New machine learning models to boost diagnosis of women’s heart disease

New machine learning models to boost diagnosis of women’s heart disease
x
Highlights

As cardiovascular diseases in women remain underdiagnosed compared to men, new machine learning models that use sex-specific criteria may help...

As cardiovascular diseases in women remain underdiagnosed compared to men, new machine learning models that use sex-specific criteria may help overcome this as well as boost treatment outcomes, according to a study.

Although anatomical differences exist between male and female hearts as women have smaller hearts with thinner walls, yet, the diagnostic criteria for certain heart diseases have been the same for both.

“This means that women’s hearts must increase disproportionately more than men’s before the same risk criteria are met,” argued the researchers in the paper published in the journal Frontiers in Physiology. They said this sex-neutral approach leads to severe underdiagnosis of women, especially during “first-degree atrioventricular block (AV) block, a disorder affecting the heartbeat, and dilated cardiomyopathy, a heart muscle disease, twice and 1.4 times more than men, respectively.”

“We found that that sex-neutral criteria fail to diagnose women adequately. If sex-specific criteria were used, this underdiagnosis would be less severe,” said Skyler St Pierre, a researcher at Stanford University’s Living Matter Lab, US.

“We also found the best exam to improve detection of cardiovascular disease in both men and women is the electrocardiogram (EKG),” he added.

To build more accurate heart risk models based on sex-specific criteria, the team added four metrics not considered in the popular Framingham Risk Score – cardiac magnetic resonance imaging, pulse wave analysis, EKGs, and carotid ultrasounds.

The Framingham Risk Score is a popular system to diagnose heart risks based on age, sex, cholesterol levels, and blood pressure. The diagnostic system can estimate how likely a person is to develop a heart disease within the next 10 years. The team used data from more than 20,000 individuals in the UK Biobank who had undergone these tests. Using machine learning, the researchers determined that of the tested metrics, EKGs were most effective at improving the detection of cardiovascular disease in both men and women. This, however, does not mean that traditional risk factors are not important tools for risk assessment, the researchers said.

“We propose that clinicians first screen people using a simple survey with traditional risk factors, and then do a second stage screening using EKGs for higher risk patients,” they added.

Show Full Article
Print Article
Next Story
More Stories
ADVERTISEMENT
ADVERTISEMENTS