Two NHS hospital trusts in London are piloting an AI system called Aire-DM to identify patients at risk for type 2 diabetes up to a decade before diagnosis. The AI analyzes ECG data for subtle signs of risk. Early results indicate a detection accuracy of around 70%, with enhanced predictions when additional patient factors are included. Clinical trials are set for 2025, aiming to potentially implement the technology across NHS services, which could transform diabetes risk assessment and management.