Scientists have identified five subtypes of heart failure that could help better predict patients’ risk of dying.
Heart failure occurs when the heart is unable to pump blood around the body properly, usually because it has become too weak or stiff.
More than 900,000 people in the UK are thought to be living with the condition but it is difficult to predict how the disease is likely to progress.
A team at UCL analysed data from more than 300,000 UK patients diagnosed between 1998 and 2018.
They used artificial intelligence tools to identify five new subtypes of heart failure, based on 87 factors including age, symptoms, underlying conditions, medications taken and test results.
The researchers calculated a patient’s risk of dying in the year after their diagnosis depending on which “cluster” they fell into. It varied from 11 percent for the “metabolic” subtype to 61 percent for “atrial fibrillation related”.
Patients who fell into the metabolic category tended to be overweight and had a low rate of cardiovascular disease (CVD), while those in the atrial fibrillation related group had a condition that causes an irregular heart rate, and valve disease.
Those who fell into the “early onset” cluster were younger and had a 20 percent risk of dying within 12 months. The “cardiometabolic” group had a 37 per cent risk and tended to be overweight, with a high rate of prescribed medications and CVD.
Finally, patients in the “late onset” category had a 46 percent risk and were generally older, female, not taking many medications, with a low rate of CVD.
Common symptoms of heart failure include breathlessness, tiredness, feeling lightheaded or fainting, and swollen ankles and legs.
There is usually no cure but treatments to slow the condition include lifestyle changes (healthy diet, exercise, quitting smoking etc), drugs, devices implanted in the chest to control heart rhythm, and surgery such as a bypass or heart transplant.
A more specific diagnosis may help clinicians make personalised decisions about their care, the researchers said.
Lead author Professor Amitava Banerjee, of UCL’s Institute of Health Informatics, said: “Currently, how the disease progresses is hard to predict for individual patients. Some people will be stable for many years, while others get worse quickly.
“Better distinctions between types of heart failure may also lead to more targeted treatments and may help us to think in a different way about potential therapies.
“In this new study, we identified five robust subtypes using multiple machine learning methods and multiple datasets.”
The team has developed an app that can be used by doctors to quickly determine which category a patient falls into, although further testing is needed before it could become part of routine care.
Prof Banerjee said: “The next step is to see if this way of classifying heart failure can make a practical difference to patients – whether it improves predictions of risk and the quality of information clinicians provide, and whether it changes patients’ treatment.
“We also need to know if it would be cost effective. The app we have designed needs to be evaluated in a clinical trial or further research, but could help in routine care.”
The findings were published in the journal Lancet Digital Health.
Source: | This article first appeared on Express.co.uk