Incorporating Multi-threshold Polygenic Risk in Hippocampal-based Normative Models Improves Cognitive Decline Prediction
Janahi, M.; Altmann, A.; Mokrab, Y.; Barkhof, F.; Oxtoby, N.; Lorenzini, L.
Show abstract
Predicting cognitive decline using MRI measures of brain volume is challenging. Normative models capture the evolution of biomarkers over time in a healthy group, quantifying an individuals deviation from that norm. Here, we improve the precision of normative models for hippocampal volume, a key cognitive biomarker, by integrating multi-threshold polygenic scores (PGS) that capture genetic predisposition to its variability. We built Gaussian Process Regression (GPR) models on genetic, imaging, and demographic data from 23,997 UK Biobank (UKBB) participants, validating on 3,000 out-of-sample participants from the Alzheimers Disease Neuroimaging Initiative (ADNI) and the European Prevention of Alzheimers Disease (EPAD) cohorts. The genetically-informed models improved associations significantly across five experimental designs and 13 key neurocognitive measures, including Mini-Mental State Examination (MMSE), Clinical Dementia Rating (CDR), Alzheimers Disease Assessment Scale (ADAS), and importantly, improving prediction of future cognitive decline. These findings underscore the value of integrating multi-threshold PGS with neuroimaging-based predictive models for improving prognostication in neurodegenerative diseases.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- AI-driven fusion of neurological work-up for assessment of biological Alzheimer’s disease 96%
- Individual bioenergetic capacity as a potential source of resilience to Alzheimer’s disease 95%
- Lifetime brain atrophy estimated from a single MRI: measurement characteristics and genome-wide correlates 94%
Similar papers in this journal
- WMH-DualTasker: A weakly-supervised deep learning model for automated white matter hyperintensities segmentation and visual rating prediction 95%
- Cross-dataset Evaluation of Dementia Longitudinal Progression Prediction Models 94%
- Evaluation of ComBat harmonization for reducing across-tracer biases in regional amyloid PET analyses 94%
Similar papers in this journal
- AI reveals insights into link between CD33 and cognitive impairment in Alzheimer's Disease 93%
- A novel classification framework for genome-wide association study of whole brain MRI images using deep learning 93%
- Addressing biases in gene-set enrichment analysis: a case study of Alzheimer's Disease 93%
Similar papers in this journal
- Improving genetic risk modeling of dementia from real-world data in underrepresented populations 95%
- Detecting the effect of genetic diversity on brain composition in an Alzheimer's disease mouse model 93%
- Learning fast and fine-grained detection of amyloid neuropathologies from coarse-grained expert labels 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.