A Study Validating the Estimation of Anterior Chamber Depth and Iridocorneal Angle with Portable and Non-Portable Slit-Lamp Microscopy.

This study assessed the anterior chamber depth (ACD) and iridocorneal angle using a portable smart eye camera (SEC) compared to the conventional slit-lamp microscope and anterior-segment optical coherence tomography (AS-OCT). This retrospective case-control study included 170 eyes from 85 Japanese patients. The correlation between the ACD evaluations conducted with the SEC and conventional slit-lamp was high (r = 0.814). The correlation between the Van-Herick Plus grade obtained using two devices was also high (r = 0.919). A high kappa value was observed for the Van-Herick Plus grading (Kappa = 0.757). A moderate correlation was observed between the ACD measured using AS-OCT and the slit-lamp image acquired with the conventional slit-lamp microscope and SEC (r = 0.609 and 0.641). A strong correlation was observed between the trabecular-iris angle (TIA) measured using AS-OCT and Van-Herick Plus grade obtained with the conventional slit-lamp microscope and SEC (r = 0.702 and 0.764). Strong correlations of ACD evaluation and high kappa value of the Van-Herick Plus grading indicated the adequate subjective assessment function of the SEC. Moderate correlations between the ACD objective measurement and evaluation and strong correlation between the TIA and Van-Herick Plus grade suggested the good objective assessment function of the SEC. The SEC demonstrated adequate performance for ACD evaluation and angle estimation.

Primary Angle Closure Observed During a House Visit: A Case Treated With Laser Iridotomy.

Laser iridotomy (LI) is an effective treatment for patients with pupillary block mechanisms. Here, we report a case of LI performed on a patient with primary angle closure (PAC) and elevated intraocular pressure (IOP), who was unsuitable for other treatments due to specific social circumstances. The patient, a 97-year-old female residing in a private nursing home, had a medical history notable only for mild dementia and was wheelchair-bound. She had not undergone ophthalmologic evaluation for over 50 years. The patient presented with intermittent tenderness and redness in the left eye. Therefore, an ophthalmologist visited the nursing home. Examination revealed visual acuity of 20/200 in the right eye and 20/100 in the left eye, IOP of 24 mmHg in the right eye and 26 mmHg in the left eye, no conjunctival hyperemia, shallow anterior chambers, and nuclear sclerosis grade 4 cataracts in both eyes. Fundus examination was challenging due to lens opacity, and both optic nerve papillae appeared pale. Given her history of episodic eye pain and hyperemia, PAC was diagnosed. Treatment options, including eye drops and cataract surgery, were discussed. However, the patient opted for LI due to her advanced age and inability to attend frequent follow-up visits. LI was successfully performed on both eyes during her visit to the clinic. One week post-procedure, IOP decreased to 12 mmHg bilaterally, with no complications. This case demonstrates that LI can be a viable option for managing PAC and high IOP in patients who are not candidates for surgery or eye drops due to social constraints.

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

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.

AI-based diagnosis of nuclear cataract from slit-lamp videos.

In ophthalmology, the availability of many fundus photographs and optical coherence tomography images has spurred consideration of using artificial intelligence (AI) for diagnosing retinal and optic nerve disorders. However, AI application for diagnosing anterior segment eye conditions remains unfeasible due to limited standardized images and analysis models. We addressed this limitation by augmenting the quantity of standardized optical images using a video-recordable slit-lamp device. We then investigated whether our proposed machine learning (ML) AI algorithm could accurately diagnose cataracts from videos recorded with this device. We collected 206,574 cataract frames from 1812 cataract eye videos. Ophthalmologists graded the nuclear cataracts (NUCs) using the cataract grading scale of the World Health Organization. These gradings were used to train and validate an ML algorithm. A validation dataset was used to compare the NUC diagnosis and grading of AI and ophthalmologists. The results of individual cataract gradings were: NUC 0: area under the curve (AUC) = 0.967; NUC 1: AUC = 0.928; NUC 2: AUC = 0.923; and NUC 3: AUC = 0.949. Our ML-based cataract diagnostic model achieved performance comparable to a conventional device, presenting a promising and accurate auto diagnostic AI tool.

Artificial intelligence to estimate the tear film breakup time and diagnose dry eye disease.

The use of artificial intelligence (AI) in the diagnosis of dry eye disease (DED) remains limited due to the lack of standardized image formats and analysis models. To overcome these issues, we used the Smart Eye Camera (SEC), a video-recordable slit-lamp device, and collected videos of the anterior segment of the eye. This study aimed to evaluate the accuracy of the AI algorithm in estimating the tear film breakup time and apply this model for the diagnosis of DED according to the Asia Dry Eye Society (ADES) DED diagnostic criteria. Using the retrospectively corrected DED videos of 158 eyes from 79 patients, 22,172 frames were annotated by the DED specialist to label whether or not the frame had breakup. The AI algorithm was developed using the training dataset and machine learning. The DED criteria of the ADES was used to determine the diagnostic performance. The accuracy of tear film breakup time estimation was 0.789 (95% confidence interval (CI) 0.769-0.809), and the area under the receiver operating characteristic curve of this AI model was 0.877 (95% CI 0.861-0.893). The sensitivity and specificity of this AI model for the diagnosis of DED was 0.778 (95% CI 0.572-0.912) and 0.857 (95% CI 0.564-0.866), respectively. We successfully developed a novel AI-based diagnostic model for DED. Our diagnostic model has the potential to enable ophthalmology examination outside hospitals and clinics.

Clinical Observation of Allergic Conjunctival Diseases with Portable and Recordable Slit-Lamp Device.

BACKGROUND: The incidence of allergic conjunctival diseases (ACDs) is gradually increasing worldwide. Both ophthalmologists and non-ophthalmologists prescribe eye drops to treat ACDs; however, there are many cases which are treated without sufficient examination and diagnosis of the eyes. We have invented a portable, recordable, and smartphone-attachable slit-lamp device-Smart Eye Camera (SEC). The purpose of this study was to compare the diagnostic abilities of ACDs between the SEC and the conventional, non-portable slit-lamp microscope. METHODS: This prospective observational study included 32 eyes of 17 Japanese patients (mean age: 21.5 ± 14.8 years; range: 11-51 years; female: 5). The severity of 10 objective signs in the palpebral conjunctiva, bulbar conjunctiva, limbus, and cornea were scored on a grading scale of 0 to 4 (0 = normal; 1+ = mild; 2+ = moderate; 3+ = severe), respectively. First, the conventional slit-lamp microscope was used to examine the grade of the ACDs. Second, another ophthalmologist filmed the eyes using the SEC and two other ophthalmologists evaluated the grades on another day. The correlation and inter-rater reproducibility in total scores among the two devices were determined. RESULTS: Total scores of clinical signs, evaluated by the two approaches, correlated significantly (both eyes: r = 0.918 (95% CI: 0.839 to 0.959; p < 0.001)), with substantial inter-rater agreement (weighted κ value = 0.631 (95% CI: 0.601 to 0.661; p < 0.001)). CONCLUSIONS: The SEC is as reliable as the conventional non-portable slit-lamp microscope for assessing ACDs.

Smart Eye Camera: A Validation Study for Evaluating the Tear Film Breakup Time in Human Subjects.

Purpose: This study aimed to demonstrate the efficacy of a "Smart Eye Camera (SEC)" in comparison with the efficacy of the conventional slit-lamp microscope by evaluating their diagnostic functionality for dry eye disease (DED) in clinical cases. Methods: This retrospective study included 106 eyes from 53 adult Japanese patients who visited the Ophthalmology outpatient clinics in Keio University Hospital from June 2019 to March 2020. Tear film breakup time (TFBUT) and corneal fluorescence score (CFS) measurements for the diagnosis of DED were compared between the conventional slit-lamp microscope and SEC. Results: The objective findings of DED showed that there was a strong correlation between the conventional slit-lamp microscope and SEC with respect to TFBUT and CFS results (Spearman's r = 0.887, 95% confidence interval [CI] = 0.838-0.922, and r = 0.920, 95% CI = 0.884-0.945, respectively). The interobserver reliability between the conventional slit-lamp microscope and SEC showed a moderate agreement (weighted Kappa κ = 0.527, 95% CI = 0.517-0.537 and κ = 0.550, 95% CI = 0.539-0.561 for TFBUT and CFS, respectively). The diagnostic performance of the SEC for Asia Dry Eye Society diagnostic criteria showed a sensitivity of 0.957 (95% CI = 0.841-0.992), specificity of 0.900 (95% CI = 0.811-0.927), positive predictive value of 0.880 (95% CI = 0.774-0.912), and negative predictive value of 0.964 (95% CI = 0.869-0.993). Moreover, the area under the receiver operating characteristic curve was 0.928 (95% CI = 0.849-1.000). Conclusions: Compared with the conventional slit-lamp microscope, SEC has sufficient validity and reliability for diagnosing DED in the clinical setting. Translational Relevance: The SEC can portably evaluate TFBUT in both basic research and clinical care.

Evaluation of Nuclear Cataract with Smartphone-Attachable Slit-Lamp Device.

Background: Visual impairments and age-related eye diseases need to be detected and treated in a timely manner. However, this is often hampered by lack of appropriate medical equipment. We have invented a portable, recordable, and smartphone-attachable slit-lamp device, called the Smart Eye Camera (SEC). The aim of this study was to compare evaluating nuclear cataract (NUC) between the SEC and the conventional, non-portable slit-lamp microscope. Methods: A total of 128 eyes of 64 Japanese patients (mean age: 73.95 ± 9.28 years; range: 51‒92 years; female: 34) were enrolled. The NUC was classified into four grades (grade 0 to 3) based on three standard photographs of nuclear opacities according to the WHO classification by ophthalmologists. An ophthalmic healthcare assistant (non-ophthalmologist) filmed the eyes in video mode by the SEC and an ophthalmologist graded the NUC. Grade correlation and inter-rater reproducibility were determined. Results: NUC grading by the two approaches correlated significantly (both eyes: r = 0.871 [95%CI: 0.821 to 0.907; p < 0.001]). Inter-rater agreement was high (weighted κ = 0.807 [95%CI: 0.798 to 0.816; p < 0.001]). Conclusions: This study suggests that the SEC is as reliable as the conventional non-portable slit-lamp microscope for evaluating NUC.