Using a data-driven strategy, scientists “innovatively identified plasma biomarkers important for predicting future dementia,” the researchers wrote in a paper published Monday in the peer-reviewed journal Nature Aging. Stated.
01:50
Chinese researchers claim breakthrough in brain-computer interface using monkey brain signals
Chinese researchers claim breakthrough in brain-computer interface using monkey brain signals
But scientists have bigger goals in mind for blood biomarker tools, including using them to accurately predict whether a patient is likely to develop the disease in the future, before clinical symptoms appear. ing.
The authors say there is no cure for dementia, but understanding whether a person is likely to develop dementia could allow for earlier diagnosis and intervention.
The large-scale study of proteins, also known as proteomics, can be used to find potential drugs and diagnostic interventions for diseases and to better understand how the human body works.
However, systematically studying proteins in blood has proven difficult due to “technical constraints” and a lack of comparative methods, the researchers wrote.
To overcome this barrier, the research team used the support of a large UK biobank cohort. This cohort enrolled over 50,000 people from age 40 to age 69, and the median follow-up period from the mid-2000s was 14 years.
Just over 1,400 people in the biobank cohort, all of whom provided biological samples and demographic information, developed dementia within 10 years of initial data collection.
The Biobank recently announced a new dataset of more than 1,400 plasma, or blood proteins, found in participants’ samples during initial intake and follow-up sessions.
Deciphering Dementia: SCMP Lifestyle Series highlights research on causes and treatments
Deciphering Dementia: SCMP Lifestyle Series highlights research on causes and treatments
The publication of this data gives the team an “unprecedented opportunity” to conduct proteomic studies of blood proteins associated with the development of dementia, the paper said.
This allowed them to “trace the trajectory of plasma proteins from the time of dementia diagnosis and assess when each protein begins to deviate from normal control values,” the researchers wrote.
Scientists found hundreds of proteins involved, but focused their research on a small number of “key proteins” whose expression began to change at least 10 years before the clinical onset of dementia. .
Machine learning algorithms were used to determine which proteins produced better predictive models, which were then matched against biobank data showing which subjects developed dementia.
The algorithm, which played a “key” role in the study, has “powerful pattern recognition and prediction capabilities” and enables more efficient screening of large datasets, Yu said. .
According to the research team, including the protein data itself in a predictive model is “unlikely to achieve the highest predictive accuracy.”
02:13
Singaporean with dementia rediscovers fond memories at quiet disco
Singaporean with dementia rediscovers fond memories at quiet disco
To develop “an optimal predictive algorithm that is non-invasive, cost-effective, and easily accessible,” they combined data on a protein called GFAP, which was found to more than double the risk of dementia. , combined with demographic information such as age. And sex.
Their final integrated predictive model shows the potential to “accurately predict future dementia even more than 10 years before diagnosis,” according to the paper.
And compared to imaging scans and spinal taps used to test for disease risk, the method could “offer significant cost benefits,” the paper says.
Chinese government pushes breakthroughs in future-defining chips and quantum computing
Chinese government pushes breakthroughs in future-defining chips and quantum computing
The research team said the study remains limited as more than 90% of the biobank population is comprised of subjects of Caucasian ethnicity and is therefore not globally representative. The proteins examined do not involve the entire human proteome.
However, Yu said the research team was also currently studying a cohort of Chinese people, which would allow them to examine similarities and differences with the UK-based database.
Previous research “has provided clues for the development of new treatments and intervention strategies,” he said, adding that the research team is also using the biobank to test for other brain-related diseases, such as depression and Parkinson’s disease. He added that
