You are here: Home » News-ANI » Health
Business Standard

Machine learning could predict death or heart attack with over 90% accuracy: Study

ANI 

A study claimed that machine learning, modern bedrock of artificial intelligence, could predict death or with more than 90 per cent accuracy.

The study was presented at The International Conference on Nuclear Cardiology and CT (ICNC) 2019.

is used every day. Google's search engine, face recognition on smartphones, self-driving cars, and -- all use algorithms to adapt to the individual user.

By repeatedly analysing 85 variables in 950 patients with known six-year outcomes, an algorithm 'learned' how data interacts. It then identified patterns correlating the variables to death and with more than 90 per cent accuracy.

Study author, Dr of the Turku PET Centre, 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 and often have modest accuracy in individual patients.

Through repetition and adjustment, can exploit large amounts of data and identify complex patterns that may not be evident to humans.

Dr Juarez-Orozco explained, "Humans have a very hard time thinking further than three dimensions (a cube) or four dimensions (a cube through time). The moment we jump into the fifth dimension we are 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 who underwent the center's to look for coronary artery

A coronary computed angiography (CCTA) scan yielded 58 pieces of data on the presence of coronary plaque, vessel narrowing, and calcification. Those with scans suggestive of underwent a positron emission (PET) scan which produced 17 variables on blood flow. Ten clinical variables were obtained from medical records including sex, age, smoking, and

During an average six-year follow-up there were 24 and 49 deaths from any cause. The 85 variables were entered into a machine learning algorithm called 'LogitBoost', which analysed them over and over again until it found the best structure to predict who had a or died.

"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," said Dr Juarez-Orozco.

"Doctors already collect a lot of information about patients. 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," added Dr Juarez-Orozco.

(This story has not been edited by Business Standard staff and is auto-generated from a syndicated feed.)

First Published: Sun, May 12 2019. 19:55 IST
RECOMMENDED FOR YOU
RECOMMENDED FOR YOU