Research map / Probabilistic and scientific modeling / Dynamical systems
Infra-slow brain dynamics as a marker for cognitive function and decline
Shagun Ajmera, Shreya Rajagopal, Razi Rehman, Devarajan Sridharan
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 |
|---|---|---|---|
| keep only slow (<1 Hz) GPFA dimensions (ablation) | GPFA time series classifier · HCP task classification | median accuracy: 97.8% -> 98% | No clear effect |
| use oscillation power spectra instead of latent time series (ablation) | GPFA classifier · HCP task classification | median accuracy: 97.8% -> 57.8% | Hurt |
| recursive feature elimination on PC+LC features (ablation) | SVM MCI classifier · MCIc vs MCIs | accuracy: 63.6% -> 73.6% | Improved |
| recursive feature elimination on oscillation spectra (ablation) | SVM MCI classifier · MCIc vs MCIs | accuracy: 65.1% -> 67.2% | Improved |
| use lagged covariance instead of partial correlation features (ablation) | SVM MCI classifier · MCIc vs MCIs | accuracy: 61.2% -> 71.0% | Improved |
| combine PC and LC features (ablation) | SVM MCI classifier · MCIc vs MCIs | accuracy: 71.0% -> 63.6% | Hurt |
| use PC+LC features instead of oscillation spectra for CDR-SOB regression (ablation) | lasso regression · CDR-SOB prediction | correlation r: 0.56 -> 0.34 | Hurt |
| increase cross-validation folds k up to leave-one-out (ablation) | lasso CDR-SOB regression · CDR-SOB prediction | prediction accuracy | Improved |
| use different 90-node parcellation (ablation) | GPFA task classification · HCP task classification | accuracy | No clear effect |
| replace GPFA with ROI selection or PCA (ablation) | dimensionality reduction for task classification · HCP task classification | accuracy | Improved |
| slow vs fast timescale latent dimensions | GPFA latents · HCP tasks | synchronization index | Improved |
Closest papers by meaning
- A state-space model for inferring effective connectivity of latent neural dynamics from simultaneous EEG/fMRI (NeurIPS 2019 · similarity 0.85)
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG (NeurIPS 2026 · similarity 0.84)
- BrainLM: A foundation model for brain activity recordings (ICLR 2024 · similarity 0.84)
- FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model (NeurIPS 2026 · similarity 0.82)
- BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction (NeurIPS 2026 · similarity 0.82)
- Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens (NeurIPS 2025 · similarity 0.82)
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.
