Scientists in the United States have announced that they have developed a new blood test that can predict whether someone is at high risk for heart attack, stroke, heart failure or death from the above within the next four years.
The test, which depends on measurements of proteins in the blood, is about twice as accurate as existing methods of assessing heart risk, according to the researchers. They said it could help doctors decide in the future how effective the drugs they have given their patients are or if they need more to reduce the risk of a heart attack.
Also, the test, which began to be used in the US, could be used to accelerate the development of new cardiovascular drugs, as it will show in time if a candidate drug "works" in a clinical trial.
The researchers, led by Dr. Stephen Williams of SomatoLogic, Colorado, who published the study in the American journal Science Translational Medicine, according to the British Guardian, used artificial intelligence to learn machine learning. about 5.000 proteins in blood samples from 22.849 people. Thus, the "signature" of 27 proteins that can function as biomarkers for the prediction of cardiovascular risk during the next four years was identified.
It was tested on over 11.000 people
The system was then tested on 11.609 people and found to be almost twice as accurate as the current risk prediction models used by cardiologists, which take into account various factors (age, sex, medical history, blood counts such as cholesterol, hypertension). etc.).
The test is also very accurate in assessing the future risk of a second heart attack for those who have had a heart attack, stroke or other related event in the past, as well as for those who have other conditions (comorbidities) and are taking extra medication.
"This is the new frontier of personalized medicine: being able to answer the question of whether a person needs better treatment, and whether treatment really works for someone," Williams said. "It would not matter if everyone was the same. But the problem is that everyone can have a cure, but while some people will benefit and have the reduced risk of a 40-year-old or 30-year-old, others will have a new heart attack next year, even though they all look the same. "The ability to distinguish between these two different people in order to give some people better cardioprotective drugs because they are more at risk is a medical need that has not been met so far."
The SomatoLogic test uses protein biomarkers to categorize people in a range of low to high risk and gives a "score" for the likelihood of a heart attack within the next four years. According to Williams, "if someone's score is high, there is a one in two chance of having a heart attack, but the average time it takes for that to happen is within the next 18 months, with the most likely outcome being death. This person will need immediate improved cardioprotection. Fortunately, treatments already exist. The problem is to find who needs them the most and then measure if they really worked well enough. "
However, Manuel Meyer, professor of cardiovascular medicine at King's College London, said: "While the new study brings to light new correlations between blood proteins and death from all causes, more research is needed to assess the potential clinical utility use of these 27 proteins, compared to existing cardiovascular risk prediction tools ”.