Exploring the impact of manual and automatic EEG pre-processing methods on interpersonal neural synchrony measures in parent-infant hyperscanning studies

Background: Electroencephalograph (EEG) hyperscanning allows studying Interpersonal Neural Synchrony (INS) between two or more individuals across different social conditions, including parent-infant interactions. Signal pre-processing is crucial to optimize computation of INS estimates; however, few attempts have been made at comparing the impact of different dyadic EEG data pre-processing methods on INS estimates. New methods: EEG data collected on 31 mother-infant dyads (8-10 months) engaged in a Face-to-Face Still-Face Procedure were pre-processed with two versions of the same pipeline, the "automated" and the "manual". Cross- frequency PLV in the theta (3-5 Hz, 4-7 Hz) and alpha (6-9 Hz, 8-12 Hz) frequency bands were computed after automated and manual pre-processing and compared through Pearson's correlations and Repeated Measures ANOVAs. Results: PLVs computed in the theta, but not alpha, frequency band were significantly higher after automated preprocessing than after manual pre-processing. Moreover, the automated pipeline rejected a significantly lower percentage of ICs and epochs compared to the manual pipeline. Comparison with existing methods: While no direct comparison with existing dyadic EEG data pre-processing pipelines was made, this is the first study assessing the impact of different methodological decisions, particularly of the degree of pre-processing automatization, on cross-frequency PLV computed on a dataset of parent- infant dyads. Conclusions: Non-directional phase-based INS indexes such as the PLV seem to be affected by the degree of automatization of the pre-processing pipeline. Future research should strive for standardization of dyadic EEG pre-processing methods.