The test, which is already available in the US, could allow doctors to determine if patients’ existing medications work or if they need additional medications to reduce the risk. It could also accelerate the development of new cardiovascular drugs by providing a faster means of assessing whether drug candidates are working during clinical trials. Protein analysis can provide a more accurate picture of what one’s organs, tissues, and cells are doing at any given time. Stephen Williams at SomaLogic in Boulder, Colorado, and colleagues used machine learning to analyze 5,000 proteins in plasma samples from 22,849 people and identify a protein signature that could predict a four-year chance of heart attack, stroke or stroke. death. When validated in 11,609 participants, they found that their model surpassed existing risk prediction tools, which use age, gender, race, medical history, cholesterol and blood pressure to characterize risk. “Our ability to stratify risk in all populations is more than double that of existing risk scores,” said Williams, whose findings were published in Science Translational Medicine. Importantly, the test could also accurately assess risk in people who have had a previous cardiovascular event and are taking medications to reduce the risk, something that existing risk assessments find difficult to do. The tool is already used in four health systems in the US and SomaLogic is in discussions about its possibility to be introduced in the UK.
