Scroll Top

AI has learnt to predict heart attacks more accurately than doctors

article_heartattack

WHY THIS MATTERS IN BRIEF

  • Every year millions of people die from heart disease and this new system could save thousands, perhaps tens of thousands of extra lives


 

Every year an estimated 20 million people die from heart disease, but now, hot on the heels of an artificial intelligence (AI) system that can predict death, a team of researchers from the University of Nottingham, the same university that’s found a way to regrow teeth from stem cells, have developed a machine learning algorithm that can predict an individuals likelihood of having a heart attack, or a stroke, better than any doctor.

 

See also
Microsoft's VALL-E AI can clone your voice in just three seconds

 

Over the past few decades the American College of Cardiology and the American Heart Association (ACC-AHA) has developed a series of guidelines to help doctors evaluate a patient’s cardiovascular risk, based on eight factors that include age, cholesterol level and blood pressure. And average, this system correctly guesses a person’s risk of getting heart disease with an accuracy of 72.8 percent.

You might think that’s already good enough – but Stephen Weng and his team wanted to make it even better so they built four computer learning algorithms and fed them data from over 380,000 patients.

Firstly, the new system used 295,000 records to build its internal predictive models, and then it used the remaining 85,000 records to test and refine them, and the result? A 74.5 to 76.4 percent accuracy and 1.6 percent fewer false alarms. After all, you don’t want to be told you’re likely to have a heart attack if you aren’t – doctors aren’t beasts you know…

Translating all of that into normal language what this all means is that out of the 85,000 records it analysed the new model could have saved 355 lives, but interestingly the AI system identified a number of risk factors and predictors not covered in the existing guidelines, like severe mental illness and the consumption of oral corticosteroids.

 

See also
Scientists develop Matrix style technology capable of 'uploading knowledge' to your brain

 

“There’s a lot of interaction in biological systems,” said Weng, “that’s the reality of the human body. What computer science allows us to do is to explore those associations.”

So, as another AI moves in on human territory – and beats us, again – this time we should be thankful, but as surprising, and perhaps as shocking as this new announcement might be, don’t have a coronary. Chill, eat salad and watch the clouds pass by.

Related Posts

Leave a comment

FREE! DOWNLOAD THE 2024 EMERGING TECHNOLOGY AND TRENDS CODEXES!DOWNLOAD

Awesome! You're now subscribed.

Pin It on Pinterest

Share This