Protein biomarkers help predict dementia 15 years in advance

New drug technology can slow or even reverse the progress of Alzheimer’s, but only if the disease is detected early enough. Now UK and Chinese scientists have shown how profiles of proteins in the blood accurately predict dementia up to 15 years prior to clinical diagnosis, with their breakthrough study — understood to be the largest of its kind — published in the journal Nature Aging.

Scientists at The University of Warwick and Fudan University used the largest known cohort of blood proteomics and dementia to date, including blood samples from 52,645 healthy participants recruited from the UK Biobank (UKBB). Blood samples collected between 2006 and 2010 were frozen and then analysed by the research team between April 2021 and February 2022. As of March 2023, a total of 1417 participants had gone on to develop dementia — and these people’s blood showed dysregulation of protein biomarkers.

Of 1463 proteins analysed, aided by a type of artificial intelligence (AI) known as machine learning, 11 proteins were identified and combined as a protein panel, which the researchers showed to be highly accurate at predicting future dementia. Further incorporation of conventional risk factors of age, sex, education level and genetics saw the predictive model reach an accuracy of over 90%, indicating its potential future use in community-based dementia screening programs.

“This model could be seamlessly integrated into the NHS and used as a screening tool by GPs,” said lead author Professor Jianfeng Feng, from the University of Warwick and Fudan University.

Proteins (eg, Glial Fibrillary acidic protein, or GFAP) had previously been identified as potential biomarkers for dementia in smaller studies, but this new research was much larger and conducted over several years. Known as a longitudinal analysis (a study conducted on a sample of participants over a number of years), the researchers were able to show the differences and trajectories between those with dementia and controls across 15 years.

Feng said the combination of AI and protein analysis offers a promising avenue for precision medicine, which is highly important for screening middle-aged to older individuals within the community who are at high risk of dementia. He hopes that future drugs may be developed to interact with the proteins identified in the study.

Co-corresponding author Professor Wei Cheng, from Fudan University, added that the research builds on the team’s previously developed dementia prediction model which used variables such as age, the presence of a certain gene and mother’s age at death. Co-corresponding author Professor Jintai Yu, also from Fudan University, noted that other previous risk models were primarily dependent on intricate and difficult-to-obtain biomarkers using procedures such as lumbar puncture or complex imaging methods, hindering their widespread use.

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

Commenting on the news was Dr Sheona Scales, Director of Research at Alzheimer’s Research UK, who said the new study “adds to the growing body of evidence that measuring levels of certain proteins in the blood of healthy people could accurately predict dementia before symptoms develop”.

“Further studies, including in more diverse populations, are needed to verify these tests and predictive models,” Scales noted. “And, even when tests show promise in studies like this, they still need to go through regulatory approval before they can be used in a healthcare setting.”

Dr Amanda Heslegrave, a Senior Research Fellow at the UK Dementia Research Institute at UCL, added that studies such as this “are required if we are to intervene with disease-modifying therapies at the very earliest stage of dementia”.

“Limitations to be aware of are that the UKBB is a highly curated biobank and may not capture all populations that we need to know the risk for; the new biomarkers identified will need further validation before being used as screening tools,” she said.

“The implications are that with disease-modifying treatments close to being approved in the UK we need to develop a screening strategy. This study with its use of follow-up data needs to be replicated, and biomarkers that enable us not only to screen for disease risk, but also to differentiate between diseases, should be a priority.”

Image credit: iStock.com/Henk Badenhorst