NEUROCLEAN: A GENERALIZED MACHINE-LEARNING APPROACH TO NEURAL TIME-SERIES CONDITIONING

Electroencephalography (EEG) and local field potentials (LFP) are two widely used techniques to record electrical activity from the brain. These signals are used in both the clinical and research domains for multiple applications. However, most brain data recordings suffer from a myriad of artifacts and noise sources other than the brain itself. Thus, a major requirement for their use is proper and fully automatized conditioning. Consequently, here we introduce an unsupervised, multipurpose EEG/LFP preprocessing method, the NeuroClean pipeline. NeuroClean is an unsupervised series of algorithms intended to mitigate reproducibility issues and biases caused by human intervention. The pipeline is designed as a sequential multi-step process, from common bandpass and line noise filtering to sophisticated AI algorithms. However, it incorporates an efficient independent component analysis and an automatic component rejection based on a clustering algorithm. This machine learning classifier is used to ensure that task-relevant information is preserved after each step of the cleaning process. Several datasets were used to validate the pipeline under different contexts. NeuroClean removed several common types of artifacts from the signal. Moreover, in the context of motor tasks of varying complexity, it yielded more than 97% accuracy (chance-level of 33.3%) in an optimized Multinomial Logistic Regression model after cleaning the data, compared to the raw data, which performed at 74% accuracy. These results show that NeuroClean is a promising pipeline and workflow that can be applied to future work and studies to achieve better generalization and performance on machine learning pipelines.