Inflammation and Brain Network Data for Female Nurses with Shift Work Sleep Disorder

Fifty female nurses with shift work sleep disorder and 50 healthy controls underwent clinical assessments, inflammatory marker quantification, and resting-state fMRI. The study links elevated inflammatory markers like IL-6 and IFN-γ to specific disruptions in brain network topology, which correlate with symptoms like poor sleep and anxiety. A support vector classifier model built on these multimodal features achieved 90% accuracy in classifying SWSD.

Use Cases

• Train machine learning classifiers for sleep disorder diagnosis based on multimodal clinical and neuroimaging features.
• Analyze associations between specific inflammatory markers (e.g., IL-6, IFN-γ) and graph theory metrics of brain network topology.
• Investigate spatial correlations between brain network alterations and gene expression patterns using imaging transcriptomics data.
• Conduct mediation analysis to model pathways linking systemic inflammation, brain network disruption, and clinical symptom severity.

Strengths

• Includes a matched case-control cohort of 100 participants (50 SWSD, 50 healthy controls).
• Multimodal data integrates clinical symptoms, quantified inflammatory markers, and resting-state fMRI-derived graph theory metrics.
• The associated machine learning model reported a classification accuracy of 90%.
• Data is shared under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is small in scale (851.7 KB), suggesting it contains summary or processed results rather than raw data.

Provenance

Source

figshare, authored by Si-Yu Gu.

Collection Method

Data was collected from clinical assessments, blood tests for inflammatory markers, and resting-state fMRI scans analyzed with graph theory.

Freshness

Last updated 2026-06-02 05:26:47; freshness should be verified.