Researchers at Lund University in Sweden have developed an artificial intelligence model capable of detecting and distinguishing several neurodegenerative brain diseases from a single blood sample. The findings were published on March 31, 2026, in the journal Nature Medicine.
The AI system was created by a team led by Dr Jacob Vogel, assistant professor and head of a research group within the MultiPark strategic research area at Lund University, and Dr Lijun An, postdoctoral researcher specialising in neurodegeneration.
The work was conducted in collaboration with colleagues from the Swedish BioFINDER study and the Global Neurodegenerative Proteomics Consortium, an international collaboration that maintains one of the world’s largest proteomic databases for neurodegenerative diseases.
The AI model analyses proteomic data from blood, measuring thousands of proteins to identify unique biological signatures associated with different neurodegenerative conditions. Unlike traditional diagnostic tools that focus on one disease at a time, the AI uses a method called joint learning to recognise patterns that distinguish multiple diseases simultaneously. This allows the system to classify several disorders using data from a single blood draw.
In research testing, the AI successfully distinguished among five major conditions: Alzheimer’s disease, Parkinson’s disease, amyotrophic lateral sclerosis (ALS), frontotemporal dementia, and cognitive decline related to prior stroke.
The model was trained on proteomic profiles from more than 17,000 individuals, making it one of the largest datasets ever used for this purpose. Lead researcher Jacob Vogel said the model could outperform previous diagnostic approaches by identifying both shared and unique protein patterns across diseases.
First author Lijun An noted that some individuals clinically diagnosed with one condition showed protein profiles more consistent with other neurodegenerative disorders, revealing biological insights that current clinical methods may miss.
Although the technology is still in the research phase and not yet ready for routine clinical use, it represents a significant step toward non-invasive, early, and cost-effective diagnosis of complex brain disorders. If successfully translated into clinical practice, the system could reduce reliance on expensive neuroimaging and invasive procedures, helping clinicians make earlier and more accurate diagnoses.
Senior Reporter/Editor
Bio: Ugochukwu is a freelance journalist and Editor at AIbase.ng, with a strong professional focus on investigative reporting. He holds a degree in Mass Communication and brings extensive experience in news gathering, reporting, and editorial writing. With over a decade of active engagement across diverse news outlets, he contributes in-depth analytical, practical, and expository articles exploring artificial intelligence and its real-world impact. His seasoned newsroom experience and well-established information networks provide AIbase.ng with credible, timely, and high-quality coverage of emerging AI developments.