New models improve risk prediction for heart disease, especially for women

New models improve risk prediction for heart disease, especially for women

When it comes to heart matters, cardiovascular disease is underdiagnosed in women compared to men. A popular scoring system for estimating the likelihood of a person developing cardiovascular disease within the next 10 years is the Framingham Risk Score. It is based on factors such as age, gender, cholesterol levels and blood pressure.

Researchers in the US and the Netherlands have now used a large data set to create more accurate cardiovascular risk models than the Framingham Risk Score. They also quantified the underdiagnosis of women compared to men. The results were published inLimits in physiology.

We have found that gender-neutral criteria are not sufficient when diagnosing women. If gender-specific criteria were used, this underdiagnosis would be less serious. We also found that the best test to better detect cardiovascular disease in both men and women is the electrocardiogram (ECG).”

Skyler St. Pierre, Researcher, Living Matter Lab, Stanford University

Underdiagnosis due to cardiac differences

Anatomically speaking, female and male hearts are different. For example, female hearts are smaller and have thinner walls. However, the diagnostic criteria for certain heart diseases are the same for women and men, meaning that women's hearts must grow disproportionately more than men's before the same risk criteria are met.

When researchers quantified the underdiagnosis of women compared to men, they found that using gender-neutral criteria results in severe underdiagnosis of female patients. “In women, first-degree atrioventricular block (AV), a disorder that affects the heartbeat, and dilated cardiomyopathy, a heart muscle disease, are twice and 1.4 times more likely to be underdiagnosed than in men,” St. Pierre said. Women have also been found to be underdiagnosed with other heart diseases.

Old vs. new

To achieve more accurate predictions for both sexes, the scientists used four additional measurements not included in the Framingham Risk Score: cardiac magnetic resonance imaging, pulse wave analysis, EKGs and carotid ultrasound. They used data from more than 20,000 people in the UK Biobank - a biomedical database containing information from around half a million British people aged 40 and over - who had undergone these tests.

“While traditional clinical models are easy to use, we can now use machine learning to sift through thousands of other possible factors to find new, meaningful features that could significantly improve early disease detection,” St. Pierre explained. These methods were not available ten years ago, which is why rating scales such as the Framingham Risk Score have been used for half a century.

Using machine learning, the researchers found that of the measurements tested, ECGs were most effective at improving the detection of cardiovascular disease in both men and women. However, this does not mean that traditional risk factors are not important risk assessment tools, the researchers said. “We suggest that physicians first screen patients for traditional risk factors using a simple survey and then perform a secondary screening using ECGs for patients at higher risk.”

Paving the way for individual medicine

The present study represents a first step in reconsidering risk factors for heart disease. The use of new technologies is a promising way to improve risk prediction. However, the study has some limitations that should be addressed in the future, the researchers said.

One such limitation is the fact that gender is treated as a binary variable in the UK Biobank. However, sex is inherently complex and involves hormones, chromosomes, and physical characteristics, all of which can fall somewhere on a spectrum between “typical” male and “typical” female.

Furthermore, the study population was middle-aged and older people residing in the UK, so the results may not be generalizable to people of other backgrounds and ages. “While gender-specific medicine is a step in the right direction, patient-specific medicine would provide the best results for everyone,” St. Pierre concluded.

Sources: