Dataset Information

Functional connectome fingerprint of sleep quality in insomnia patients: Individualized out-of-sample prediction using machine learning.

ABSTRACT: OBJECTIVES:Insomnia disorder has been reclassified into short-term/acute and chronic subtypes based on recent etiological advances. However, understanding the similarities and differences in the neural mechanisms underlying the two subtypes and accurately predicting the sleep quality remain challenging. METHODS:Using 29 short-term/acute insomnia participants and 44 chronic insomnia participants, we used whole-brain regional functional connectivity strength to predict unseen individuals' Pittsburgh sleep quality index (PSQI), applying the multivariate relevance vector regression method. Evaluated using both leave-one-out and 10-fold cross-validation, the pattern of whole-brain regional functional connectivity strength significantly predicted an unseen individual's PSQI in both datasets. RESULTS:There were both similarities and differences in the regions that contributed the most to PSQI prediction between the two groups. Further functional connectivity analysis suggested that between-network connectivity was re-organized between short-term/acute insomnia and chronic insomnia. CONCLUSIONS:The present study may have clinical value by informing the prediction of sleep quality and providing novel insights into the neural basis underlying the heterogeneity of insomnia.

SUBMITTER: Ma X

PROVIDER: S-EPMC7522804 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Functional connectome fingerprint of sleep quality in insomnia patients: Individualized out-of-sample prediction using machine learning.

Ma Xiaofen X Wu Dongyan D Mai Yuanqi Y Xu Guang G Tian Junzhang J Jiang Guihua G

NeuroImage. Clinical 20200918

<h4>Objectives</h4>Insomnia disorder has been reclassified into short-term/acute and chronic subtypes based on recent etiological advances. However, understanding the similarities and differences in the neural mechanisms underlying the two subtypes and accurately predicting the sleep quality remain challenging.<h4>Methods</h4>Using 29 short-term/acute insomnia participants and 44 chronic insomnia participants, we used whole-brain regional functional connectivity strength to predict unseen indivi ...[more]

PMID: 32980600

Similar Datasets

Project description:BackgroundMillions of COVID-19 survivors experience a wide range of long-term symptoms after acute infection, giving rise to serious public health concerns. To date, few risk factors for post-COVID-19 conditions have been determined. This study evaluated the role of pre-infection sleep quality/duration and insomnia severity in the incidence of long-term symptoms after COVID-19.Material and methodsThis prospective study involved two assessments (April 2020 and 2022). At the baseline (April 2020), sleep quality/duration and insomnia symptoms in participants without current/prior SARS-CoV-2 infection were measured using the Pittsburgh Sleep Quality Index (PSQI) and the Insomnia Severity Index (ISI). At the follow-up (April 2022), we asked a group of COVID-19 survivors to retrospectively evaluate the presence of twenty-one symptoms (psychiatric, neurological, cognitive, bodily, and respiratory) that have been experienced one month (n = 713, infection in April 2020-February 2022) and three months after COVID-19 (n = 333, infection in April 2020-December 2021). In April 2022, participants also reported how many weeks passed to fully recover from COVID-19. Zero-inflated negative binomial models were used to estimate the effect of previous sleep on the number of long-term symptoms. Binomial logistic regressions were performed to evaluate the association between sleep variables, the incidence of each post-COVID-19 symptom, and the odds of recovery four/twelve weeks after infection.ResultsAnalyses highlighted a significant effect of pre-infection sleep on the number of symptoms one/three months after COVID-19. Previous higher PSQI and ISI scores, and shorter sleep duration significantly increased the risk of almost every long-term symptom at one/three months from COVID-19. Baseline sleep problems were also associated with longer recovery times to return to the pre-infection daily functioning level after COVID-19.ConclusionsThis study suggested a prospective dose-dependent association between pre-infection sleep quality/quantity and insomnia severity with the manifestation of post-COVID-19 symptoms. Further research is warranted to determine whether preventively promoting sleep health may mitigate the COVID-19 sequelae, with substantial public health and societal implications.

Dataset Information

Functional connectome fingerprint of sleep quality in insomnia patients: Individualized out-of-sample prediction using machine learning.

Publications

Functional connectome fingerprint of sleep quality in insomnia patients: Individualized out-of-sample prediction using machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets