US’s VA and DeepMind to use AI to detect risks with hospital stay

26 February 2018 (Last Updated February 26th, 2018 17:12)

The US Department of Veterans Affairs (VA) has formed a medical research partnership with artificial intelligence (AI) research firm DeepMind to address the issues associated with patient deterioration during hospital care.

The US Department of Veterans Affairs (VA) has formed a medical research partnership with artificial intelligence (AI) research firm DeepMind to address the issues associated with patient deterioration during hospital care.

The firms will leverage AI to develop machine learning algorithms to identify risk factors related to patient deterioration, which is reportedly responsible for 11% of all in-hospital deaths.

To detect the risk factors, the firms plan to analyse patterns from approximately 700,000 historical, depersonalised medical records.

The newly developed AI algorithms are expected to aid in predicting the onset of patient deterioration.

VA Secretary David Shulkin said: “Clinicians need to be able to identify risks to help prevent disease.

“This project has great potential intelligently to detect and prevent deterioration before patients show serious signs of illness.”

“This collaboration is an opportunity to advance the quality of care for our nation’s veterans by predicting deterioration and applying interventions early.”

The VA and DeepMind will initially focus on improving the existing algorithms used for the detection of acute kidney injury (AKI), one of the most common conditions associated with patient deterioration.

At a later stage, the firms plan to extend the research to other signs of patient deterioration in order to ensure better care for more patients.

DeepMind co-founder Mustafa Suleyman said: “This project has great potential intelligently to detect and prevent deterioration before patients show serious signs of illness.

“Speed is vital when a patient is deteriorating: the sooner the right information reaches the right clinician, the sooner the patient can be given the right care.”