2025 Hyper Recent •CC0 1.0 Universal

This work is dedicated to the public domain. No rights reserved.

Access Preprint From Server
July 4th, 2025
Version: 1
University of Pittsburgh
neuroscience
biorxiv

Recognizing EEG responses to active TMS vs. sham stimulations in different TMS-EEG datasets: a machine learning approach

Keihani, A.Open in Google Scholar•Donati, F. L.Open in Google Scholar•Russo, S.Open in Google Scholar•Parmigiani, S.Open in Google Scholar•Solbiati, M.Open in Google Scholar•Casali, A. G.Open in Google Scholar•Fecchio, M.Open in Google Scholar•Chaichian, O.Open in Google Scholar•Rothwell, J.Open in Google Scholar•Massimini, M.Open in Google Scholaret al.

Background: Transcranial Magnetic Stimulation (TMS) with simultaneous Electroencephalogram (TMS-EEG) allows assessing the neurophysiological properties of cortical neurons. However, TMS-evoked EEG potentials (TEPs) can be affected by components unrelated to TMS direct neuronal activation. Accurate, automatic tools are therefore needed to establish the quality of TEPs. Objective: To assess the discriminability of EEG responses to TMS vs. EEG responses to sham stimulations using sequence-to-sequence machine learning (ML). Methods: Two indipendent TMS-EEG datasets including TMS and several sham stimulation conditions were obtained from the left motor area of healthy volunteers (N=33 across datasets). A Bi-directional Long Short-Term Memory (BiLSTM) ML network was used to label each time point of the EEG signals as pertaining to TMS or sham conditions. Main outcome measures included accuracy at single-trial level and after averaging five to twenty trials. Results: For TMS conditions, post-stimulus vs. baseline/pre-stimulus EEG comparisons yielded moderate (60%-75%) single-trial accuracy and high-accuracy (>75%) for 20 trials across datasets, while for sham conditions post- vs. baseline/pre-stimulus EEG comparisons yielded lower accuracy rates than for TMS conditions, except for unmasked auditory stimulation. Furthermore, baseline/pre-stimulus TMS vs. baseline/pre-stimulus sham EEG comparisons showed chance-level accuracy, whereas post-stimulus TMS vs. post-stimulus sham EEG comparisons had moderate (single trial) to high (20 trial) accuracy, except for TMS with and without the click noise masking. Single-subject findings were comparable to group-level results across datasets. Conclusions: TEPs after active TMS are discernible from various sham stimulations even after a handful of trials and at the single-subject level using a BiLSTM ML approach.

Similar Papers

biorxiv
Sat Jul 05 2025
Electrocorticographic Detection of Speech Networks in Glioma-infiltrated Cortex
Direct cortical stimulation (DCS) is the clinical gold standard for identifying functional cortex in the human brain, which is essential for the safe removal of brain lesions. Defining the electro-physiological properties of DCS-positive cortical regions may facilitate the identification of critical language regions, thereby permitting safe glioma resections in communities without access. Leveragi...
Ambati, V. S.
•
Persad, A. S.
•
Kaur, J.
•
Herr, S.
...•
Hervey-Jumper, S. L.
biorxiv
Sat Jul 05 2025
Dissociating the Effects of Light at Night from Circadian Misalignment in a Neurodevelopmental Disorder Mouse Model Using Ultradian Light-Dark Cycles.
Individuals with neurodevelopmental disorders (NDDs) often experience sleep disturbances and are frequently exposed to light during nighttime hours. Our previous studies using the Cntnap2 knockout (KO) mouse model of NDDs demonstrated that nighttime light exposure increases behaviors such as excessive grooming, reduces social interactions, and disrupts daily locomotor rhythms. To further evaluate ...
Villanueva, S. A.
•
Wang, H.-B.
•
Nguyen-Ngo, K.
•
Chen, C. T.
...•
Colwell, C. S.
biorxiv
Sat Jul 05 2025
Cortex-Wide, Cellular-Resolution Volumetric Imaging with a Modular Two-Photon Imaging Platform
Mapping cortex-wide neuronal activity at single-cell resolution has been limited by the physical trade-off between numerical aperture and field-of-view (FOV) in two-photon microscopes. We present Meso2P, a modular two-photon platform that decouples excitation and detection by introducing a lateral paraboloid fluorescence collector. The design sustains an effective NA 0.87 over a contiguous 6 * 6 m...
Hu, J.
•
Zhu, Y.
•
Liu, S.
•
Li, C.
...•
Li, B.
biorxiv
Sat Jul 05 2025
Progressive Supranuclear Palsy PERK haplotype B selectively translates DLX1 promoting tau toxicity
The unfolded protein response sensor PERK exists in haplotypes A and B. PERK-B confers increased risk for tauopathies like progressive supranuclear palsy (PSP), but the mechanisms distinguishing its function from PERK-A and contributing to its association with tauopathy remain unknown. Here, we developed a controlled cellular model for a pair-wise comparison of the two PERK haplotypes, finding the...
Lessard, C. B.
•
Rubio-Rubio, D.
•
Tolton, S.
•
Criado-Marrero, M.
...•
Abisambra, J.
biorxiv
Sat Jul 05 2025
The c-Src inhibitor eCF506 diminishes opioid tolerance creating bias against β-arrestin2 recruitment
Opioids reduce severe pain, but persistent use is compromised by tolerance, attenuated by either {beta}-arrestin2 depletion, prompting development of biased opioids limited by partial efficacy, or c-Src kinase inhibitors, potentially acting through off-target effects. We tested eCF506, a conformationally selective c-Src inhibitor, on morphine antinociception and examined its effect on receptor si...
Singleton, S.
•
Nunn, F.
•
Lorente-Macias, A.
•
Unciti-Broceta, A.
•
Hales, T. G.
biorxiv
Sat Jul 05 2025
Differential encoding of social identity, valence and unfamiliarity in the amygdala and piriform cortex
To appropriately respond to social situations, animals must rapidly identify conspecifics as individuals, gauge their familiarity and recall any good or bad associations. In previous work (Mazuski & OKeefe, 2022), we characterized populations of neurons in the basolateral amygdala complex (BLA) that were strongly tuned to social conspecifics. In this current study, we asked whether these or other ...
Mazuski, C.
•
Oettl, L.-L.
•
Ren, C.
•
O'Keefe, J.
biorxiv
Sat Jul 05 2025
Strengthening Medial Olivocochlear Feedback Reduces the Developmental Impact of Early Noise Exposure
The early onset of peripheral deafness significantly disrupts the proper development of the auditory system. Likewise, exposure to loud noise during early development produces a similar disruptive effect. Before hearing onset in altricial mammals, cochlear inner hair cells exhibit spontaneous electrical activity that activates primary afferents and propagates into the central nervous system. This ...
Castagna, V. C.
•
Boero, L. E.
•
Di Guilmi, M. N.
•
Catalano Di Meo, C.
...•
Gomez-Casati, M. E.
biorxiv
Sat Jul 05 2025
Multi-task machine learning reveals the functional neuroanatomy fingerprint of mental processing
Mental processing delineates the functions of human mind encompassing a wide range of motor, sensory, emotional, and cognitive processes, each of which is underlain by the neuroanatomical substrates. Identifying accurate representation of functional neuroanatomy substrates of mental processing could inform understanding of its neural mechanism. The challenge is that it is unclear whether a specifi...
Wang, Z.
•
Chen, Y.
•
Yan, J.
•
Pan, Y.
...•
Jiang, X.
biorxiv
Sat Jul 05 2025
Extracting Reproducible Components from Electroencephalographic Responses to Transcranial Magnetic Stimulation with Group Task-Related Component Analysis
Transcranial magnetic stimulation combined with electroencephalography (TMS-EEG) is a powerful technique for investigating human cortical circuits. However, characterizing TMS-evoked potentials (TEPs) at the group level typically relies on grand averaging across stimulus repetitions (trials) and subjects - an approach that assumes a level of spatial and temporal consistency that is often lacking i...
Couto, B. A. N.
•
Fecchio, M.
•
Russo, S.
•
De Martino, E.
...•
Casali, A. G.
biorxiv
Sat Jul 05 2025
Reframing Sleep Architecture: A Compositional and Temporal Approach to Sleep Data Analysis
Significant progress has been made in developing sleep staging methodologies; however, less attention has been devoted to the analysis of sleep architecture. Two critical aspects remain underexplored: the choice of binning window (i.e., grouping data into time intervals) and the statistical treatment of the interdependencies among sleep phases. While one-hour bins are commonly used, this choice is...
Bonzanni, M.
•
Braga, A.