With the advancement of computational power, refinement of learning algorithms and architectures, and availability of big data, artificial intelligence (AI) technology, particularly with machine learning and deep learning, is paving the way for ‘intelligent’ healthcare systems. AI-related research in ophthalmology previously focused on the screening and diagnosis of posterior segment diseases, particularly diabetic retinopathy, age-related macular degeneration and glaucoma. There is now emerging evidence demonstrating the application of AI to the diagnosis and management of a variety of anterior segment conditions. In this review, we provide an overview of AI applications to the anterior segment addressing keratoconus, infectious keratitis, refractive surgery, corneal transplant, adult and paediatric cataracts, angle-closure glaucoma and iris tumour, and highlight important clinical considerations for adoption of AI technologies, potential integration with telemedicine and future directions.

PurposeThe COVID-19 pandemic has drastically disrupted global healthcare systems. With the higher demand for healthcare and misinformation related to COVID-19, there is a need to explore alternative models to improve communication. Artificial Intelligence (AI) and Natural Language Processing (NLP) have emerged as promising solutions to improve healthcare delivery. Chatbots could fill a pivotal role in the dissemination and easy accessibility of accurate information in a pandemic. In this study, we developed a multi-lingual NLP-based AI chatbot, DR-COVID, which responds accurately to open-ended, COVID-19 related questions. This was used to facilitate pandemic education and healthcare delivery.MethodsFirst, we developed DR-COVID with an ensemble NLP model on the Telegram platform (https://t.me/drcovid_nlp_chatbot). Second, we evaluated various performance metrics. Third, we evaluated multi-lingual text-to-text translation to Chinese, Malay, Tamil, Filipino, Thai, Japanese, French, Spanish, and Portuguese. We utilized 2,728 training questions and 821 test questions in English. Primary outcome measurements were (A) overall and top 3 accuracies; (B) Area Under the Curve (AUC), precision, recall, and F1 score. Overall accuracy referred to a correct response for the top answer, whereas top 3 accuracy referred to an appropriate response for any one answer amongst the top 3 answers. AUC and its relevant matrices were obtained from the Receiver Operation Characteristics (ROC) curve. Secondary outcomes were (A) multi-lingual accuracy; (B) comparison to enterprise-grade chatbot systems. The sharing of training and testing datasets on an open-source platform will also contribute to existing data.ResultsOur NLP model, utilizing the ensemble architecture, achieved overall and top 3 accuracies of 0.838 [95% confidence interval (CI): 0.826–0.851] and 0.922 [95% CI: 0.913–0.932] respectively. For overall and top 3 results, AUC scores of 0.917 [95% CI: 0.911–0.925] and 0.960 [95% CI: 0.955–0.964] were achieved respectively. We achieved multi-linguicism with nine non-English languages, with Portuguese performing the best overall at 0.900. Lastly, DR-COVID generated answers more accurately and quickly than other chatbots, within 1.12–2.15 s across three devices tested.ConclusionDR-COVID is a clinically effective NLP-based conversational AI chatbot, and a promising solution for healthcare delivery in the pandemic era.

PURPOSE: To compare long-term corneal nerve status following small incision lenticule extraction (SMILE) versus laser in situ keratomileusis (LASIK). METHODS: Twenty-four patients were randomized to receive SMILE in one eye and LASIK in the other eye. In vivo confocal microscopy examination and dry eye assessments were performed at a mean of 4.1 years postoperatively. The patients were further divided into two groups based on the mean assessment time: 2.7 years postoperatively (2.7 years group) and 5.5 years postoperatively (5.5 years group). Another 6 age-matched normal patients were recruited. RESULTS: At 4.1 years, LASIK eyes had significantly less corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), corneal nerve fiber length (CNFL), and corneal total branch density and significantly more nerves with beading than SMILE eyes. The CNFD, CNBD, CNFL, and number of nerves with sprouting were significantly higher in the 5.5 years group than in the 2.7 years group, in both types of surgery, suggesting persistent nerve regeneration. The CNBD and CNFD in the 5.5 years group, regardless of surgical types, were significantly lower than those in the control group, indicating the nerve status had not recovered to normal ranges even at 5.5 years. High myopic treatment resulted in significantly reduced CNFD with LASIK but not with SMILE. There were no significant differences in the dry eye parameters between the two procedures at 4.1 years postoperatively. CONCLUSIONS: The impact on corneal nerves following refractive surgery is long-lasting. SMILE had better nerve preservation and regeneration than LASIK, but neither procedure had recovered nerve status to normal levels even at 5.5 years. [ J Refract Surg . 2020;36(10):653–660.]

Following refractive surgery, the cornea is denervated and re-innervated, hence a reproducible tool to objectively quantify this change is warranted. This study aimed to determine the repeatability and reproducibility of corneal nerve quantification between automated (ACCMetrics) and manual software (CCMetrics) following refractive surgery. A total of 1007 in vivo confocal microscopy images from 20 post-small incision lenticule extraction (SMILE) or post-laser-assisted in situ keratomileusis (LASIK) patients were evaluated by two independent observers using CCMetrics for corneal nerve fibre density (CNFD), corneal nerve branch density (CNBD), and corneal nerve fibre length (CNFL). Intra-observer and inter-observer reproducibility and repeatability, as well as agreement and correlation between the measurements obtained by ACCMetrics and CCMetrics, were assessed. We found that CNFL demonstrated the best intra- and inter-observer agreement followed by CNFD (intra-class correlation coefficient (ICC) = 0.799 and 0.740, respectively for CNFL; 0.757 and 0.728 for CNFD). CNBD demonstrated poorest intra- and inter-observer ICC. There was an underestimation in ACCMetrics measurements compared to CCMetrics measurements, although the differences were not significant. Our data suggested that both automated and manual methods can be used as reliable tools for the evaluation of corneal nerve status following refractive surgery. However, the measurements obtained with different methods are not interchangeable.

No abstract