Linking dynamic connectivity states to cognitive decline and anatomical changes in Alzheimer’s disease

Alterations in brain connectivity provide early indications of neurodegenerative diseases disease (AD). Here, we present a novel framework that integrates a Hidden Markov Model the architecture of a convolutional neural network (CNN) to analyze dynamic functional connectivity resting-state functional magnetic resonance imaging (rs-fMRI). Our unsupervised approach captures connectivity states in a large cohort of subjects spanning the Alzheimer's disease continuum, including controls, individuals with mild cognitive impairment (MCI), and patients with clinically diagnosed We propose a deep neural model with embedded HMM dynamics to identify stable recurring from resting-state fMRI. These states exhibit distinct connectivity patterns and are differentially across the Alzheimer's disease continuum. Our analysis shows that the fraction of time each state systematically with disease severity, highlighting dynamic network alterations that track neurodegeneration. Our findings suggest that the disruption of dynamic connectivity patterns in AD may follow trajectory, where early shifts toward integrative network states give way to reduced connectivity as the disease progresses. This framework offers a promising tool for early diagnosis and monitoring and may have broader applications in the study of other neurodegenerative conditions.