DeepMind was founded in London in 2010 with the hope it could bring artificial intelligence (AI) technology to the medical field in a meaningful way. The idea was that AI could be utilized to enhance and improve diagnosis, treatment and ultimately patient care. In their latest research, Deep Mind unveiled a technology that it believes holds the potential to give doctors a 48-hour head start in treating acute kidney injury (AKI).
Acute kidney injury is a condition where a patient’s kidneys suddenly stop working properly. The condition is associated with over 100,000 people in the UK every year, or up to one-in-five hospitalized patients. It’s believed up to 30 percent of cases could be preventable if early intervention were possible.
In an effort to provide early intervention, Deep Mind worked with the US Department of Veteran Affairs (VA). In a statement released to Parentology, Dr. Dominic King, Health Lead at DeepMind said, “Working with the VA, the DeepMind team applied AI technology to a comprehensive de-identified electronic health record dataset collected from a network of over a hundred VA sites. The research shows that the AI could accurately predict AKI in patients up to 48 hours earlier than it is currently diagnosed.”
Part of the study’s success is attributed to Streams, DeepMind’s mobile medical assistant. The app-based technology, which has been in use at the Royal Free London NHS Foundation Trust since early 2017, allows instant communication between clinical teams. So, when a patient’s vitals slip, or a blood test result is available, the information is shared immediately through Streams. This not only saves physicians time throughout their day, but it could also be the difference between life and death for some patients.

Using streams, physicians were able to diagnose urgent cases within 15 minutes or less. In the case of a condition like AKI, this makes an incredible difference in the course of treatment and, ultimately, patient prognosis. Allowing medical teams to communicate more fluidly and immediately is beneficial both for patient care and hospital efficiency.
The hope is this technology will translate to other disease states. While the study focused specifically on the use of AI to diagnose AKI, King feels the results have far-reaching benefits, “Getting the right information about the right patient at the right time is a huge problem for healthcare systems across the globe.”
DeepMind hopes to build upon the successful AI identification of AKI combined with its Streams technology to provide more efficient healthcare. According to King, “These results comprise the building blocks for our long-term vision of preventative healthcare, helping doctors to intervene in a proactive, rather than reactive, manner. “