Machine Learning Tackles Heart Disease... - Cholesterol Support

Cholesterol Support

9,642 members2,634 posts

Machine Learning Tackles Heart Disease Risk Assessment

Markl60 profile image
3 Replies

Machine learning is the process of taking lots of data about a subject, splitting it into around 75% and 25% and then training the computer on the 75% where it knows the result we want to predict eg did someone get heart disease, and then asking it to make predictions on the unseen 25%. We can then see how good it was at predicting on the fresh 25% but more importantly we can also get the computer model to tell us which variables were deemed the most important out of the variables it was using when 'learning' how to predict. This form of machine learning has been used to defeat world chess champions and makes predictions on a huge array of other automated predictions we know take for granted. OK so why the ML lesson ?, well it has been applied to predicting heart disease. Using thousands of patients who initially has no signs and then logging those that developed hear disease 10 years later, the machine learning alogorithm was let loose on the data. If performed better than conventional prediction method thrown at us by our doctors but of real interest was the top 10 risk factors. They used four different types of ML program and in none of them did LDL cholesterol appear in the top 10 risk factors. HDL appeared in two of them and Triglycerides in one of them but LDL appeared in NONE of them.

You can read the paper here

journals.plos.org/plosone/a...

Written by
Markl60 profile image
Markl60
To view profiles and participate in discussions please or .
Read more about...
3 Replies
sandybrown profile image
sandybrown

Thank you, very interesting, this is new. The question is when will this be available?

Markl60 profile image
Markl60 in reply to sandybrown

One thing you can do is focus on those to ranked risks, so when it comes to lipids that would be getting Triglycerides down and boosting HDL. The data adds more weight to the theory that total to HDL ratio is best or even HDL to Triglyceride ratio, in preference to obsessing over LDL

Markl60 profile image
Markl60 in reply to sandybrown

Let me also reiterate that all 4 machine learning varieties did better than the conventional risk predictions we are all currently plugging into when calculating our risk. The risk table in terms of individual factors is therefore worth taking note of.

Not what you're looking for?

You may also like...

The Best Measure of Cardiovascular Disease Risk

For the past 50 or so years, the medical community has psychologically conditioned their patients...

risk of heart disease .. medicine?

I was having a blood test for something else but turned out that my cholesterol levels were v high....

Heart Disease and Cholesterol by Country

Looking at the World Health Organisation data on average total cholesterol levels for men aged 25+...

Why Cholesterol does not cause Heart Disease

The latest informative post from Dr Kendrick, a must read for all What causes heart disease part...

Cholesterol Measures and the Risk of Heart Attack and Stroke

EDUCATIONAL POST - PLEASE SHARE Total cholesterol, on its' own, is of little value and is not...