Machine learning algorithm is able to predict cardiac arrest 4 hours in advance and is accurate 66% of the time

[New Scientist] The researchers trained a machine-learning algorithm on data from 133,000 patients who visited the NorthShore University HealthSystem, a partnership of four Chicago hospitals, between 2006 and 2011. Doctors called a Code Blue 815 times. By looking at 72 parameters in patients’ medical history including vital signs, age, blood glucose and platelet counts, the system was able to tell, sometimes from data from 4 hours before an event, whether a patient would have gone into arrest. It guessed correctly about two-thirds of the time, while a scorecard flagged just 30 per cent of events.

The algorithm still needs work – it reports a false positive 20 per cent of the time, says Somanchi. To improve its performance, his team is planning to train the system with data from other hospitals.

The system could be combined with wearable sensors to monitor blood glucose and platelet counts in real time.

If you liked this article, please give it a quick review on ycombinator or StumbleUpon. Thanks