Companies are already using artificial intelligence to play board games and recommend content, and now researchers want to use AI for something a bit more personal: predicting how long heart patients have to live.

In a paper recently published in the journal Radiology, researchers at the MRC London Institute of Medical Sciences used machine learning to predict the mortality rates of patients suffering from pulmonary hypertension, a rare and serious lung disorder that restricts the amount of oxygen going to the heart.

If left untreated, roughly one-third of patients suffering from PH die within five years. Because the disorder is worsens over time, it is important for doctors to accurately estimate a patient’s life expectancy to determine how aggressively they should treat the condition.

Using machine learning, the researchers trained an AI using over eight years of patient health data. They then used that AI to analyze data taken from MRI scans of 256 patients who had recently been diagnosed with PH. The AI monitored over 30,000 data points that moved during each heartbeat, allowing it to measure small changes that might be imperceptible to doctors.

After analyzing the data, the AI correctly predicted which patients would still be alive after one year with 80 percent accuracy. The same predictions made by doctors were only 60 percent accurate.

The researchers said that their experiment demonstrates that an AI can assist doctors in making an accurate, semi-automated analysis of medical scans, allowing patients to receive better treatment.

“The AI really allows you to tailor the individual treatment,” researcher Declan O’Regan told BBC News. “So it takes the results of dozens of different tests including imaging, to predict what’s going to happen to individual patients very accurately. So we can tailor getting absolutely the right intensive treatment to those who will benefit the most.”

The United Kingdom has become a testing ground for a number of medical applications for artificial intelligence. In November, for example, Alphabet Inc. announced that its DeepMind AI team had teamed with the U.K.’s National Health Service to improve patient care using AI. DeepMind also works with Moorfields Eye Hospital in London to use computer vision and deep learning to catch eye ailments early.

Photo credit: Força Aérea Brasileira – Página Oficial Centro cirúrgico do HFAB via photopin (license)