An AI model detects several neurodegenerative diseases from a single blood sample, researchers at Lund University in Sweden say.
Neurodegenerative diseases are conditions in which brain cells progressively deteriorate, such as Alzheimer’s and Parkinson’s.
Different conditions can show similar symptoms, making them hard to distinguish, especially in the early stages of cognitive decline.
A patient may also have multiple overlapping disease processes in the brain at the same time.
The new model was trained on protein measurements from more than 17,000 patients and control participants, using data from what its creators describe as the world’s largest proteomics database for neurodegenerative diseases.
Jacob Vogel, assistant professor, head of a research group and part of the strategic research area MultiPark at Lund University, said: “Our hope is to be able to accurately diagnose several diseases at once with a single blood test in the future.”
Researchers Vogel and Lijun An, together with colleagues from the Swedish BioFINDER study and the Global Neurodegenerative Proteomics Consortium, developed the AI model.
Proteomics is the large-scale study of proteins in biological samples such as blood, which can reveal patterns that offer clues about how diseases develop.
Using advanced statistical learning methods and a process known as joint learning, in which the AI analyses data across multiple conditions at the same time, the model identified a set of proteins that form a general pattern for diseases involving brain degeneration.
The researchers said the model outperformed previous models while also diagnosing five dementia-related conditions: Alzheimer’s disease, Parkinson’s disease, ALS, a disease that attacks nerve cells controlling movement, frontotemporal dementia, a form of dementia affecting the front and sides of the brain, and previous stroke.
The researchers said the results were validated across multiple independent datasets.
Lijun An, the study’s first author, said: “We also found that the protein profile predicted cognitive decline better than the clinical diagnosis did, and it seems like individuals with the same clinical diagnosis may have different underlying biological subtypes.”
Many individuals diagnosed with Alzheimer’s disease showed a protein pattern more similar to other brain disorders.
Vogel said: “This could mean they have more than one underlying disease, that Alzheimer’s can develop in multiple ways, or that the clinical diagnosis is incorrect.
“However, I don’t think current protein measurements from blood samples will be sufficient on their own to diagnose multiple diseases, we need to refine the method and combine it with other clinical diagnostic tools.”
He added that diagnostics is not the only potential application of the model. Many of the proteins that contributed to it point to areas where follow-up studies could improve understanding of the biological processes driving these neurodegenerative conditions.
The next step is to include more proteomic markers using advanced methods such as mass spectrometry, a technique that identifies and measures molecules by their mass, to identify patterns unique to each disease.
Vogel said: “We hope to inch closer toward a blood test that can make reliable diagnosis across disorders without aid from other clinical instruments.”
