Functional MRI and ApoE4 genotype for predicting cognitive decline in amyloid-positive individuals

Predicting early Alzheimer's with blood biomarkers and clinical features

Alzheimer's disease (AD) is an incurable neurodegenerative disorder that leads to dementia. This study employs explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from Alzheimer's Disease Neuroimaging Initiative (ADNI). Analyzing 623 ADNI participants, we found that the Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieved exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, we achieved very good performance (AUC = 0.65, AUC = 0.63, respectively). Using SHapley Additive exPlanations (SHAP), we identified significant features, potentially serving as AD biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. In summary, this genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods.

Gray matter reserve determines glymphatic system function in young-onset Alzheimer's disease: Evidenced by DTI-ALPS and compared with age-matched controls

BACKGROUND

The diffusion tensor imaging analysis along the perivascular space (ALPS)-index can be used to model the glymphatic system in vivo.

AIM

This study explores putative mechanisms between prediction of ALPS-index and cognitive outcomes in young-onset Alzheimer's disease (YOAD) and age-matched controls (CTLs) and analyzes whether the link was mediated by the integrity of ALPS-index-anchored cerebral gray matter (GM).

METHODS

We enrolled 130 patients with YOAD and 137 CTLs. All participants underwent three-dimensional T1 -weighted MRI, diffusion tensor imaging and cognitive tests. We constructed GM regions correlated with the ALPS-index in the YOAD and CTL groups. For the GM regions significantly correlated with the ALPS-index and cognitive measures, we extracted a 4-mm radius sphere. In the YOAD and CTL groups, we used mediator analysis to explore the ALPS-index as predictor, GM partitions as mediators, and significant cognitive test scores as outcomes.

RESULTS

Patient group had significantly lower ALPS-index. The ALPS-index was associated with GM volume in the cerebellar gray, dorsolateral prefrontal, thalamus, superior frontal, amygdala and hippocampus, and these coherent regions coincided with those showing GM atrophy in the YOAD group. Mediation analysis of the YOAD group suggested that the relationships between the ALPS-index and cognitive performance were fully mediated by the integrity of ALPS-index coherent GM areas.

DISCUSSION

Reserved GM mediates the link between the glymphatic system and cognition. Our findings suggest that GM integrity rather than the glymphatic system could serve as a direct cognitive test scores predictor in patients with YOAD.