Algorithm similar to Netflix’s can predict death or heart attacks with 90 per cent accuracy, study finds
A MACHINE algorithm similar to those used by Netflix can predict death or heart attacks with 90 per cent accuracy, a study found.
LogitBoost is more accurate than humans after being programmed to use 85 variables to calculate risks, it claimed.
By analysing the variables in 950 patients with known six-year outcomes, the machine “learned” a number of individual risks, according to scientists in Finland.
It was then able to find patterns correlating the variables to heart attack and even death with more than 90 per cent accuracy.
Services like Netflix and Spotify systems all use algorithms to adapt to individual users, which is why you will be recommended music and films based on your listening and watching habits.
Study author Dr Luis Eduardo Juarez-Orozco, said these advances go beyond medicine.
Humans have a very hard time thinking further than three dimensions or four dimensions.
Dr Juarez-Orozco
He said: “These advances are far beyond what has been done in medicine, where we need to be cautious about how we evaluate risk and outcomes.
“We have the data but we are not using it to its full potential yet.”
Doctors use risk scores to make treatment decisions – but these scores are based on just a “handful” of variables in patients.
Through repetition and adjustment, machines use large amounts of data to identify complex patterns not evident to humans.
most read in health news
Dr Juarez-Orozco said: “Humans have a very hard time thinking further than three dimensions or four dimensions.
“The moment we jump into the fifth dimension we’re lost.
“Our study shows that very high dimensional patterns are more useful than single dimensional patterns to predict outcomes in individuals and for that we need machine learning.”
- GOT a story? Ring The Sun on 0207 782 4104 or WHATSAPP on 07423720250 or email exclusive@the-sun.co.uk.