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

Effective drug delivery to heart with tannic acid

September 18, 2018
Typical methods of drug delivery to the heart require surgical procedures involving incisions in the chest wall and bones. To efficiently treat cardiovascular and related vascular diseases without surgery, a KAIST research ...

Daily low-dose aspirin found to have no effect on healthy life span in older people

September 16, 2018
In a large clinical trial to determine the risks and benefits of daily low-dose aspirin in healthy older adults without previous cardiovascular events, aspirin did not prolong healthy, independent living (life free of dementia ...

Financial incentives for cholesterol control may be cost-effective

September 14, 2018
A program that offered financial incentives to both patients and their physicians to control low-density lipoproteins (LDL) cholesterol could be a cost-effective intervention for patients at high risk of cardiovascular disease ...

Apple's smartwatch has a heart monitor now

September 13, 2018
There will soon be another way to monitor your heart—from your wrist.

3-D virtual simulation gets to the 'heart' of irregular heartbeats

September 12, 2018
In a proof of concept study, scientists at Johns Hopkins report they have successfully performed 3-D personalized virtual simulations of the heart to accurately identify where cardiac specialists should electrically destroy ...

Dairy consumption linked to lower rates of cardiovascular disease and mortality

September 12, 2018
Dairy consumption of around three servings per day is associated with lower rates of cardiovascular disease and mortality, compared to lower levels of consumption, according to a global observational study of over 130,000 ...

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.