Year: 2024
Type: conference-paper
Abstract: Accurately characterizing progression states is crucial for developing effective therapeutic interventions. Various factors contribute to this challenge, including the need for precise methods that can account for the complex nature of HD progression. This study aims to address this gap by leveraging the concept of the brain’s biological age as a foundation for a data-driven clustering method to delineate various states of progression. Brain age, influenced by somatic expansion and its impact on brain volumes, offers a promising avenue for stratification, by stratifying subgroups and determining the optimal timing for interventions. To achieve this, data from 953 participants (including more than 5000 scans) across diverse cohorts, including PREDICT-HD, TRACK-HD, and IMAGE-HD, were analysed. Brain age was computed using Gaussian Processes Regression, with brain volumetric data as independent variable and age as dependent variable, and participants were categorized into four groups based on CAG and age product score. Unsupervised k-means clustering with brain-predicted age difference (brain-PAD) was then employed to identify distinct progression states. The analysis revealed significant disparities in brain age between HD participants and controls, with these differences becoming more pronounced as the disease progressed. Brain-PAD demonstrated a correlation with disease severity, effectively identifying five distinct progression states characterized by significant longitudinal disparities. These findings highlight the potential of brain-PAD in capturing HD progression states, thereby enhancing prognostic methodologies and providing valuable insights for future clinical trial designs and interventions.
Language: English
Subfield: Cellular and Molecular Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: gold
OpenAlex ID: W4402374384