EEG microstate changes track white matter hyperintensity burden and dementia status

Patients with white matter hyperintensity (WMH) show electroencephalography (EEG) microstate C temporal parameter drops and fewer transitions toward C (P<0.001); machine learning separated WMH with dementia from WMH without dementia with 76.67% accuracy and AUC 0.84.

• Cross-sectional study of 90 subjects: 30 WMH with dementia, 30 WMH without dementia, and 30 age- and sex-matched healthy controls.
• Temporal parameters of microstates A and B and transitions toward them correlated positively with WMH volume and negatively with MMSE score; microstate D showed opposite correlations.
• Classification was highest for WMH without dementia versus healthy controls (logistic regression accuracy 79.17%, AUC 0.86) and lowest for WMH with dementia versus healthy controls (support vector machine accuracy 68.33%, AUC 0.77).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.