Article Dans Une Revue Scientific Reports Année : 2025

A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity

Résumé

Functional connectivity holds promise as a biomarker of schizophrenia. Yet, the high dimensionality of predictive models trained on functional connectomes, combined with small sample sizes in clinical research, increases the risk of overfitting. Recently, low-dimensional representations of the connectome such as macroscale cortical gradients and gradient dispersion have been proposed, with studies noting consistent gradient and dispersion differences in psychiatric conditions. However, it is unknown which of these derived measures has the highest predictive capacity and how they compare to raw functional connectivity specifically in the case of schizophrenia. Our study evaluates which connectome features derived from resting state functional MRI -functional connectivity, gradients, or gradient dispersion -best identify schizophrenia. To this end, we leveraged data of 936 individuals from three large open-access datasets: COBRE, LA5c, and SRPBS-1600. We developed a pipeline which allows us to aggregate over a million different features and assess their predictive potential in a single, computationally efficient experiment. We selected top 1% of features with the largest permutation feature importance and trained 13 classifiers on them using 10-fold cross-validation. Our findings indicate that functional connectivity outperforms its low-dimensional derivatives such as cortical gradients and gradient dispersion in identifying schizophrenia (Mann-Whitney test conducted on test accuracy: connectivity vs. 1st gradient: U = 142, p < 0.003; connectivity vs. neighborhood dispersion: U = 141, p = 0.004). Additionally, we demonstrated that the edges which contribute the most to classification performance are the ones connecting primary sensory regions. Functional connectivity within the primary sensory regions showed the highest discrimination capabilities between subjects with schizophrenia and neurotypical controls. These findings along with the feature selection pipeline proposed here will facilitate future inquiries into the prediction of schizophrenia subtypes and transdiagnostic phenomena.

Functional connectivity holds promise as a potential biomarker for schizophrenia 1-5 , as evidenced by a robust body of fMRI literature that highlights distinct functional profiles between people with schizophrenia and neurotypical individuals. Prior studies have reported lower connectivity across regions, reduced smallworldness of the resting state networks, and lower functional network segregation 5-7 . However, when the goal is to predict clinical status using the entire functional connectome as features for model training, the resulting model becomes high-dimensional and overly complex. This high dimensionality, coupled with small sample sizes in clinical research, increases the risk of overfitting 8-10 .

Recently, low-dimensional representations of the connectome such as macroscale cortical gradients 11,12 and gradient dispersion 13,14 have been proposed. The gradients are derived from functional connectivity matrices

Fichier principal
Vignette du fichier
Shevchenko et al. 2025 - A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity.pdf (5.97 Mo) Télécharger le fichier
Origine Publication financée par une institution
licence

Dates et versions

hal-04911960 , version 1 (25-01-2025)

Licence

Identifiants

Citer

Victoria Shevchenko, R Austin Benn, Robert Scholz, Wei Wei, Carla Pallavicini, et al.. A comparative machine learning study of schizophrenia biomarkers derived from functional connectivity. Scientific Reports, 2025, 15, ⟨10.1038/s41598-024-84152-2⟩. ⟨hal-04911960⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More