Machine Learning for Brain Health Across the Lifespan
The lab builds machine learning frameworks to model brain structure in health and disease across the lifespan, drawing on large-scale, multimodal neuroimaging datasets to capture heterogeneity in structure, function, and disease progression. A central emphasis is on unsupervised and semi-supervised methods — normative modeling, non-negative matrix factorization (NMF), and deep generative models — to uncover latent patterns and subtypes tied to specific outcomes or disease states.
People and Publications
- Tom Earnest — biological staging of tau pathology in Alzheimer’s disease (Alzheimer’s & Dementia, 2024).
- Gordon An — characterization of Alzheimer’s disease heterogeneity in clinical cohorts (Alzheimer’s Research & Therapy, 2025).
- Sayantan Kumar (alum) — Improving Normative Modeling for Multi-modal Neuroimaging Data using mixture-of-product-of-experts variational autoencoders and Normative Modeling using Multimodal Variational Autoencoders to Identify Abnormal Brain Structural Patterns in Alzheimer Disease.
- Robert J. Jirsaraie (alum) — A systematic review of multimodal brain age studies: Uncovering a divergence between model accuracy and utility.
- Nazeri et al. — white matter development in neonates (Neuron, 2022; external collaborator, not a current lab member).
Related GitHub Projects
This repository develops data-driven biological staging models for Alzheimer's disease by combining amyloid and tau PET analyses with non-negative matrix factorization (NMF) to identify reproducible spatial pathology factors.
It includes preprocessing workflows, shared NMF factors, projection utilities for new datasets, and staging code to derive amyloid and tau severity labels for external cohorts.
This repository contains code for predicting future cognitive impairment in preclinical Alzheimer's disease using multimodal amyloid PET and MRI features across multiple cohorts.
It includes data processing, subject selection, machine learning training and evaluation workflows, and figure/table generation for the Neurobiology of Aging 2026 study.
This repository evaluates variability in AT(N) biomarker operationalizations for predicting cognition in Alzheimer's disease using multimodal imaging and clinical data.
It provides reproducible modeling scripts, experiment pipelines, and figure-generation utilities for cross-validated regression and SVM analyses.