IMPROVING EFFICIENCY AND ROBUSTNESS IN INFANT EEG PREPROCESSING An Optimized Pipeline.

APICE-Py constitute the fully open-source Python counterpart of the APICE pipeline, a MATLAB-based tool for infant Electroencephalogram (EEG) preprocessing. It is devel??oped to enhance accessibility, foster collaboration among research teams, and integrate seamlessly with modern machine learning tools. The difference between the programming languages, required key modifications, notably the parallelization of the Spherical Spline Interpolation (SSI), which dramatically im??proved computational efficiency for large datasets when compared to the original func??tion of the MNE-Python library. While numerical differences in filter implementations led APICE-Py to be more conservative in the number of retained epochs, the valida??tion demonstrated comparable performance. Using the Standardized Measurement Error (SME), no significant statistical differences were found in the extracted Evoked Response Potential (ERP)s between the Python and MATLAB versions. Computational time anal??yses confirmed that the parallelized Python version achieves similar processing speeds. APICE-Py democratizes robust infant EEG preprocessing, promoting broader research and clinical applications. The pipeline is openly available in the NeuroKidsLab GitHub repository.