- Klíčová slova
- data report, fMRI, multiple sclerosis, neurorehabilitation, open access,
- Publikační typ
- časopisecké články MeSH
Explainable artificial intelligence holds a great promise for neuroscience and plays an important role in the hypothesis generation process. We follow-up a recent machine learning-oriented study that constructed a deep convolutional neural network to automatically identify biological sex from EEG recordings in healthy individuals and highlighted the discriminative role of beta-band power. If generalizing, this finding would be relevant not only theoretically by pointing to some specific neurobiological sexual dimorphisms, but potentially also as a relevant confound in quantitative EEG diagnostic practice. To put this finding to test, we assess whether the automatic identification of biological sex generalizes to another dataset, particularly in the presence of a psychiatric disease, by testing the hypothesis of higher beta power in women compared to men on 134 patients suffering from Major Depressive Disorder. Moreover, we construct ROC curves and compare the performance of the classifiers in determining sex both before and after the antidepressant treatment. We replicate the observation of a significant difference in beta-band power between men and women, providing classification accuracy of nearly 77%. The difference was consistent across the majority of electrodes, however multivariate classification models did not generally improve the performance. Similar results were observed also after the antidepressant treatment (classification accuracy above 70%), further supporting the robustness of the initial finding.
- Klíčová slova
- EEG, biomarkers, classification, explainable artificial intelligence, machine learning, major depressive disorder, sexual dimorsphism,
- Publikační typ
- časopisecké články MeSH
This work presents and evaluates a 12-electrode intracranial electroencephalography system developed at the National Institute of Mental Health (Klecany, Czech Republic) in terms of an electrical source imaging (ESI) technique in rats. The electrode system was originally designed for translational research purposes. This study demonstrates that it is also possible to use this well-established system for ESI, and estimates its precision, accuracy, and limitations. Furthermore, this paper sets a methodological basis for future implants. Source localization quality is evaluated using three approaches based on surrogate data, physical phantom measurements, and in vivo experiments. The forward model for source localization is obtained from the FieldTrip-SimBio pipeline using the finite-element method. Rat brain tissue extracted from a magnetic resonance imaging template is approximated by a single-compartment homogeneous tetrahedral head model. Four inverse solvers were tested: standardized low-resolution brain electromagnetic tomography, exact low-resolution brain electromagnetic tomography (eLORETA), linear constrained minimum variance (LCMV), and dynamic imaging of coherent sources. Based on surrogate data, this paper evaluates the accuracy and precision of all solvers within the brain volume using error distance and reliability maps. The mean error distance over the whole brain was found to be the lowest in the eLORETA solution through signal to noise ratios (SNRs) (0.2 mm for 25 dB SNR). The LCMV outperformed eLORETA under higher SNR conditions, and exhibiting higher spatial precision. Both of these inverse solvers provided accurate results in a phantom experiment (1.6 mm mean error distance across shallow and 2.6 mm across subcortical testing dipoles). Utilizing the developed technique in freely moving rats, an auditory steady-state response experiment provided results in line with previously reported findings. The obtained results support the idea of utilizing a 12-electrode system for ESI and using it as a solid basis for the development of future ESI dedicated implants.
- Klíčová slova
- auditory steady-state response experiment, electrical source imaging, electroencephalography, fieldtrip, preclinical models, translational research,
- Publikační typ
- časopisecké články MeSH
Infant development of reaching to tactile targets on the skin has been studied little, despite its daily use during adaptive behaviors such as removing foreign stimuli or scratching an itch. We longitudinally examined the development of infant reaching strategies (from just under 2 to 11 months) approximately every other week with a vibrotactile stimulus applied to eight different locations on the face (left/right/center temple, left/right ear, left/right mouth corners, and chin). Successful reaching for the stimulus uses tactile input and proprioception to localize the target and move the hand to it. We studied the developmental progression of reaching and grasping strategies. As infants became older the likelihood of using the hand to reach to the target - versus touching the target with another body part or surface such as the upper arm or chair - increased. For trials where infants reached to the target with the hand, infants also refined their hand postures with age. As infants became older, they made fewer contacts with a closed fist or the dorsal part of the hand and more touches/grasps with the fingers or palm. Results suggest that during the first year infants become able to act more precisely on tactile targets on the face.
- Klíčová slova
- hand-to-mouth coordination, motor development, multisensory coordination, prehension, reaching, tactile localization,
- Publikační typ
- časopisecké články MeSH