Machine learning-based prediction of tear osmolarity for contact lens practice.

PURPOSE: This study addressed the utilisation of machine learning techniques to estimate tear osmolarity, a clinically significant yet challenging parameter to measure accurately. Elevated tear osmolarity has been observed in contact lens wearers and is associated with contact lens-induced dry eye, a common cause of discomfort leading to discontinuation of lens wear. METHODS: The study explored machine learning, regression and classification techniques to predict tear osmolarity using routine clinical parameters. The data set consisted of 175 participants, primarily healthy subjects eligible for soft contact lens wear. Various clinical assessments were performed, including symptom assessment with the Ocular Surface Disease Index and 5-Item Dry Eye Questionnaire (DEQ-5), tear meniscus height (TMH), tear osmolarity, non-invasive keratometric tear film break-up time (NIKBUT), ocular redness, corneal and conjunctival fluorescein staining and Meibomian glands loss. RESULTS: The results revealed that simple linear regression was insufficient for accurate osmolarity prediction. Instead, more advanced regression models achieved a moderate level of predictive power, explaining approximately 32% of the osmolarity variability. Notably, key predictors for osmolarity included NIKBUT, TMH, ocular redness, Meibomian gland coverage and the DEQ-5 questionnaire. In classification tasks, distinguishing between low (<299 mOsmol/L), medium (300-307 mOsmol/L) and high osmolarity (>308 mOsmol/L) levels yielded an accuracy of approximately 80%. Key parameters for classification were similar to those in regression models, emphasising the importance of NIKBUT, TMH, ocular redness, Meibomian glands coverage and the DEQ-5 questionnaire. CONCLUSIONS: This study highlights the potential benefits of integrating machine learning into contact lens research and practice. It suggests the clinical utility of assessing Meibomian glands and NIKBUT in contact lens fitting and follow-up visits. Machine learning models can optimise contact lens prescriptions and aid in early detection of conditions like dry eye, ultimately enhancing ocular health and the contact lens wearing experience.

Tear Film Surface Quality in Modern Daily Disposable Contact Lens Wear.

OBJECTIVES: As reported previously, tear film surface quality (TFSQ) should be considered in contact lens (CL) fitting. This study followed noninvasive keratograph tear film break-up time (NIKBUT) in CL wearers for 12 months to validate its clinical utility in predicting CL performance. METHODS: Fifty-five subjects (M/F=17/38) aged 26±4 years were prescribed silicone hydrogel or hydrogel CLs. The study included baseline measurements without CLs; 2 visits for CL fitting and control; follow-up after 3, 6, and 12 months of CL wear; and postwear visit without CLs. Ocular Surface Disease Index (OSDI), 8-Item Contact Lens Dry Eye Questionnaire (CLDEQ-8), first and mean NIKBUT (F/M-NIKBUT), fluorescein tear film break-up time (FBUT), and ocular surface staining were evaluated. RESULTS: Post hoc analysis of each pair of visits showed differences between baseline and all CL visits for F-NIKBUT, M-NIKBUT, FBUT, and corneal staining. No difference was reported in symptoms. In addition, differences between baseline and postwear visits were noted in OSDI, M-NIKBUT, FBUT, and corneal staining, with three of the latter parameters showing a downward trend. CONCLUSIONS: No changes in TFSQ and symptoms were reported over 12 months. Introducing NIKBUT as part of routine CL fitting is advised to improve CL fit and predict success.

Meibomian glands structure in daily disposable soft contact lens wearers: a one-year follow-up study.

PURPOSE: To assess the impact of daily disposable soft contact lenses on meibomian gland morphology over a period of 12 months. METHODS: Forty-one subjects (33 experienced and 8 neophytes) were fitted with either silicone-hydrogel or hydrogel daily contact lenses. The study protocol included four visits: baseline, day-2 for contact lens fit and follow-up measurements, as well as after 6 and 12 months of lens wear. Non-contact infrared meibography images were acquired with Keratograph 5M topographer (www.oculus.de) and analysed with an automated method, which objectively estimates the area of gland atrophy, gland length and width, number of glands and gland irregularity. Protocol at follow-up visits also included symptom assessment with the Ocular Surface Disease Index and clinical assessment of tear meniscus height, bulbar and limbal redness, tear osmolarity, non-invasive fluorescein break-up time and ocular surface staining. RESULTS: Statistically significant differences were found in gland atrophy (p = 0.02) and length (p = 0.008) between experienced and novel contact lens wearers at the baseline visit. Changes over time (after 6 and 12 months) were found in gland atrophy (p = 0.02) and the number of glands (p = 0.01) in subjects fitted with hydrogel contact lenses. Changes in gland atrophy between baseline and 12 months of lens wear correlated with changes in corneal staining (r = 0.40, p = 0.03) and fluorescein break-up time in subjects fitted with silicone-hydrogel lenses (r = 1-0.43, p = 0.02). CONCLUSIONS: Contact lens wear impacts meibomian gland morphology. However, changes are either long-term or characteristic to an early phase. Subjects with no history of contact lens wear exhibit better meibomian gland condition than experienced wearers. During one year of contact lens wear, meibomian gland morphology changes in subjects wearing daily disposable hydrogel lenses.

The tear turnover and tear clearance tests - a review.

INTRODUCTION: The aim is to provide a summary of methods available for the assessment of tear turnover and tear clearance rates. The review defines tear clearance and tear turnover and describes their implication for ocular surface health. Additionally, it describes main types of techniques for measuring tear turnover, including fluorescein tear clearance tests, techniques utilizing electromagnetic spectrum and tracer molecule and novel experimental techniques utilizing optical coherence tomography and fluorescein profilometry. AREAS COVERED: Internet databases (PubMed, Science Direct, Google Scholar) and most frequently cited references were used as a principal resource of information on tear turnover rate and tear clearance rate, presenting methodologies and equipment, as well as their definition and implications for the anterior eye surface health and function. Keywords used for data-search were as follows: tear turnover, tear clearance, fluorescein clearance, scintigraphy, fluorophotometry, tear flow, drainage, tear meniscus dynamics, Krehbiel flow and lacrimal functional unit. EXPERT COMMENTARY: After decades, the topic of tear turnover assessment has been reintroduced. Recently, new techniques have been developed to propose less invasive, less time consuming and simpler methodologies for the assessment of tear dynamics that have the potential to be utilized in clinical practice.

The utility of measuring tear film break-up time for prescribing contact lenses.

PURPOSE: To evaluate the clinical value of non-invasive keratograph tear film breakup time (NIKBUT) in the assessment of pre-corneal and pre-lens tear film quality for prescribing contact lenses (CLs). METHODS: Forty-six subjects aged 25.5±4.3 (mean±standard deviation) years were recruited. Visual acuity (VA), anterior eye health checks and NIKBUT were evaluated. On the following day, subjects were fitted with a daily Silicon Hydrogel (SiHy) CL in one eye and a Hydrogel (Hy) CL in the other. After four hours one material for both eyes was chosen based on a qualitative analysis which included VA, CL fitting and comfort. Information about the first and the mean NIKBUT was then contrasted against the prescription decision. RESULTS: Thirty-four subjects were fitted with SiHy and twelve with Hy CL. No statistically significant differences were found for both NIKBUT parameters between left and right eye at baseline (p=0.38 and p=0.50, respectively) and post four hours of CL wear (p=0.61 and p=0.06). The chosen lens did not always correspond to longer NIKBUT. In 39.1% and 34.8% of cases (i.e., 18 and 16 out of 46), there was a match between prescription decision and the first and the mean NIKBUT results, respectively. CONCLUSIONS: Although there is no evidence whether tear film surface quality measurement has a superior diagnostic values compared to other traditional clinical measures used in practice, NIKBUT measurements have provided additional information that could be of interest during CL fit.

Evaluating tear clearance rate with optical coherence tomography.

PURPOSE: To assess the early-phase of tear clearance rate (TCR) with anterior segment optical coherence tomography (OCT) and to determine the association between TCR and other clinical measures of the tear film in a group of young subjects with different levels of tear film quality. METHODS: TCR was classified as the percentage decrease of subject's inferior tear meniscus height 30s after instillation of 5µl 0.9% saline solution. Fifty subjects (32F and 18M) aged (mean±standard deviation) 25.5±4.3 years volunteered for the study. It consisted of a review of medical history, Ocular Surface Disease Index (OSDI) questionnaire, tear film osmolarity measurements, slit lamp examination and TCR estimation based on dynamic measurements of the lower tear meniscus with OCT. Estimates of TCR were contrasted against subject age and tear film measures commonly used for dry eye diagnosis, which includes OSDI score, fluorescein tear film break-up time (FBUT), tear meniscus height (TMH), blinking frequency, tear film osmolarity and corneal staining. RESULTS: The group mean TCR was 29±13% and 36±19% respectively after 30 and 60s margin after saline solution instillation. Statistically significant correlations were found between TCR and FBUT (r2=0.319, p<0.001), blinking frequency (r2=0.138, p<0.01), tear film osmolarity (r2=0.133, p<0.01) and subject's age (r2=0.095, p<0.05). CONCLUSIONS: Anterior segment optical coherence tomography allows following changes of tear meniscus morphology post saline solution instillation and evaluating the TCR. OCT based TCR might be used as additional measure of the lacrimal functional unit.

Qualitative assessment of tear dynamics with fluorescein profilometry.

PURPOSE: To describe a new methodology for tear-film dynamics assessment by observing fluorescein decay rate over time and to understand the relationship between the newly defined tear fluorescein washout rate (TFWR) and other measures of the tear film behaviour. METHODS: Forty subjects (24F/16M) aged (mean±standard deviation) 31.8±14.2years volunteered for the study. It consisted of the review of medical history, McMonnies questionnaire (McMQ), slit lamp examination, and TFWR using a newly-developed fluorescein profilometry. The repeatability of TFWR measurements was assessed. TFWR estimates were contrasted against patient age, McMQ score, daytime, fluorescein tear film break-up time (FTBUT), tear meniscus height (TMH) and blink frequency. RESULTS: Mean repeatability of the method was 28.13±9.59%. The group mean TFWR was 39±23% at 30-s mark after the beginning of measurements, ranging from 1.4% to 83%. This indicates that TFWR is highly subject-dependent. Statistically significant correlations were found between the percentage TFWR and McMQ score (r2=0.214, p=0.001) as well as FTBUT (r2=0.136, p=0.009). No statistically significant correlations were found between TFWR and age, daytime, TMH, and blink frequency. CONCLUSIONS: Fluorescein profilometry allows clinicians to follow dynamic changes in the tear film on the entire ocular surface and may be used for qualitative assessment of the tear film dynamics.