he prospect of improved clinical outcomes and more efficient health systems has fueled a rapid rise in the development and evaluation of AI systems over the last decade. Because most AI systems within healthcare are complex interventions designed as clinical decision support systems, rather than autonomous agents, the interactions among the AI systems, their users and the implementation environments are defining components of the AI interventions' overall potential effectiveness. Therefore, bringing AI systems from mathematical performance to clinical utility needs an adapted, stepwise implementation and evaluation pathway, addressing the complexity of this collaboration between two independent forms of intelligence, beyond measures of effectiveness alone 1 . Despite indications that some AI-based algorithms now match the accuracy of human experts within preclinical in silico studies 2 , there

No abstract

Literature review for indocyanine green angiography and evaluate the role of indocyanine green angiogram (ICGA) in patients with posterior uveitis seen at a tertiary referral eye care centre. Detailed review of the literature on ICGA was performed. Retrospective review of medical records of patients with posterior uveitis and dual fundus and ICGA was done after institutional board approval. Eighteen patients (26 eyes) had serpiginous choroiditis out of which 12 patients had active choroiditis and six patients had healed choroiditis, six patients (12 eyes) had ampiginous choroiditis, six patients (12 eyes) had acute multifocal posterior placoid pigment epitheliopathy, eight patients (10 eyes) had multifocal choroiditis, four patients (eight eyes) had presumed ocular histoplasmosis syndrome, four patients (eight eyes) had presumed tuberculous choroiditis, two patients (four eyes) had multiple evanescent white dot syndrome and two patients (four eyes) had Vogt Koyanagi Harada (VKH) syndrome. The most characteristic feature noted on ICGA was the presence of different patterns of hypofluorescent dark spots, which were present at different stages of the angiogram. ICGA provides the clinician with a powerful adjunctive tool in choroidal inflammatory disorders. It is not meant to replace already proven modalities such as the fluorescein angiography, but it can provide additional information that is useful in establishing a more definitive diagnosis in inflammatory chorioretinal diseases associated with multiple spots. It still needs to be determined if ICGA can prove to be a follow up parameter to evaluate disease progression.

No abstract

In the version of this article initially published, a list of the DECIDE-AI expert group members and their affiliations was omitted and has now been included in the HTML and PDF versions of the article.

Diabetes mellitus (DM) is a global pandemic that is one of the fastest growing chronic diseases and the top cause of blindness in the working population. The eye provides a direct visualization to the body's vasculature and systemic health, allowing it to be a minimally invasive tool to evaluate DM and its micro- and macrovascular complications, including diabetic retinopathy, corneal neuropathy, cardiovascular disease, chronic kidney disease and cerebrovascular disease. With the rapid rate of disease burden, there is an unmet public health need to identify these diseases at an early stage to implement timely management. Artificial intelligence (AI), in particular deep learning, has been widely explored for disease segmentation, classification, and prediction. Despite the advances in AI for optimizing the screening and management of DM, future work is warranted to address the issues such as interpretability, cost, and acceptance of AI systems by patients and healthcare workers.

No abstract