Distinct features of EEG microstates in autism spectrum disorder revealed by meta-analysis: the contribution of individual age to heterogeneity across studies

Background and purpose: Electroencephalographic (EEG) microstates, as quasi-stable scalp EEG spatial patterns, are characterized by their high temporal resolution, making them a potentially powerful approach for studying the function of large-scale brain networks. A substantial body of research has demonstrated that abnormalities in the function or structure of large-scale brain networks are closely related to many characteristics of autism spectrum disorder (ASD). Investigating the EEG microstate features of individuals with autism can help reveal the nature of autism. To date, numerous studies have observed unique resting-state microstate patterns in individuals with autism. However, the results of these studies have not been consistent. Therefore, the present study aims to assess the differences in microstate parameters between ASD and non-autistic groups through meta-analysis and to explore the sources of research heterogeneity. Method: This meta-analysis was preregistered with PROSPERO (CRD42024599897) and followed PRISMA guidelines. Studies in English comparing EEG microstate patterns between ASD and Non-autistic groups were retrieved by database search to October 20, 2024. The meta-analysis was then conducted using RevMan5.2. Pooled results are expressed as standardized mean difference (SMD). Heterogeneity (I-2) and publication bias were assessed using Stata15.0. Result: Seven studies enrolling 194 ASD individuals were included, four deemed high quality and three moderate quality according to bias risk assessment. Microstate B duration and coverage were significantly greater in the pooled ASD group (duration SMD=0.83, 95%CI: 0.17-1.5; coverage SMD=0.54, 95%CI: 0.18-0.90), but heterogeneity could not be excluded. Microstate C occurrence frequency was also in the ASD group (SMD= -0.61, 95%CI: -1.08 to -0.15), and heterogeneity was significant. Sensitivity analysis revealed that only the group difference in microstate B coverage was robust. Subgroup analysis suggested that age was the main source of heterogeneity in microstate B and C coverage. Results were not affected by publication bias according to Egger's test. Conclusion: Future studies on the EEG microstate characteristics of ASD must control for age as an important cofounding variable.