Blood-brain barrier permeability changes: nonlinear analysis of ECoG based on wavelet and machine learning approaches

Nadezhda Semenova; Konstantin Segreev; Andrei Slepnev; Anastasiya Runnova; Maxim Zhuravlev; Inna Blokhina; Alexander Dubrovsky; Maria Klimova; Andrey Terskov; Oxana Semyachkina-Glushkovskaya; Jürgen Kurths

doi:10.1140/epjp/s13360-021-01715-2

2022 Impact factor 3.4

EPJ PLUS - Condensed Matter and Complex Systems

Focus Point on Breakthrough Optics- and Complex Systems-based Technologies of Modulation of Drainage and Clearing Functions of the Brain

Eur. Phys. J. Plus (2021) 136: 736
https://doi.org/10.1140/epjp/s13360-021-01715-2

Regular Article

Blood-brain barrier permeability changes: nonlinear analysis of ECoG based on wavelet and machine learning approaches

Nadezhda Semenova¹^,2^a, Konstantin Segreev¹, Andrei Slepnev¹, Anastasiya Runnova¹^,3, Maxim Zhuravlev¹^,3, Inna Blokhina¹, Alexander Dubrovsky¹, Maria Klimova¹, Andrey Terskov¹, Oxana Semyachkina-Glushkovskaya¹^,4 and Jürgen Kurths¹^,4^,5

¹ Saratov State University, Astrakhanskaya str., 83, 410012, Saratov, Russia
² Département d’Optique P. M. Duffieux, Institut FEMTO-ST, Université Bourgogne-Franche-Comté CNRS UMR 6174, Besançon, France
³ State Medical University, B. Kazachaya str., 112, 410012, Saratov, Russia
⁴ Physics Department, Humboldt University, Newtonstrasse 15, 12489, Berlin, Germany
⁵ Potsdam Institute for Climate Impact Research, Telegrafenberg A31, 14473, Potsdam, Germany

^a nadya.i.semenova@gmail.com

Received: 12 January 2021
Accepted: 1 July 2021
Published online: 9 July 2021

Abstract

The blood-brain barrier plays a decisive role in protecting the brain from toxins and pathogens. The ability to analyze the BBB opening (OBBB) is crucial for the treatment of many brain diseases, but it is very difficult to noninvasively monitor OBBB. In this paper we analyze the EEG series of healthy rats in free behaviour and after music-induced OBBB. The research is performed using two completely different methods based on wavelet analysis and machine learning approach. The wavelet-approach demonstrates quantitative changes in the oscillatory structure in EEG signals after music listening, namely, a decrease in the number of patterns to the frequency band Hz. Using methods of machine learning we analyze the number of fragments of EEG realizations recognized as OBBB. After the music impact the number of recognized OBBB is increased in about 50%. Both methods enable us to recognize OBBB and are in a good agreement with each other. The comparative analysis was carried out using F-measures and ROC-curves.