Historically, medicine has been a male-biased field. Women are also less likely to be diagnosed with cardiovascular disease, diagnosed later, and have more symptoms. Scientists are now using machine learning to build new and improved models that can better predict risk, especially for women. They also found that women are twice as likely to be underdiagnosed as men for certain heart conditions, highlighting the need for gender-specific risk criteria for heart disease detection.
When it comes to heart problems, cardiovascular disease in women is underdiagnosed compared to men. A common scoring system used to estimate the likelihood of developing cardiovascular disease within the next 10 years is the Framingham Risk Score. This is based on factors such as age, gender, cholesterol levels, and blood pressure.
Researchers in the United States and the Netherlands are currently using large datasets to build cardiovascular risk models that are more accurate than the Framingham Risk Score. They also quantified the underdiagnosis of women compared to men. Result is, Frontiers in physiology.
Want more breaking news?
apply technology network'Daily Newsletter. Get the latest science news delivered straight to your inbox every day.
Subscribe for free
“We found that gender-neutral criteria do not adequately diagnose women. If gender-specific criteria were used, this underdiagnosis would be less severe,” said researchers at Stanford University's Living Matter Institute. Schuyler St. Pierre said. “We also found that the best test to improve the detection of cardiovascular disease in both men and women is the electrocardiogram (EKG).”
Underdiagnosis due to heart differences
Anatomically, a woman's heart and a man's heart are different. For example, women's hearts are smaller and have thinner walls. However, the diagnostic criteria for certain heart diseases are the same for women and men. This means that women's hearts must increase 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 the use of gender-neutral criteria led to severe underdiagnosis of female patients. “Women are twice and 1.4 times more underdiagnosed than men for first-degree atrioventricular block (AV) block, a disease that affects the heartbeat, and dilated cardiomyopathy, a heart muscle disease, respectively.” Professor Pierre said. Other heart diseases were also found to be underdiagnosed in women.
old and new
To achieve more accurate predictions for both men and women, scientists leveraged four additional indicators not considered in the Framingham Risk Score: cardiac magnetic resonance imaging, pulse wave analysis, electrocardiogram, and carotid ultrasound. Did. They used data from more than 20,000 individuals who have taken these tests, registered in the UK Biobank, a biomedical database comprising information from around 500,000 people aged 40 and over in the UK. used.
“Traditional clinical models are easy to use, but we use machine learning to examine thousands of other possible factors to find new and meaningful features that can significantly improve early detection of disease. Now we can do that,” explained St-Pierre. Just a decade ago, these techniques were not available. That's why rating scales like the Framingham Risk Score have been used for half a century.
Using machine learning, researchers determined that of the indicators tested, electrocardiograms were the most effective at improving the detection of cardiovascular disease in both men and women. However, this does not mean traditional risk factors are not important tools for risk assessment, the researchers said. “We want clinicians to first screen people using simple surveys that include traditional risk factors, and then do a second stage of screening using electrocardiograms for high-risk patients. I'll make a suggestion.
Paving the way to custom medicine
This study is a first step in reconsidering risk factors for heart disease. Leveraging new technologies is a promising way to improve risk prediction. However, the study had some limitations that need to be addressed in the future, the researchers said.
One such limitation is that gender is treated as a dichotomous variable in the UK Biobank. But sex is inherently complex, involving hormones, chromosomes, and physical characteristics, all of which can fall somewhere on the spectrum between a “typical” man and a “typical” woman. There is a gender.
Additionally, the study subjects were middle-aged and older people residing in the UK, so the results may not be applicable to people from other backgrounds or ages. “Gender-specific medicine is a step in the right direction, but patient-specific medicine will yield the best outcomes for everyone,” St-Pierre concluded.
reference: St. Pierre SR, Kaczmarski B, Peirlinck M, Kuhl E. Sex-specific cardiovascular risk factors in the UK Biobank. Frontiers in physiology. 2024;15. doi: 10.3389/fphys.2024.1339866
This article has been reprinted from the following material: Note: Materials may be edited for length and content. Please contact the citation source for details.You can access our press release publishing policy here.
