Incremental drops in heart function are treatable with medication but can be hard to spot.
According to the study authors, the findings add to evidence that such technology could help to reliably address diagnostic and treatment disparities for lower-income populations with limited access to dermatologists.
Researchers have made sustained progress in artificial intelligence (AI) for use in medicine. AI is particularly promising in radiology, where waiting for technicians to process medical images can delay patient treatment.
The study, published in the journal Clinical Infectious Diseases, outlines the results of a randomized controlled trial led by Oregon Health & Science University in seven rural counties in Oregon.
The findings, published in Nature Human Behaviour, demonstrate that large language models (LLMs) trained on vast datasets of text can distil patterns from scientific literature, enabling them to forecast scientific outcomes with superhuman accuracy.