Mobile Artificial Intelligence Technology for Detecting Macula Edema and Subretinal Fluid on OCT Scans: Initial Results from the DATUM alpha Study

Importance: Artificial Intelligence (AI) is necessary to address the large and growing deficit in retina and healthcare access globally. Mobile AI diagnostic platforms running in the Cloud may effectively and efficiently distribute such AI capability. Objective: To evaluate the feasibility of Cloud-based mobile artificial intelligence for detection of retinal disease. And to evaluate the accuracy of a particular such system for detection of subretinal fluid (SRF) and macula edema (ME) on OCT scans. Design: A multicenter retrospective image analysis was conducted in which board-certified ophthalmologists with fellowship training in retina evaluated OCT images of the macula. They noted the presence or absence of macula edema or subretinal fluid, then compared their assessment to that obtained from Fluid Intelligence, a mobile AI app that detects SRF and ME on OCT scans. Setting: Clinic setting with PACS access to OCT images of patients with or without retinal fluid. Participants: Board-certified ophthalmologists with fellowship training in retina retrospectively selected retinal OCT images in a consecutive fashion. Effort was made by each center to balance the number of scans with retinal fluid and scans without. Exclusion criteria included poor quality scans, ambiguous or overly subtle features, macula holes, retinoschisis, and dense epiretinal membranes. Main outcome and Measures: Accuracy in the form of sensitivity and specificity of the AI mobile app compared against assessments of board-certified retina specialists.