Alphabet’s artificial-intelligence subsidiary DeepMind is partnering with the US Department of Veterans Affairs to try to predict when a patient is about to take a turn for the worse, even before any outward signs of getting sick.

Life or death: Roughly 11 percent of all in-hospital deaths occur because someone misses or fails to act properly on warnings signs that a patient’s condition is declining.

How it will work: The project will analyze patterns from 700,000 anonymized medical records to see if machine learning can identify which patients will get worse during a hospital stay and correctly predict the decline.

Practical applications: The VA and DeepMind say one possible use for the technology is spotting kidney failure or damage early on. Kidney injuries commonly occur after routine procedures and operations, like a hip replacement, and often come on suddenly with no obvious warning signs. These injuries can be life-threatening, so DeepMind wants to find ways to detect them earlier in hopes of saving patients.