Using artificial intelligence to predict heart failure risk

Using machine learning to predict clinical outcomes in heart failure.

Dr Declan O’Regan and his colleagues at Imperial College London are using artificial intelligence (AI) to interpret heart scans and tests. They want to find out if AI can accurately predict what will happen to people with heart failure, so that they can receive the best treatment. Heart failure is when the heart is unable to pump blood around the body properly. Doctors need to know when people with heart failure are likely to get worse so they can provide the right treatment, but this is not always straightforward. Current measurements don’t accurately show how a person with heart failure’s condition will progress. Artificial intelligence can do many things faster and more accurately than humans. It could transform the way scans and other tests are used to make the best decisions about treatment. In this project, Dr O’Regan will use AI to interpret thousands of heart scans and build a detailed three-dimensional model of the heart, before ‘training’ the computer to recognise the earliest signs of heart failure. He will then be able to see how accurately the computer predicts the likely outcomes for people with dilated cardiomyopathy and pulmonary arterial hypertension - two serious conditions that can lead to heart failure. If this work can reveal a better way to predict how heart failure progresses, it could lay the foundations for introducing AI into heart treatment.