Analysis of Breast Cancer Routine Scans Can Predict Cardiovascular Disease Risk

November 8, 2020
Matthew Fowler
Matthew Fowler

A recent study found that automated analyses of CT scans for patients with breast cancer can predict which patients are likely to develop cardiovascular disease in the future.

According to research that was presented at the 12th European Breast Cancer Conference, automated analyses of routine scans for patients with breast cancer can predict which women have greater than a 1 in 4 risk of eventually developing cardiovascular disease.

The research suggests that women who have recently been treated for breast cancer have a higher risk of developing cardiovascular disease, and the risk of dying from cardiovascular disease is greater than the risk of dying from breast cancer in some groups of patients.

"We've seen great improvement in breast cancer survival, thanks in part to better treatment,” Professor Helena Verkooijen, of the University Medical Center Utrecht in The Netherlands, said in a press release. “However, treatments have side effects and some treatments - such as radiotherapy and certain types of cancer drug - can increase the risk of cardiovascular disease. In my opinion, treating breast cancer means finding the right balance between maximising chances of tackling the tumour, while minimising the risks of side effects, including the risk of cardiovascular disease.”

The study analyzed around 14,000 patients with breast cancer treated with radiotherapy between 2005 and 2016 in 3 hospitals across The Netherlands. The researchers followed the cohort of women for an average of 52 months to identify if any of them developed cardiovascular disease.

In terms of calcifications found in patients, 5% of women with no calcifications went on to be hospitalized or die from cardiovascular disease. For women with a score between 1 and 10, 8.9% were hospitalized or died. More, a score of 11-100 saw women hospitalized or died 13.5% of the time. Finally, for women with a score of 101-400 it was 17.5% and in women with a score above 400, it was 28.3%.

When taking into account age and the year a patient was diagnosed, researchers found a 3.7 times greater risk of cardiovascular disease for patients with a score of 400 or above compared to women with no calcifications.

The researchers implemented a coronary artery calcium (CAC) score, which calculates the amount of calcium in the walls of the heart's arteries, which is known to be a strong indicator of high risk factor for cardiovascular disease. They then developed a deep learning algorithm to gauge the presence and extent of coronary artery calcifications from CT scans, allowing the researchers to automate the process.

"We believe this is the first time anyone has conducted a large-scale study like this,” said Verkooijen. “We've shown that we can use routine CT scans to indicate which breast cancer patients are most likely to develop cardiovascular disease. Now we need to do more research to find out what can be done to help minimise this risk, for instance whether patients' cardiovascular health should be monitored or treated."

Computer analysis of CT scans was able to spot patients at greater risk for cardiovascular disease, which researchers suggested could allow for ample steps to be taken to minimize that risk.

The team of researchers are working to utilize their technique for cardiovascular risk prediction in radiotherapy units across The Netherlands. For patients who took part in the research and were found to have increased risk of cardiovascular disease, they will be offered further cardiovascular screenings and lifestyle advice, while their scores will be used to plot a breast cancer treatment course.

Reference:

Risk of heart disease in breast cancer patients can be predicted from routine scans [news release]. Published October 1, 2020. https://www.eurekalert.org/pub_releases/2020-10/eofr-roh092920.php. Accessed November 2, 2020.