Protein Score from Single Plasma Sample Predicts Cardiovascular Disease

In a large retrospective analysis, utilizing measurements of plasma proteins from thousands of individuals across primary and secondary event populations, researchers have harnessed artificial intelligence (AI) to create a protein score for predicting major atherosclerotic cardiovascular disease events (ASCVD).

The study by scientists from deCODE genetics (Reykjavik, Iceland) was based on an extensive dataset comprising more than 13,500 Icelanders without a history of major ASCVD prior to plasma sampling, as well as over 6,000 participants from the FOURIER trial who had already experienced ASCVD before plasma sampling. In all these cases, plasma protein levels were assessed using the SomaScan platform, measuring approximately 5,000 plasma proteins. Notably, the protein risk score, derived solely from proteomics data of a single plasma sample, effectively predicts ASCVD events even without access to medical history or risk factor information. While much of the risk assessed by the proteins is also reflected in established risk factors, the protein score captures additional risk.

Furthermore, the protein risk score is a dynamic measure. Unlike certain immutable classic risk factors like family history and prior ASCVD events, this score can be modified upon treatment. The dynamic nature of protein risk scores—where protein levels fluctuate in relation to the timing of events—makes them well-suited for predicting event timelines. Consequently, these protein risk scores could prove invaluable in clinical trials for early evaluation of treatment efficacy or risk monitoring.

“We believe that in the proteomic risk score, we may have a biomarker that will allow the world to conduct shorter clinical trials with fewer participants,” said Kari Stefansson, CEO of deCODE genetics and one of the senior investigators of the study. “This is going to make the development of new medicines less expensive and make them available sooner for those who need them. Furthermore, in clinical practice it may allow for more effective prevention of ASCVD.”

Related Links:
deCODE genetics