Predict a heart attack with 60% accuracy? A new protein test could indicate your risk

0

Do you know your risk of heart attack? Many people don’t know — or don’t seem to care to know — their risk “rating”.

But such a risk score system has been used for quite some time. In general, it establishes his overall risk of heart disease. These tools include: cholesterol test, blood pressure, lifestyle factors (do you exercise 150 minutes a week?), family history, and other conditions such as diabetes.

But can you predict when a heart attack is likely to strike someone, with greater accuracy?

It turns out that it may now be possible. A new test using artificial intelligence (AI) analyzing a host of proteins in the blood has been developed, promising much higher accuracy in predicting cardiovascular ‘events’ you may face.

Compared to the existing ‘risk score’ system, the protein-based analyzer claims 60% accuracy in predicting heart attack risk over a period of 4 years to 48 months.

36seconds

One person dies every 36 seconds in the United States from cardiovascular disease.

What is the new test?

This is called the “protein model”. The method uses at least 27 proteins found in the blood. This is significant: this number represents about a quarter of all the proteins encoded by our genes, according to experts.

Why only now?

This method has only become possible in the current era, thanks to new emerging technologies and rapid computing power, which allow experts to measure thousands of blood proteins to assess individual patient risk.

Who invented it?

Colorado-based researchers led by Dr. Stephen Williams developed the test and published their work in Science Translational Medicine newspaper of April 6, 2022.

Dr. Williams, chief medical officer of the American company SomaLogic, specializes in translational medicine and the development of diagnostics and the management of a clinical trial laboratory. The team included 22 experts in different medical disciplines from different parts of the world to collaborate on the development of the test.

LOW, MEDIUM, HIGH RISK

SomaLogic’s test uses protein measurements to categorize people at ‘high’ to ‘low’ risk – as well as providing a percentage chance that they will suffer a cardiovascular event within the next four years.

It uses AI to develop a predictive model. An algorithm was developed to determine the risk.

Image Credit: Seyyed de la Llata ​​/ Gulf News

How many blood samples were used to test its accuracy?

To test the accuracy of this protein method, 32,130 samples of “archived” plasma (amber-colored fluid in the blood) from 22,849 participants in nine clinical studies were used, according to the journal.

Using machine learning, Williams’ team analyzed 5,000 proteins in blood plasma samples from 22,849 people. And that’s how they identified a signature of 27 proteins that could predict the likelihood of a heart attack, stroke, heart failure or death, over a 48-month period. .

What is the role of blood proteins in predicting heart attacks?

In general, heart disease (or cardiovascular risk factors) activates a number of pro-oxidant genes in the wall of blood vessels (vascular). This results in the generation of reactive oxygen species, especially those generated by the endothelium (a thin membrane that lines the inside of the heart and blood vessels).

Using modern clinical tools, measurement of endothelial-dependent vasodilation (a nitric oxide-mediated process) by a variety of different techniques now provides a marker of endothelial integrity.

What is the role of the endothelium in the production of these proteins?

In medical science, it is a known fact that endothelial cells release substances that control vascular relaxation and contraction – as well as enzymes that control blood clotting, immune function, and platelet adhesion (a colorless substance in the blood).

I think this is the new frontier of personalized medicine, to be able to answer the question, does this person need enhanced treatment? And when you treated someone, did it actually work?

– Dr. Stephen Williams, chief medical officer of the American company SomaLogic

These genes also induce a complex cascade of events that underlies the transition from normal endothelial function to dysfunction. The result: abnormal heart activity, development of a pro-coagulant endothelial surface, inflammation, and eventually the formation of plaques that progressively block the flow of oxygenated blood to the heart, possibly leading to a heart attack.

What does this new test mean?

Globally, heart disease is the leading cause of death – one in three – as well as disability.

In both the developed and developing world, the risk is increasing, despite the development of lipid-lowering, anti-inflammatory, antithrombotic, dual antiplatelet, and antidiabetic therapies.

A 2012 study published in the journal JAMA predicts that the risk of developing heart disease is more than 40% on average and 30% in women over the course of their lives.

“I think that’s the new frontier of personalized medicine, to be able to answer the question, does that person need enhanced treatment? And when you’ve treated someone, does that really worked?” said lead researcher Dr Williams.

But can you really predict when a heart attack would happen?

According to Dr. Sutter Zi-Jian Xu, a cardiologist with the Sutter Health Network, people may notice subtle symptoms of a heart attack months before an actual event occurs.

The current risk score system – the most widely used in the world – takes into account a person’s age, gender, race, medical history, cholesterol and blood pressure to assess their likelihood of have a cardiovascular event.

The new 27-protein model takes this scoring method to the next level.

When its predictive ability was validated on 11,609 individual cases, the researchers found that their model was about “twice as good” as existing heart disease risk “scores.”

The new test was also able to accurately assess risk in people who have already had a heart attack or stroke, or who have other illnesses, and are taking medication to reduce their risk. This is where existing risk prediction scores tend to fall short.

Where does the “60% accuracy” come from?

Overall, the researchers said that in their study, less than a quarter of people who tested positive had had a heart attack, which equates to a positive predictive value of 22% (at a 95% confidence interval). .

The test, however, accurately identified nearly all patients who died or had a major cardiac adverse event within 30 days, equating to a sensitivity of 98.0%.

190831 heart attack

HEART ATTACK PREDICTOR | The protein model test differs from genetic testing in that protein analysis provides a more accurate snapshot of what a person’s organs, tissues and cells are doing at any given time, William’s team explained. .

What is the benefit of the protein test?

The most common predictor of heart attack risk is high LDL cholesterol (the “bad” cholesterol) or low HDL cholesterol (the “good” cholesterol), or both.

In general, genetic testing can give an idea of ​​a person’s risk for certain diseases based on their genetic profile. The protein model test differs from genetic testing in that protein analysis provides a more accurate snapshot of what a person’s organs, tissues and cells are doing at any given time, William’s team explained. .

Risk Rating System

FACTORS | The current risk score system – the most widely used in the world – takes into account a person’s age, gender, race, medical history, cholesterol and blood pressure to assess their likelihood of have a cardiovascular event.

FACTS ABOUT HEART DISEASE:

Heart disease is the leading cause of death for men, women, and people of most racial and ethnic groups in the United States.

One person dies every 36 seconds in the United States from cardiovascular disease.

Approximately 659,000 people in the United States die each year from heart disease, or 1 in 4 deaths. $363 billion, annual cost of heart disease in the United States, 2016 to 2017.

[Source: CDC]

How much does this test cost? When can I get it?

The test is already in use in four health systems in the United States. Pricing for the test is not immediately available.

Professor Manuel Mayr, British Heart Foundation Professor of Cardiovascular Proteomics at King’s College London, said: “Proteins are the building blocks of our bodies. Although this study reveals novel associations between proteins in the blood and death from all causes, further research is needed to assess the potential clinical impact of using these 27 proteins, compared to current tools for predicting risk of cardiovascular disease.

Share.

About Author

Comments are closed.