A MACHINE LEARNING MODEL FOR THE PROGNOSIS OF ALZHEIMER’S DISEASE DEMENTIA AT THE MILD COGNITIVE IMPAIRMENT STAGE USING MITOCHONDRIAL METHYLCYTOSINES AS NOVEL BLOOD‐BASED BIOMARKERS
Jose Luis Mosquera, Marta Blanch, Beatriz Fontal, Pau Martí, Paula Ferrer, Carla Trapero, Nuria Rojo, Inma Rico, Jaume Campdelacreu, Joan Bello López, Alberto Lleo, Juan Fortea, Pablo Martinez‐Lage, Adrià Tort‐Merino, Raquel Sanchez‐Valle, Carlos Cruchaga, Christopher J Fowler, Simon M Laws, Courosh · 2025
Read A MACHINE LEARNING MODEL FOR THE PROGNOSIS OF ALZHEIMER’S DISEASE DEMENTIA AT THE MILD COGNITIVE IMPAIRMENT STAGE USING MITOCHONDRIAL METHYLCYTOSINES AS NOVEL BLOOD‐BASED BIOMARKERS by Jose Luis Mosquera, Marta Blanch, Beatriz Fontal, Pau Martí, Paula Ferrer, Carla Trapero, Nuria Rojo, Inma Rico, Jaume Campdelacreu, Joan Bello López, Alberto Lleo, Juan Fortea, Pablo Martinez‐Lage, Adrià Tort‐Merino, Raquel Sanchez‐Valle, Carlos Cruchaga, Christopher J Fowler, Simon M Laws, Courosh (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11714325.txt.
Description
Mosquera and a large team (2025) built a machine learning model that forecasts which patients with mild cognitive impairment will progress to Alzheimer's dementia. The model uses a blood-based signal: the methylation pattern of mitochondrial DNA, which earlier work found altered in Alzheimer's brains and in patients' blood. The team measured over 200 methylation features in 600 people recruited across several cohorts, added plain clinical variables, and trained the model without using brain scans.
On held-out test data, the model classified people into healthy, stable impairment, and progressing impairment with about 83 percent accuracy. It was especially good at catching the progressors, with high sensitivity, and the authors say it can flag progression up to 14 years before dementia signs appear. They present it as a promising, low-burden prognostic tool for the clinic.
Catalog record
| CREATOR | Jose Luis Mosquera, Marta Blanch, Beatriz Fontal, Pau Martí, Paula Ferrer, Carla Trapero, Nuria Rojo, Inma Rico, Jaume Campdelacreu, Joan Bello López, Alberto Lleo, Juan Fortea, Pablo Martinez‐Lage, Adrià Tort‐Merino, Raquel Sanchez‐Valle, Carlos Cruchaga, Christopher J Fowler, Simon M Laws, Courosh |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |