Scientists have developed an AI tool that is capable of diagnosing and predicting the risk of developing multiple health conditions, including heart failure. Named RETFound, this AI-powered tool can diagnose and predict the risk of developing a range of health conditions, from ocular diseases to heart failure and Parkinson's disease, all through the analysis of individuals' retinal images. According to the paper published in Nature.com, RETFound is trained using the innovative self-supervised learning method; it does not require the researchers to manually label each of the 1.6 million retinal images used for training. The method further made RETFound a more efficient and cost-effective way to develop AI tools for medical diagnosis. The AI-powered tool RETFound has already learned what a normal retina should look like from the unlabeled data. So using that data, it can analyse retinal scans to assess whether there are any abnormalities, which can then be used to diagnose diseases.