Objective: Electroencephalogram (EEG) measures electrophysiological activity in the cerebral cortex and is broadly used across diagnostic, research, and clinical contexts. Missing data gaps are a pervasive issue in EEG signal recording, resulting from sensor failures and sensor disconnections, amongst other sources. To preserve a continuous signal describing underlying electrophysiological processes, imputation must be used to reconstruct these gaps. The aim of this review is to examine the methods that have been developed for missing data gap imputation in EEG signals. Methods: A search of five databases was conducted based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. The search question examined existing algorithms for imputation in EEG signals. Results: The initial search yielded 17,490 results (an update included 1913 additional results). This review includes 16 articles presenting EEG gap imputation methods. These imputation methods were characterized as (i) tensor-based, (ii) machine learning and deep learning, and (iii) model-based and classical. Conclusions: Several of these methods achieved strong effectiveness for accurately reconstructing gaps in ‘ground truth’ EEG signals; however, the limited generalizability of many of the studies due to small datasets lacking adequate participant diversity as well as methodological differences made it impossible to describe a single leading method. Further, the reliance on full recordings for segment imputation in some methods could prove prohibitive to real-time imputation. Future study is required to rectify these limitations and to properly investigate computational latency and requirements. Significance: This work provides novel insights into existing methods for EEG gap imputation, as it identifies current shortcomings in the literature and paves a way for a more generalizable solution to be achieved through future work.
Bergmann et al. (Wed,) studied this question.