Friday, May 24, 2019

Mortality Algorithm Can Predict Heart Attack, Death With 90% Accuracy



 We need this badly and not just for folks actually experiencing chest pain. Many heart attacks give no real warning.  In fact the best advice i can give anyone in the right age group is to literally lie about chest pain in order to drum up testing.  You really need to know certain things to protect yourself.

Recall ninety percent of men aged 60 have chronic circulatory disease needing attention.  It is completely possible to locate blockages through imaging, particularly if they are long term and have calcification.  Confirmation will at least allow you to focus on suppressing inflammation by taking a small aspirin.

All men and women need to get out of our culture of denial because this disease profile can be a successfully managed allowing real life extension.  A proper medical work up at fifty or much earlier for family histories of early heart attacks should be mandatory and needs to determine real vulnerabilities.

Knowing leads to successful therapy that will carry you forward..


Mortality Algorithm Can Predict Heart Attack, Death With 90% Accuracy

 
Tue, 05/14/2019 - 23:45


 https://www.zerohedge.com/news/2019-05-14/mortality-algorithm-can-predict-heart-attack-and-death-90-accuracy

An algorithm which can predict whether a person will have a heart attack or die with 90% accuracy has been developed by researchers at Finland's Turku PET Centre.


Utilizing similar machine learning functions as those employed by Netflix and Spotify to personalize content, a team led by Dr. Luis Eduardo Juarez-Orozco programmed the LogitBoost algorithm to use 85 variables to calculate the risk to the health of 950 test subjects who were subject to a host of scans and tests prior to being treated via traditional methods.

After patients complained of chest pain, their data was collected and used to 'train' the algorithm, which 'learned' the risks over a six-year period, during which it achieved 90% success at predicting 24 heart attacks and 49 deaths from any cause.


"These advances are far beyond what has been done in medicine, where we need to be cautious about how we evaluate risk and outcomes," said Juarez-Orozco, adding "We have the data but we are not using it to its full potential yet."

Doctors typically use risk scores to make treatment decisions, according to the Daily Mail, however these scores utilize just a 'handful' of variables in patients.

"Humans have a very hard time thinking further than three dimensions or four dimensions," said Juarez-Orozco. "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. -Daily Mail

"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," added Juarez-Orozco. "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."

No comments: