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Primary angle closure glaucoma (PACG) is a major cause of visual impairment, particularly in Asia. Although effective screening tools are necessary, the current gold standard is complex and time-consuming, requiring extensive expertise. Artificial intelligence has introduced new opportunities for innovation in ophthalmic imaging. Anterior chamber depth (ACD) is a key risk factor for angle closure and has been suggested as a quick screening parameter for PACG. This study aims to develop an AI algorithm to quantitatively predict ACD from anterior segment photographs captured using a portable smartphone slit-lamp microscope. We retrospectively collected 204,639 frames from 1586 eyes, with ACD values obtained by anterior-segment OCT. We developed two models, (Model 1) diagnosable frame extraction and (Model 2) ACD estimation, using SWSL ResNet as the machine learning model. Model 1 achieved an accuracy of 0.994. Model 2 achieved an MAE of 0.093 ± 0.082 mm, an MSE of 0.123 ± 0.170 mm, and a correlation of R = 0.953. Furthermore, our model’s estimation of the risk for angle closure showed a sensitivity of 0.943, specificity of 0.902, and an area under the curve (AUC) of 0.923 (95%CI: 0.878–0.968). We successfully developed a high-performance ACD estimation model, laying the groundwork for predicting other quantitative measurements relevant to PACG screening.

show abstract

Feasibility of Tear Meniscus Height Measurements Obtained with a Smartphone-Attachable Portable Device and Agreement of the Results with Standard Slit Lamp Examination

Cited by 6 publications

References 42 publications

A Novel Noninvasive Screening Tool for Dry Eye Disease

A Novel Noninvasive Screening Tool for Dry Eye Disease

Epidemiological survey of anterior segment diseases in Japanese isolated island using a portable slit-lamp device in home-based cases in Miyako Island

The Use of Artificial Intelligence for Estimating Anterior Chamber Depth from Slit-Lamp Images Developed Using Anterior-Segment Optical Coherence Tomography

Contact Info

Product

Resources

About