AI beats doctors at predicting heart disease deaths

September 4, 2018, The Francis Crick Institute
heart
Human heart. Credit: copyright American Heart Association

A model developed using artificial intelligence (AI) is better at predicting risk of death in patients with heart disease than models designed by medical experts, a new study from the Francis Crick Institute shows.

The study, published in PLOS One, adds to the growing evidence that AI could revolutionise healthcare in the UK and beyond. So far, the emphasis has been on the potential of AI to help diagnose and treat various diseases, but these new findings suggest it could also help predict the likelihood of patients dying too.

"It won't be long before doctors are routinely using these sorts of tools in the clinic to make better diagnoses and prognoses, which can help them decide the best ways to care for their patients," says Crick scientist Andrew Steele, first author of the paper.

"Doctors already use computer-based tools to work out whether a patient is at risk of , and machine-learning will allow more accurate models to be developed for a wider range of conditions."

Data-driven model

The model was designed using the electronic health data of over 80,000 patients, collected as part of routine care, and available for researchers on the CALIBER platform.

Scientists at the Crick, working collaboratively with colleagues at the Farr Institute of Health Informatics Research and University College London Hospitals NHS Foundation Trust, wanted to see if they could create a model for coronary artery disease—the leading cause of death in the UK—that outperforms experts using self-taught machine learning techniques.

Coronary artery disease develops when the major blood vessels that supply the with blood, oxygen and nutrients become damaged, or narrowed by fatty deposits. Eventually restricted blood flow to the heart can lead to chest pain and shortness of breath, while a complete blockage can cause a heart attack.

An expert-constructed prognostic model for which this work was compared against made predictions based on 27 variables chosen by , such as age, gender and chest pains. By contrast, the Crick team got their AI algorithms to train themselves, searching for patterns and picking the most relevant variables from a set of 600.

Outperforming experts

Not only did the new data-driven model beat expert-designed models at predicting patient mortality, but it also identified new variables that doctors hadn't thought of.

"Along with factors like age and whether or not a patient smoked, our models pulled out a home visit from their GP as a good predictor of patient mortality," says Andrew. "Home visits are not something a cardiologist might say is important in the biology of heart , but perhaps a good indication that the patient is too unwell to make it to the doctor themselves, and a useful variable to help the model make accurate predictions."

This study was a proof-of-principle to compare expert-designed models to machine learning approaches, but a similar model could be implemented in the clinic in the not too distant future.

"Machine learning is hugely powerful tool in medicine and has the ability to revolutionise how we deliver care to over the next few years," says Andrew.

Explore further: Model improves prediction of mortality risk in ICU patients

More information: Andrew J. Steele et al, Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease, PLOS ONE (2018). DOI: 10.1371/journal.pone.0202344

Related Stories

Model improves prediction of mortality risk in ICU patients

August 30, 2018
In intensive care units, where patients come in with a wide range of health conditions, triaging relies heavily on clinical judgment. ICU staff run numerous physiological tests, such as bloodwork and checking vital signs, ...

World-first test could predict risk of heart attack in coronary artery disease patients

June 14, 2018
Researchers have developed a world-first blood test which improves the prediction of the long-term risk of heart attack or death in those with severe coronary artery disease.

New risk score predicts heart disease in patients with chest pain

June 12, 2012
A new risk prediction tool can identify patients at high risk of coronary artery disease who might need further diagnostic work, says a study published on BMJ today. The tool is more accurate than existing models and could ...

New blood test reveals risk of coronary artery disease

September 1, 2017
A study led by researchers at Uppsala University, which included more than 13,000 patients, has resulted in a new tool that will facilitate the treatment of patients with stable coronary artery disease.

I have had a heart attack. Do I need open heart surgery or a stent?

August 25, 2018
New advice on the choice between open heart surgery and inserting a stent via a catheter after a heart attack is launched today. The European Society of Cardiology (ESC) and European Association for Cardio-Thoracic Surgery ...

Machine learning techniques show promise for supporting medical decisions

February 28, 2018
Several studies being presented at the American College of Cardiology's 67th Annual Scientific Session demonstrate how the computer science technique known as machine learning can be used to accurately predict clinical outcomes ...

Recommended for you

New treatment significantly reduces cardiovascular events when combined with statins

November 12, 2018
Statins are the most commonly used treatment for cardiovascular disease. Despite reducing certain risk factors, if triglyceride levels remain high with use of statins, there is still a significant risk for heart attack, stroke ...

Kawasaki disease: One disease, multiple triggers

November 12, 2018
Researchers at University of California San Diego School of Medicine, Scripps Institution of Oceanography, and international collaborators have evidence that Kawasaki Disease (KD) does not have a single cause. By studying ...

Study: How vitamin D and fish oil affect risk of heart attack, stroke and cancer

November 12, 2018
For years, it's remained an open question: What effects do dietary supplements such as high doses of vitamin D or omega-3 fatty acids derived from fish oil have on the risk of diseases such as heart attack, stroke and cancer? ...

Diabetes drug might also ease heart failure risks

November 12, 2018
(HealthDay)—The diabetes drug Farxiga might do double-duty for patients, helping to ward off another killer, heart failure, new research shows.

Updated cholesterol guidelines offer more personalized risk assessment, additional treatment options

November 12, 2018
More personalized risk assessments and new cholesterol-lowering drug options for people at the highest risk for cardiovascular disease (CVD) are among the key recommendations in the 2018 cholesterol guidelines from the American ...

Heart meeting features fish oil, vitamin D, cholesterol news

November 11, 2018
Fish oil, vitamin D, novel drugs, new cholesterol guidelines: News from an American Heart Association conference over the weekend reveals a lot about what works and what does not for preventing heart attacks and other problems.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.