The VA wants to use machine learning to detect patient deterioration
The Department of Veterans Affairs wants to explore how machine learning can help predict the onset of patient deterioration.
The department announced Wednesday a partnership with DeepMind to conduct medical research on deterioration, which generally happens when, despite providing care, medical staff fail to notice that a patient’s condition is worsening.
DeepMind — a London-based Alphabet subsidiary that explores wide-ranging applications of artificial intelligence — and the VA plan to use AI to analyze about 700,000 anonymized health records and develop machine learning algorithms that “will accurately identify risk factors for patient deterioration and predict its onset.”
The VA says the partnership will initially focus on detecting early signs of risk. It says that acute kidney injury, for example, can lead to dialysis or death but can be prevented if detected early.
“Medicine is more than treating patients’ problems,” said VA Secretary David Shulkin in a press release. “Clinicians need to be able to identify risks to help prevent disease. 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 say that developing machine learning techniques to detect patient deterioration will lead to more proper care for patients. The VA says patient deterioration is the cause of 11 percent of in-hospital patient deaths globally.
DeepMind has in the past worked with the U.K.’s National Health Service on similar projects, like using machine learning to detect early warning signs of blindness.
“This project has great potential intelligently to detect and prevent deterioration before patients show serious signs of illness,” DeepMind co-founder Mustafa Suleyman said in the release. “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.”
