Medical Breakthrough: New Blood Test Could Detect A Wide Range Of Diseases

While a yearly routine health checkup may identify worrisome health indicators, more detailed information can be provided by cost-effective artificial intelligence that can determine prognosis based on a single sample of blood. 

A recent study published Monday in the journal Nature Medicine elaborated how they utilized datasets and statistical methods to predict 11 health concerns in total. Researchers from the University of Cambridge, University of California, San Francisco, and American biotech firm SomaLogic collaborated on the project. After doing the blood test, they first used genetic sequencing technology to identify the concentration levels of aptamers present in the blood plasma, which bind to specific proteins.

Proteins are useful in making predictions about health conditions because several protein patterns are associated with certain risks. One such protein is leptin, which regulates hunger pangs and metabolism that is also helpful in identifying future risks of gaining body fat, visceral fat, implications of less physical activity and fitness.

The results were then analyzed further with machine learning algorithms, which evaluated various health risks through the analysis of plasma. Blood plasma is a light-yellow fluid when separated from blood that makes up 55 percent of the blood content. It is the fluid that transports nutrients, hormones, salt, enzymes and proteins throughout the body. 

"Proteins circulating in our blood are a manifestation of our genetic make-up as well as many other factors, such as behaviours or the presence of disease, even if not yet diagnosed. This is one of the reasons why proteins are such good indicators of our current and future health state and have the potential to improve clinical prediction across different and diverse diseases," Dr. Claudia Langenberg, who works at the MRC Epidemiology Unit at the University of Cambridge, said.

This proof-of-concept study was executed with the use of archived plasma samples from 16,894 participants, containing 5,000 proteins each. Overall, the study measured 85 million protein targets. 

The wide range of diseases predicted included a host of issues related to putting on weight and lifestyle factors such as percentage of body fat, body mass, visceral fat, impact of low physical activity and cardiopulmonary fitness, risks involved with excessive indulgence in alcohol and smoking. The more specific ill-health indicators included liver fat, kidney filtration, diabetes risk and primary cardiovascular event risk.

The researchers believe more safety testing and clinical trials need to be done. But they are confident that with the rapid advancement of technology, this process will help doctors perform a comprehensive “liquid health check” with just a single blood sample from the patient. 

"It's remarkable that plasma protein patterns alone can faithfully represent such a wide variety of common and important health issues, and we think that this is just the tip of the iceberg," Dr. Stephen Williams, Chief Medical Officer of SomaLogic and lead study author, said. 

"We have more than a hundred tests in our SomaSignal pipeline and believe that large-scale protein scanning has the potential to become a sole information source for individualised health assessments," Dr. Williams added. 

However, the researchers noted that not all the models were completely accurate in the predictions, especially for cardiovascular risk, whereas the risk assessment was spot on for body fat parameters.  

Blood samples A recent study published in the journal Nature Medicine evaluated how a single blood test could help detect as many as 11 indicators of deteriorating health. Photo courtesy of U.S. Navy