A team of researchers from the University of Nottingham have trained a computer algorithm to predict if a patient will have a heart attack more accurately than doctors.

Typically doctors use guidelines similar to the American Heart Association (AHA) to assess patients and make a prediction based on their age, sex, race, total cholesterol, HDL cholesterol, systolic blood pressure, blood pressure lowering medication use, diabetes status, and smoking status.

However, this doesn’t take into account many medications a patient might be on, or other disease and lifestyle factors.

Epidemiologist at the University of Nottingham, Dr Stephen Weng, told Science magazine that using computer algorithms allows researchers to explore counterintuitive associations in diagnosis. For example, he says a lot of body fat could protect against heart disease in some cases.

In the study the researchers compared the use of AHA guidelines with four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, and neural networks) and used the algorithms to analyse data from nearly 400,000 electronic medical records (EMRs).

First, the artificial intelligent algorithms were fed complete data from around 300,000 patients to look for patterns and create ‘rules’.

The remaining records were then given to the algorithms. However, researchers held back information on whether the patients ended up having heart trouble in the next decade.

The results showed the algorithms correctly predicted risk 7.6% more often than doctors, with 1.6% less false positives. The researchers say this means 355 patients could have been told earlier they were at risk of a heart attack or stroke.

While the algorithm identified several risk factors that are not included in the AHA guidelines such as severe mental illness and taking oral corticosteroids, it doesn’t include information on if the patient had diabetes, which is on the AHA list.

In future, Dr Weng says he hopes to include other lifestyle and genetic factors in computer algorithms to further improve their accuracy.

For more information contact news@eHealthNews.co.za, like us on Facebook or tweet us @eHealthNewsZA.