Google's AI anticipates 90% of kidney failures up to 48 hours prior to symptoms, study shows

Mackenzie Garrity - Print  | 

Google's DeepMind created an algorithm that correctly predicted more than 90 percent of acute kidney injuries that would require dialysis up to 48 hours before symptoms are recognized, according to CNBC.

A study on the artificial intelligence solution was published July 31 in Nature.

"We've been really excited for the potential of using AI to support clinicians moving care from reactive to proactive and preventative," said Dominic King, DeepMind's co-founder and clinical lead, to CNBC.

Researchers analyzed data from 100 Veteran Affairs hospitals, reviewing information on hundreds of patients.

Along with predicting acute kidney disease early, DeepMind is developing a strategy to implement alerts in emergency situations so physicians can react promptly. DeepMind is also still working to create a regulatory framework for transitioning predictive solutions to healthcare, Mr. King said.

Google acquired DeepMind in 2014 for $500 million, CNBC reports. The goal was to expand Google's presence in AI and machine learning. In the near future, DeepMind's health projects will be combined into Google Health, CNBC reports.

More articles on artificial intelligence:
UnityPoint Health invests $1M in AI for lung analysis
Cincinnati Children's AI system reduces patient screening time by 34%
Children's National Health to apply AI to study ICU transitions

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.