Researchers have developed a new way of assessing a person’s risk of heart failure or death, by using AI during chest scans to measure the size of their pectoral muscle.
The study, funded by us and published in the Journal of the American College of Cardiology, outlines how this tool can be used to produce a figure that is more useful for predicting risk than current standards like BMI.
The figure, called the sarcopenic obesity index, is calculated using a person’s weight and the size of their pectoral muscle. This means it considers not only their size but also sarcopenia – loss of their overall muscle mass and strength – which is a key indicator of their health.
Researchers tracked patients’ health for an average of four years after their index score was measured. They showed that, for people with a score in the top 15 per cent, there was at least a 51 per cent higher risk of a cardiovascular-related death, and a 37 per cent higher risk of any death, compared to an average score.
These people also had at least a 31 per cent higher chance of developing heart failure in this period. The results took into account age, sex and other cardiovascular risk factors including cholesterol, blood pressure, diabetes and smoking.
Helping doctors take action
Dr Mihir Sanghvi, Clinical Lecturer in Cardiology at Queen Mary, University of London, and lead author on the study, said:
“Aging and obesity are two of the most central health problems of our time, and both are key risk factors for heart disease. Sarcopenic obesity represents a meeting between the two – it is a crucial sign of health deterioration in obesity, especially for older people.
“We have developed a deep learning tool to measure this, in the hope that it will allow doctors and patients to take action to protect their health. This new tool can help identify people who most need interventions to prevent further muscle loss and a worsening of their condition.”
Sarcopenia is often linked to aging and is common in older adults with long term health problems who find it hard to be active. It is rarely diagnosed because, until now, accurate measurements of sarcopenia required more specialized scans that are less commonly done.
This means that sarcopenic obesity is rarely taken into account when assessing heart health risk. Doctors are more likely to use simpler measures like BMI or waist-height ratio.
The researchers developed a deep learning tool which uses cardiac MRI scans – routinely done in hospitals to look at the heart – to measure the size of the pectoral muscle in grams. The pectoral muscle is the large muscle at the front of the chest, and its size was used as an indicator of general muscle loss in the body. In the study, the team used the AI tool on anonymised scans of over 55,000 people.
To get each person’s sarcopenic obesity index score, their weight in kilograms is divided by their pectoral muscle mass in grams. The heavier a person is or the more muscle they have lost, the higher their score is.
Harnessing the latest technology
Dr Sanghvi and his team found that higher scoring people tended to be older, have higher blood pressure and blood sugar levels, were less likely to be active and were more likely to come from more deprived areas. When they looked at heart measurements taken from the MRI scans, they found that a higher index score was linked to signs that heart failure was developing.
The index score was then used to assess a person’s risk of cardiovascular disease, using an algorithm that also takes into account cardiovascular risk factors. The researchers were able to show that the index score could be used to predict a person’s risk of heart failure or death with much more accuracy than if they had used simpler measures like BMI or waist-height ratio instead.
The researchers hope that, now sarcopenic obesity can be measured using a routine scan done across the country, the index can be a useful tool for doctors to identify risk in anyone having a heart MRI scan. Around 125,000 people had such a scan with the NHS between April 2023 and March 2024, offering a great opportunity for risk to be assessed for thousands of people, not just those who have obesity.
They will now test the tool in clinical practice later in the year, to see if they can identify people with high sarcopenic obesity index scores who are at risk of heart failure and death. Simple interventions like tailored exercise programmes could be enough to prevent sarcopenia worsening and improve the health of certain patients.
Professor Bryan Williams, our Chief Scientific and Medical Officer, said:
“This intriguing study demonstrates how the latest technologies could be used to expand our abilities to predict risk and save lives.
“By finding a new, easier way to measure sarcopenic obesity, this observational study has opened up many possibilities for spotting the condition and assessing the damage it can do to patients’ heart health. It is important to now test whether it can be an effective addition to a doctor’s toolkit as they work to reduce heart failure.”