STAT

DeepMind AI predicts acute loss of kidney function two days in advance, study shows

DeepMind's AI was able to predict 90% of acute kidney injury episodes that required dialysis, with a lead time of 48 hours.

One of the biggest challenges hospitals face is predicting when frail patients will decline into a life-threatening spiral. Subtle changes in health status get lost in a sea of data that is too vast for humans to effectively monitor.

In a paper published Wednesday in the journal Nature, researchers at DeepMind describe a possible solution: A machine learning system capable of crunching hundreds of thousands of data points

You’re reading a preview, subscribe to read more.

More from STAT

STAT1 min readIntelligence (AI) & Semantics
STAT+: Q&A: Defining Responsible AI In Health Care, With CHAI CEO Brian Anderson
CHAI CEO Anderson wants to build public trust in AI and empower patients and providers to have more informed conversations.
STAT2 min read
STAT+: Pharmalittle: We’re Reading About FDA Approval For Sarepta Drug, MSF Closing Access Campaign And More
After months of haggling, Vertex Pharmaceuticals and the National Health Service in England reached agreement over access to several cystic fibrosis treatments, capping an end to a controversial, long-running saga:
STAT2 min read
STAT+: Pharmalittle: We’re Reading About EMA Plans For GLP-1 Shortages, Walgreens Store Closings, And More
The European Medicines Agency and member countries announced several steps to address shortages of GLP-1 drugs.

Related Books & Audiobooks