DeepMind's AI can predict AKI up to two days before it happens, according to new research

The study was published today in Nature. The DeepMind Health mobile app Streams uses digital tools to help identify patients at risk of preventable harm, currently from acute kidney injury (AKI) and sepsis.

The Streams technology compares a patient’s results with an analysis of about 700,000 historical medical records, which have been formatted to preserve anonymity. This reveals a patient’s risk factors of AKI and predicts its onset before patient deterioration. Currently, more than 26 clinicians are using Streams at the Royal Free Hospital in London, allowing them to detect an average of 11 patients daily who are at risk of AKI, most in fewer than 15 minutes rather than the multiple hours the process usually requires.