Article image

Blood biomarkers predict dementia onset 15 years in advance

In a significant study, researchers have determined that protein biomarkers in the blood can predict the onset of dementia up to 15 years before clinical symptoms appear. 

The research, conducted by scientists from The University of Warwick and Fudan University, represents the most extensive study of its kind. The experts used blood proteomics to predict the risk of dementia long before its debilitating effects take hold.

Focus of the study 

The study was focused on blood samples from 52,645 healthy participants in the UK Biobank. These samples, collected between 2006 and 2010, were preserved and examined a decade or more later, between April 2021 and February 2022. 

By March 2023, 1,417 of the individuals had developed dementia. Remarkably, the researchers were able to trace dementia onset back to dysregulation in specific protein biomarkers identified in the participants’ blood samples.

Predicting future dementia

Utilizing a sophisticated machine learning approach, the team scrutinized 1,463 proteins, ultimately identifying and focusing on a panel of 11 proteins that demonstrated a high degree of accuracy in predicting future dementia cases. 

When this protein panel was combined with other conventional risk factors – such as age, sex, education level, and genetics – the predictive accuracy of the model soared to over 90%, showcasing its immense potential for application in community-based dementia screening programs.

Combining artificial intelligence with protein analysis

The significance of these findings cannot be overstated. Early diagnosis of dementia is crucial, as it opens the door to treatments that can slow or even reverse the progression of diseases like Alzheimer’s. The study highlights the drug lecanemab, among others, as a beacon of hope for early-stage treatment.

Study lead author Professor Jianfeng Feng emphasized the transformative potential of combining artificial intelligence with protein analysis. This methodology not only paves the way for precision medicine but also promises to enhance the screening process for middle-aged to older individuals at high risk of dementia. 

“This model could be seamlessly integrated into the NHS and used as a screening tool by GPs,” said Professor Feng.

Advantages of proteomic biomarkers

Study co-author Professor Wei Cheng highlighted the advancement this study represents over previous research efforts. Compared to earlier models that relied on variables like age and genetic markers, the protein-based model offers a non-invasive, easily accessible, and significantly more precise method for predicting dementia onset.

Professor Jintai Yu, a neurovegetative disease specialist also from Fudan University, pointed out the advantages of proteomic biomarkers over traditional, more invasive methods such as lumbar punctures or complex imaging. 

“The proteomic biomarkers are more easily to access and non-invasive, and they can substantially facilitate the application of large-scale population screening,” said Professor Yu.

Broader implications 

This study not only sheds light on the potential of protein biomarkers as a powerful tool for early dementia detection but also underscores the importance of interdisciplinary collaboration in advancing medical science. 

The integration of artificial intelligence, proteomics, and clinical research holds the promise of revolutionizing the way we predict, diagnose, and treat dementia, offering hope to millions of individuals and families affected by this devastating condition.

The research is published in the journal Nature Aging.

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.


Check us out on EarthSnap, a free app brought to you by Eric Ralls and

News coming your way
The biggest news about our planet delivered to you each day