Algorithm similar to the ones used by Netflix and Spotify to recommend content can predict who will Die or have a heart attack with 90% accuracy

Algorithm similar to the ones used by Netflix and Spotify to recommend content can predict who will DIE or have a heart attack with 90% accuracy


·        LogitBoost was trained using scans and outcomes of 950 previous patients 
·        Algorithm was then programmed to use 85 variables to calculate a patent's risk
·        Services like Netflix and Spotify use similar algorithms to personalise services 
·        After training it was able to correctly identify those likely to die or have a heart attack with 90 per cent accuracy  


Algorithms similar to those employed by Netflix and Spotify to customise services are now better than human doctors at spotting who will die or have a heart attack. 
Machine learning was used to train LogitBoost, which its developers say can predict death or heart attacks with 90 per cent accuracy.
It was programmed to use 85 variables to calculate the risk to the health of the 950 patients that it was fed scans and data from. 
Patients complaining of chest pain were subjected to a host of scans and tests before being treated by traditional methods. 
Their data was later used to train the algorithm. 
It 'learned' the risks and, during the six-year follow-up, had a 90 per cent success rate at predicting 24 heart attacks and 49 deaths from any cause. 
LogitBoost which was programmed to use 85 variables to calculate risks to a person's health who was complaining of chest pain. Patients had a coronary computed tomography angiography (CCTA) scan (pictured, stock scan) which gathered 58 of the data points 
Services like Netflix and Spotify systems all use algorithms in a similar way to adapt to individual users and offer a more personalised look.
Study author Dr Luis Eduardo Juarez-Orozco, of the Turku PET Centre, Finland, said these advances go beyond medicine.
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.
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.'
The study enrolled 950 patients with chest pain who underwent the centre's usual protocol to look for coronary artery disease.
A coronary computed tomography angiography (CCTA) scan gathered 58 pieces of data on potential risks of a heart attack.
These included the presence of coronary plaque, vessel narrowing, and calcification.
Those with scans suggestive of disease underwent a positron emission tomography (PET) scan which produced 17 variables on blood flow.
Ten clinical variables were obtained from medical records including sex, age, smoking and diabetes. 
The 85 variables were entered into LogitBoost, which analysed them repeatedly until it found the best structure to predict who had a heart attack or died.
Dr Juarez-Orozco said: 'The algorithm progressively learns from the data and after numerous rounds of analyses, it figures out the high dimensional patterns that should be used to efficiently identify patients who have the event - the result is a score of individual risk.
'Doctors already collect a lot of information about patients - for example, those with chest pain.
'We found that machine learning can integrate these data and accurately predict individual risk.
'This should allow us to personalise treatment and ultimately lead to better outcomes for patients.'
The study was presented at The International Conference on Nuclear Cardiology and Cardiac CT. 


Positron emission tomography (PET) scans are used to produce detailed three-dimensional images of the inside of the body.
The images can clearly show the part of the body being investigated, including any abnormal areas, and can highlight how well certain functions of the body are working.
PET scans are often combined with CT scans to produce even more detailed images. This is known as a PET-CT scan.
They may also occasionally be combined with an MRI scan (known as a PET-MRI scan).
PET scanners work by detecting the radiation given off by a substance injected into your arm called a radiotracer as it collects in different parts of your body.
In most PET scans a radiotracer called fluorodeoxyglucose (FDG) is used, which is similar to naturally occurring glucose (a type of sugar) so your body treats it in a similar way.
By analysing the areas where the radiotracer does and doesn't build up, it's possible to work out how well certain body functions are working and identify any abnormalities.
For example, a concentration of FDG in the body's tissues can help identify cancerous cells because cancer cells use glucose at a much faster rate than normal cells.


Popular posts from this blog

Report: World’s 1st remote brain surgery via 5G network performed in China

Facebook says hackers saw personal info of 14 million people

Too Much Power to the People? A Food Safety Site Tests the Limits