Research map / Probabilistic and scientific modeling / Molecules and proteins
Explainable Brain Age Prediction using coVariance Neural Networks
Saurabh Sihag, Gonzalo Mateos, Corey McMillan, Alejandro Ribeiro
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use VNNs trained on healthy-control chronological age instead of randomly initialized VNNs (ablation) | VNN brain age · OASIS-3 regional residuals AD+ vs HC | robustness of anatomical interpretability | Improved |
| Use randomly initialized VNNs instead of trained ones (ablation) | VNN brain age · OASIS-3 correlation of regional residuals with CDR | consistency of correlation | Hurt |
| Estimate anatomical covariance from HC group only instead of combined HC and AD+ (ablation) | VNN brain age · OASIS-3 Delta-Age HC vs AD+ | group difference in Delta-Age | Mixed |
| Estimate covariance matrix from a variable composition of HC and AD+ individuals (ablation) | VNN brain age · OASIS-3 regional profile for Delta-Age | stability of regional profile | No clear effect |
| Evaluate on independent ADNI-1 dataset with VNNs trained on OASIS-3 | VNN brain age · ADNI-1 | Delta-Age by cohort: 0 \pm 3.92 -> 3 \pm 5.74 -> 4.49\pm 5.34 | Improved |
| Compare Delta-Age of AD+ against HC | VNN brain age · OASIS-3 | Delta-Age (years): 0\pm 2.83 -> 3.54\pm 4.49 | Improved |
| Higher dementia severity (CDR sum of boxes > 4 vs <= 4) | VNN brain age · OASIS-3 AD+ | mean Delta-Age (years): 2.42 -> 6.04 | Improved |
| Evaluate on complete dataset rather than held-out test set | VNN chronological age prediction · OASIS-3 HC | MAE (years): 5.82 \pm 0.13 -> 5.44\pm 0.18 | No clear effect |
Closest papers by meaning
- Healthy Cognitive Aging: A Hybrid Random Vector Functional-Link Model for the Analysis of Alzheimer’s Disease (AAAI 2017 · similarity 0.84)
- CortiLife: A Unified Framework for Cortical Representation Learning across the Lifespan (ICLR 2026 · similarity 0.83)
- BrainODE: Neural Shape Dynamics for Age- and Disease-aware Brain Trajectories (NeurIPS 2025 · similarity 0.83)
- Systematic Bias of Machine Learning Regression Models and Correction (TPAMI 2025 · similarity 0.82)
- Covariance Scattering Transforms (AAAI 2026 · similarity 0.82)
- Adaptive Shrinkage Estimation for Personalized Deep Kernel Regression in Modeling Brain Trajectories (ICLR 2025 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
