Hope for early detection and prevention. A study shows success in predicting neurodegenerative diseases such as dementia.
Shanghai – A new study offers great hope in the fight against forgetting. A team of scientists from the University of Warwick and Fudan University in Shanghai has succeeded in developing a new procedure that diagnoses dementia well before the first symptoms appear.
Detecting dementia without symptoms: Blood test should predict illness 15 years before diagnosis
Accordingly, blood proteins can predict dementia up to 15 years before clinical diagnosis. Scientists have discovered this using machine learning methods and thus advanced research into preventing this disease. More than 55 million people worldwide suffer from dementia.
Researchers achieve breakthrough in methodology for early detection of dementia risk
The analysis, the largest of its kind to date, reinforces the results of smaller studies that suggest certain proteins are “biomarkers” of susceptibility to Alzheimer’s and other neurodegenerative diseases, the in Nature aging published study.
Effective screening methods for early detection of dementia risk would enable the use of drugs that slow or even reverse the onset of the disease, significantly reducing costs for healthcare systems.
“We can predict dementia fairly reliably 15 years before the disease is diagnosed,” Jianfeng Feng, lead author of the study and professor of computer science at the University of Warwick, told the Financial Times. “We expect our finding to open a path to developing new approaches to slow disease progression.”
Dementia is widespread in Germany
At the end of 2021, Germany recorded, according to German Alzheimer Society, nearly 1.8 million people suffered from dementia, with Alzheimer’s being the leading cause. In the same year, around 440,000 people aged 65 and older developed dementia. Due to demographic change, the number of those affected is expected to continue to rise.
Premature anamnesis: Looking into the future with the help of blood samples
The study used blood from 52,645 subjects collected and frozen between 2006 and 2010 by the UK Biobank genetic database. The researchers analyzed the samples between April 2021 and February 2022. More than 1,400 members of the research cohort developed dementia – and had abnormal levels of some blood proteins. The researchers analyzed 1,463 proteins using machine learning and identified 11 that were found to be accurate predictors of future dementia.
The combination of protein analysis and artificial intelligence techniques, such as large-language models, could enable precise screening of middle-aged and older people for their risk of dementia, Feng said. The results are “relatively ready” for use in clinical practice by national health systems, he added.
New process: Researchers want to increase prediction accuracy
The emergence of potential dementia diagnoses follows advances in treatment options. In October, pharmaceutical companies Eisai and Eli Lilly presented research showing the benefits of using new Alzheimer’s drugs at a very early stage of the disease.
The one in the magazine Nature aging The published research results are another “fantastic advance in the development of blood tests for Alzheimer’s,” said Dr. Sheona Scales, research director at the charity Alzheimer’s Research UK.
The study’s prediction models need to be further evaluated, say the scientists. The “next steps” should be to “show how these protein markers perform in other cohorts that are less healthy and affluent than the UK Biobank participants,” says Charles Marshall, professor of clinical neurology at Queen Mary University of London , who was not involved in the study Financial Times.
Another important follow-up would be to investigate whether prediction accuracy could be further improved by combining the study’s protein marker analysis with other techniques such as blood tests and brain scans, Marshall added. (ls)