Effect of artificial tears on dynamic optical quality in patients with dry eye disease.

BACKGROUND: In clinical practice, fluctuating vision or decreased quality of vision is a common complaint in DED patients. Our study was designed to investigate the change in dynamic optical quality in dry eye patients after the use of artificial tears. METHODS: Fifty-nine patients with dry eye disease (DED) and 31 control subjects were included in this prospective case-control study. There was no significant difference in age and sex between these two groups (P = 0.342, P = 0.847, respectively). Clinical evaluation of the ocular surface included Ocular Surface Disease Index (OSDI), tear film break-up time (TBUT), lipid layer thickness (LLT), and Schirmer I test. DED patients were divided into two groups, mild (31 patients) and severe (28 patients). The optical quality of the tear film was measured with the Optical Quality Analysis System (OQAS) using the mean objective scatter index (mean OSI), standard deviation of objective scatter index (SD-OSI) and modulation transfer function cut-off (MTF cut-off). After baseline examinations, one drop of artificial tears (ATs, carboxymethylcellulose ophthalmic solution, 0.5%) was instilled in both eyes, and optical quality parameters were measured again at 5 and 30 min following application of ATs. RESULTS: At baseline, the mean OSI was higher in the DED group (0.95 ± 0.54) than in controls (0.54 ± 0.23, P < 0.001). The SD-OSI was also significantly increased in DED patients (0.44 ± 0.71) compared to control subjects (0.12 ± 0.06, P = 0.003). Five minutes after AT instillation, mean OSI and SD-OSI decreased significantly in severe DED patients (P = 0.044; P = 0.018), remained unchanged in mild DED patients, and increased in the control group (P = 0.019; P < 0.001). Thirty minutes after AT instillation, no significant difference in optical quality parameters was observed among the three groups. CONCLUSION: The effect of ATs on optical quality in patients with DED may differ according to the severity of the disease. Measurement of optical quality might be a promising tool to evaluate the effects of various ATs and possibly individualize treatment in DED patients.

A deep-learning system predicts glaucoma incidence and progression using retinal photographs.

BackgroundDeep learning has been widely used for glaucoma diagnosis. However, there is no clinically validated algorithm for glaucoma incidence and progression prediction. This study aims to develop a clinically feasible deep-learning system for predicting and stratifying the risk of glaucoma onset and progression based on color fundus photographs (CFPs), with clinical validation of performance in external population cohorts.MethodsWe established data sets of CFPs and visual fields collected from longitudinal cohorts. The mean follow-up duration was 3 to 5 years across the data sets. Artificial intelligence (AI) models were developed to predict future glaucoma incidence and progression based on the CFPs of 17,497 eyes in 9346 patients. The area under the receiver operating characteristic (AUROC) curve, sensitivity, and specificity of the AI models were calculated with reference to the labels provided by experienced ophthalmologists. Incidence and progression of glaucoma were determined based on longitudinal CFP images or visual fields, respectively.ResultsThe AI model to predict glaucoma incidence achieved an AUROC of 0.90 (0.81-0.99) in the validation set and demonstrated good generalizability, with AUROCs of 0.89 (0.83-0.95) and 0.88 (0.79-0.97) in external test sets 1 and 2, respectively. The AI model to predict glaucoma progression achieved an AUROC of 0.91 (0.88-0.94) in the validation set, and also demonstrated outstanding predictive performance with AUROCs of 0.87 (0.81-0.92) and 0.88 (0.83-0.94) in external test sets 1 and 2, respectively.ConclusionOur study demonstrates the feasibility of deep-learning algorithms in the early detection and prediction of glaucoma progression.FUNDINGNational Natural Science Foundation of China (NSFC); the High-level Hospital Construction Project, Zhongshan Ophthalmic Center, Sun Yat-sen University; the Science and Technology Program of Guangzhou, China (2021), the Science and Technology Development Fund (FDCT) of Macau, and FDCT-NSFC.

EyeHealer: A large-scale anterior eye segment dataset with eye structure and lesion annotations.

Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide, including diseases associated with corneal pathologies, anterior chamber abnormalities (e.g. blood or inflammation), and lens diseases. The construction of an automatic tool for segmentation of anterior segment eye lesions would greatly improve the efficiency of clinical care. With research on artificial intelligence progressing in recent years, deep learning models have shown their superiority in image classification and segmentation. The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise; however, such data are relatively scarce in the domain of medicine. Herein, the authors developed a new medical image annotation system, called EyeHealer. It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level. Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation. The results showed that semantic segmentation models outperformed medical segmentation models. This paper describes the establishment of the system for automated classification and segmentation tasks. The dataset will be made publicly available to encourage future research in this area.

Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images.

Regular screening for the early detection of common chronic diseases might benefit from the use of deep-learning approaches, particularly in resource-poor or remote settings. Here we show that deep-learning models can be used to identify chronic kidney disease and type 2 diabetes solely from fundus images or in combination with clinical metadata (age, sex, height, weight, body-mass index and blood pressure) with areas under the receiver operating characteristic curve of 0.85-0.93. The models were trained and validated with a total of 115,344 retinal fundus photographs from 57,672 patients and can also be used to predict estimated glomerulal filtration rates and blood-glucose levels, with mean absolute errors of 11.1-13.4 ml min-1 per 1.73 m2 and 0.65-1.1 mmol l-1, and to stratify patients according to disease-progression risk. We evaluated the generalizability of the models for the identification of chronic kidney disease and type 2 diabetes with population-based external validation cohorts and via a prospective study with fundus images captured with smartphones, and assessed the feasibility of predicting disease progression in a longitudinal cohort.

Spontaneous Eye Blink Patterns in Dry Eye: Clinical Correlations.

Purpose: To evaluate spontaneous eye blink patterns and their correlations with clinical tests in dry eye disease (DED). Methods: Twenty-five DED patients and 25 healthy subjects were included in this prospective case-controlled study. Clinical evaluations included the Ocular Surface Disease Index (OSDI), lipid layer thickness (LLT), spontaneous eye blink pattern analysis, fluorescein tear film break-up time (FBUT), and so on. Eye blinks were recorded for 20 seconds with a high-speed camera. Eye blink patterns were divided into the following five phases: the eyelid closing phase (ECP), eyelid closed phase (CDP), early opening phase (EOP), late opening phase (LOP), and interblink intervals (IBI). The correlations between blink parameters and clinical tests were analyzed. Results: Compared with the control group, mean ECP, CDP, and EOP were significantly longer in DED patients (P < 0.001, P = 0.029, and P < 0.001, respectively). DED patients also had significantly shorter LOP and blink intervals (both P < 0.001) and more partial blinks as compared with control subjects (P = 0.001). FBUT was negatively correlated with ECP (r = -0.618, P=0.001) and the number of partial blinks (r = -0.413, P = 0.040). There was a positive correlation between OSDI and the number of partial blinks (r = 0.446, P = 0.026). The LLT coefficient of variation (LLT-CV) also showed a positive correlation with ECP, CDP, and LOP (P = 0.001, P = 0.050, P = 0.049, respectively). Corneal and conjunctival staining was positively correlated with ECP, CDP, and the number of blinks (r = 0.449, P = 0.024; r = 0.526, P = 0.007; r = 0.456, P = 0.022, respectively) and negatively correlated with IBI (r = -0.420, P = 0.037). Conclusions: Partial blinks, prolonged eyelid closed time and short blink intervals were the three main characteristics of DED patients' spontaneous blink patterns.