We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Population heterogeneity in clinical cohorts affects the predictive accuracy of brain imaging.
- Authors
Benkarim, Oualid; Paquola, Casey; Park, Bo-yong; Kebets, Valeria; Hong, Seok-Jun; Vos de Wael, Reinder; Zhang, Shaoshi; Yeo, B. T. Thomas; Eickenberg, Michael; Ge, Tian; Poline, Jean-Baptiste; Bernhardt, Boris C.; Bzdok, Danilo
- Abstract
Brain imaging research enjoys increasing adoption of supervised machine learning for single-participant disease classification. Yet, the success of these algorithms likely depends on population diversity, including demographic differences and other factors that may be outside of primary scientific interest. Here, we capitalize on propensity scores as a composite confound index to quantify diversity due to major sources of population variation. We delineate the impact of population heterogeneity on the predictive accuracy and pattern stability in 2 separate clinical cohorts: the Autism Brain Imaging Data Exchange (ABIDE, n = 297) and the Healthy Brain Network (HBN, n = 551). Across various analysis scenarios, our results uncover the extent to which cross-validated prediction performances are interlocked with diversity. The instability of extracted brain patterns attributable to diversity is located preferentially in regions part of the default mode network. Collectively, our findings highlight the limitations of prevailing deconfounding practices in mitigating the full consequences of population diversity. Brain-imaging research enjoys increasing adoption of supervised machine learning for single-subject disease classification. This study explores the contribution of diversity-aware machine learning models to tracking, unpacking and understanding out-of-distribution generalization in large-scale neuroimaging datasets, and shows that population diversity is a key factor contributing to generalization performance.
- Subjects
BRAIN imaging; SUPERVISED learning; DEFAULT mode network; LARGE-scale brain networks; DEMOGRAPHIC characteristics; MODULATIONAL instability
- Publication
PLoS Biology, 2022, Vol 20, Issue 4, p1
- ISSN
1544-9173
- Publication type
Article
- DOI
10.1371/journal.pbio.3001627