Nature11/09 10:58 UTC
Single-cell machine learning uncovers genetically anchored, cell-type specific programs of Alzheimer’s disease
The authors say univariate analyses alone cannot resolve multivariate disease-associated structure. They develop TriSCOPE, a machine learning approach that identifies gene programs specific to individual brain cell types in Alzheimer's disease.
Read the original →Indiana Daily Student11/10 13:00 UTC
IU, Meta partner on AI research in dementia, maternal care and early learning
IU researchers will gain access to Meta's AI models through a $2 million initiative.
Read the original →Bioengineer.org11/10 11:38 UTC
AI Model Distinguishes NPH From Alzheimer’s on Brain MRI
A study in Frontiers in Neuroinformatics evaluates an attention-enhanced deep learning framework. It achieves 93.33% image-level accuracy in distinguishing idiopathic normal pressure hydrocephalus.
Read the original →Bioengineer.org11/09 08:07 UTC
AI reads brain scans for Alzheimer’s signs, but a sweeping review urges caution
A systematic review and meta-analysis of 176 records examined automated MRI models for medial temporal and Alzheimer-related neurodegeneration. The models report pooled accuracy near 0.9.
Read the original →Bioengineer.org10/29 07:00 UTC
Machine learning finds Non-APOE gene signals too weak to predict Alzheimer’s
A Korean two-stage sequencing study found that Non-APOE candidate variants added almost no predictive power once leakage and APOE effects were removed.
Read the original →