Dynamic functional connectivity changes in noise-induced hearing loss: A resting-state fMRI study with machine...

Area of Science:

• Neuroscience
• Cognitive Science
• Medical Imaging

Background:

• Noise-induced hearing loss (NIHL) negatively impacts brain health and cognition.
• Dynamic functional connectivity (dFC) analysis is a promising tool for studying whole-brain activity.
• Previous research has underexplored dFC in the context of NIHL.

Purpose of the Study:

• To investigate abnormal temporal variability in whole-brain functional connectivity in patients with NIHL using dFC analysis.
• To identify specific dFC patterns associated with NIHL.
• To assess the diagnostic potential of dFC features in NIHL.

Main Methods:

• Observational study involving 58 patients with NIHL and 42 healthy controls.
• Resting-state functional magnetic resonance imaging (rs-fMRI) was utilized.
• Sliding window approach and k-means clustering were employed to analyze dFC and identify connectivity states.
• Support vector machine (SVM) classifiers were constructed using features identified by false discovery rate (FDR) correction and least absolute shrinkage and selection operator (LASSO).

Main Results:

• Patients with NIHL showed decreased dFC between the right supplementary motor area and bilateral cuneus.
• Increased dFC was observed between the supplementary motor area and the left inferior parietal gyrus in NIHL patients.
• SVM classifiers achieved high accuracy (82.5% with FDR, 96.8% with LASSO) in distinguishing NIHL patients from controls based on dFC features.

Conclusions:

• Abnormal dFC patterns are present in patients with NIHL.
• dFC analysis provides valuable insights into the neuropathological mechanisms of NIHL.
• dFC features show potential for accurate diagnosis of NIHL.