Connectome-Based Predictive Models Optimized for Sleep Differentiate Patients With Depression From Psychiatrically Healthy Controls
Biological Psychiatry: Cognitive Neuroscience and Neuroimaging · 2025
DOI: 10.1016/j.bpsc.2025.10.002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 2025. Verfasst von Anurima Mummaneni und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, University of California, Los Angeles, Los Angeles, California; Department of Psychiatry and Biobehavioral Sciences, Univer…. Hauptthemen laut MEDLINE: Connectome, Major Depressive Disorder, Sleep, Brain. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIMH NIH HHS, NICHD NIH HHS, National Institutes of Health.
Themen: Depression
Abstract (Originalsprache)
BACKGROUND: It is unknown whether brain-based predictive models derived from sleep features are useful for the clinical diagnosis of major depressive disorder (MDD). METHODS: Using resting-state functional magnetic resonance imaging data from the curated ABCD (Adolescent Brain Cognitive Development) Study Data Release 3.0, we trained a connectome-based predictive model (CPM) on 35,778 pairwise connections (Pearson's r) from 2349 (237 participants with at least 1 psychiatric disorder and 2112 control participants) participants ages 11 to 12 to predict sleep duration (measured from a Fitbit tracker). Linear regression models were used to compare the predicted values from these CPMs with self-reported sleep duration and diagnostic group status in an independent cohort of 78 participants (57 participants with MDD and 21 control participants) ages 14 to 18. RESULTS: The ABCD-based CPM predicted self-reported sleep duration in the independent cohort of participants with MDD (partial r = 0.332, p = .009). Even though self-reported sleep duration did not significantly differ between diagnostic groups (t75 = 0.13, p = .90), the ABCD-based CPM successfully distinguished between diagnostic groups (partial r = 0.334, p < .001), and CPM-predicted sleep durations correlated with depression symptom severity (partial r = 0.294, p < .001). These diagnostic group differences were driven primarily by patterns of hypoconnectivity within various resting-state networks (including the default mode, frontoparietal, motor, and subcortical networks). CONCLUSIONS: CPMs trained to predict objective sleep duration are robust and generalizable. Intrinsic functional connectivity differences between clinically depressed and psychiatrically healthy adolescents are detectable by CPMs optimized for sleep prediction, underscoring the shared neural bases between sleep health and depression. Future work will test whether sleep-based CPMs are predictive of clinical course and if they generalize to other disorders beyond depression.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Psychology, University of California, Los Angeles, Los Angeles, California; Department of Psychiatry and Biobehavioral Sciences, University of California, Los Angeles, Los Angeles, California.
- Department of Psychology, University of Oregon, Eugene, Oregon.
- Department of Psychology, University of California, Los Angeles, Los Angeles, California; Department of Psychiatry and Biobehavioral Sciences, University of California, Los Angeles, Los Angeles, California. Electronic a…
Förderung
- NIMH NIH HHS
- NICHD NIH HHS
- National Institutes of Health
Zitieren
APA
Mummaneni, A., Amir, C., Allen, N. B., & Ho, T. C. (2025). Connectome-Based Predictive Models Optimized for Sleep Differentiate Patients With Depression From Psychiatrically Healthy Controls. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging. https://doi.org/10.1016/j.bpsc.2025.10.002
Vancouver
Mummaneni A, Amir C, Allen NB, Ho TC. Connectome-Based Predictive Models Optimized for Sleep Differentiate Patients With Depression From Psychiatrically Healthy Controls. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging. 2025. doi:10.1016/j.bpsc.2025.10.002
BibTeX
@article{Mummaneni2025,
author = {Mummaneni, Anurima and Amir, Carolyn and Allen, Nicholas B and Ho, Tiffany C},
title = {Connectome-Based Predictive Models Optimized for Sleep Differentiate Patients With Depression From Psychiatrically Healthy Controls},
journal = {Biological Psychiatry: Cognitive Neuroscience and Neuroimaging},
year = {2025},
doi = {10.1016/j.bpsc.2025.10.002}
}
EUVIMED