Artificial intelligence ‘can tell when you will die with up to 90% accuracy’
It sounds like a chilling idea out of science fiction, but an algorithm which can predict whether patients will die in the next 12 months could actually ease people’s pain.
Stanford University researchers are testing the algorithm with two million patient records – with the goal of creating a more accurate forecast of when people need end-of-life treatment.
As it stands, doctors often provide overly optimistic estimates, meaning that while 80% of people would prefer to die at home, 60% die in hospital while receiving treatment, the Stanford researchers say.
Using the algorithm could mean that patients are released to hospices or to their own homes, rather than dying while being treated, according to IEEE Spectrum.
MOST POPULAR ON YAHOO UK TODAY
Woman, 20, raped and murdered by ‘obsessed’ uncle who padlocked her body in a freezer
Sweden distributes 4.7 million leaflets on how to prepare for war with Russia
Italian aristocrat riding illegal ‘fixie’ bicycle with no front brakes crushed to death by lorry
Selfie on Facebook helps convict woman who was WEARING the weapon she killed her friend with
Who is the porn star who claims she had sex with Donald Trump four months after Melania gave birth?
Standford PhD candidate Anand Avati, ‘The scale of data available allowed us to build an all-cause mortality prediction model, instead of being disease or demographic specific.’
Kenneth Jung, a research scientist at Stanford University says, ‘We think that keeping a doctor in the loop and thinking of this as ‘machine learning plus the doctor’ is the way to go as opposed to blindly doing medical interventions based on algorithms… that puts us on firmer ground both ethically and safety-wise.’
