EEG-based investigation of effects of mindfulness meditation training on state and trait by deep learning and traditional machine learning.

Introduction: This study examines the state and trait effects of short-term mindfulness-based stress reduction (MBSR) training using convolutional neural networks (CNN) based deep learning methods and traditional machine learning methods, including shallow and deep ConvNets as well as support vector machine (SVM) with features extracted from common spatial pattern (CSP) and filter bank CSP (FBCSP). Methods: We investigated the electroencephalogram (EEG) measurements of 11 novice MBSR practitioners (6 males, 5 females; mean age 35.7 years; 7 Asians and 4 Caucasians) during resting and meditation at early and late training stages. The classifiers are trained and evaluated using inter-subject, mix-subject, intra-subject, and subject-transfer classification strategies, each according to a specific application scenario. Results: For MBSR state effect recognition, trait effect recognition using meditation EEG, and trait effect recognition using resting EEG, from shallow ConvNet classifier we get mix-subject/intra-subject classification accuracies superior to related previous studies for both novice and expert meditators with a variety of meditation types including yoga, Tibetan, and mindfulness, whereas from FBSCP + SVM classifier we get inter-subject classification accuracies of 68.50, 85.00, and 78.96%, respectively. Conclusion: Deep learning is superior for state effect recognition of novice meditators and slightly inferior but still comparable for both state and trait effects recognition of expert meditators when compared to the literatures. This study supports previous findings that short-term meditation training has EEG-recognizable state and trait effects.

Decoding semantics from intermodulation responses in frequency-tagged stereotactic EEG.

BACKGROUND: Humans perform object recognition using holistic processing, which is different from computers. Intermodulation responses in the steady-state visual evoked potential (SSVEP) of scalp electroencephalography (EEG) have recently been used as an objective label for holistic processing. NEW METHOD: Using stereotactic EEG (sEEG) to record SSVEP directly from inside of the brain, we aimed to decode Chinese characters from non-characters with activation from multiple brain areas including occipital, parietal, temporal, and frontal cortices. RESULTS: Semantic categories could be decoded from responses at the intermodulation frequency with high accuracy (80%-90%), but not the base frequency. Moreover, semantic categories could be decoded with activation from multiple areas including temporal, parietal, and frontal areas. COMPARISON WITH EXISTING METHOD(S): Previous studies investigated holistic processing in faces and words with frequency-tagged scalp EEGs. The current study extended the results to stereotactic EEG signals directly recorded from the brain. CONCLUSIONS: The human brain applies holistic processing in recognizing objects like Chinese characters. Our findings could be extended to an add-on feature in the existing SSVEP BCI speller.

Effects of Low-Frequency Repetitive Transcranial Magnetic Stimulation of the Bilateral Parietal Cortex in Patients With Tourette Syndrome.

Background: Traditional medical treatments are not effective for some patients with Tourette syndrome (TS). According to the literature, repetitive transcranial magnetic stimulation (rTMS) may be effective for the treatment of TS; however, different targets show different results. Objective: To assess the efficacy and safety of low-frequency rTMS in patients with TS, with the bilateral parietal cortex as the target. Methods: Thirty patients with TS were divided into two groups: active and sham groups. The active group was subjected to 0.5-Hz rTMS at 90% of resting motor threshold (RMT) with 1,200 stimuli/day/side, whereas the sham group was subjected to 0.5-Hz rTMS at 10% of RMT with 1,200 stimuli/day/side with changes in the coil direction. Both groups were bilaterally stimulated over the parietal cortex (P3 and P4 electrode sites) for 10 consecutive days. The symptoms of tics and premonitory urges were evaluated using the Yale Global Tic Severity Scale (YGTSS), Modified Scoring Method for the Rush Video-based Tic Rating Scale (MRVBTS), and Premonitory Urge for Tics Scale (PUTS) scores at baseline, the end of the 10-day treatment, 1 week after treatment, and 1 month after treatment. Results: At the end of the 10-day treatment, the YGTSS total, YGTSS motor tic, YGTSS phonic tic, MRVBTS, and PUTS scores in the active group significantly improved and improvements were maintained for at least 1 month. Conclusions: Low-frequency bilateral rTMS of the parietal cortex can markedly alleviate motor tics, phonic tics, and premonitory urges in patients with TS.