Prolonged P3 latency predicts clinical response to repetitive transcranial magnetic stimulation in tinnitus.

Overview

1. Department of Ear, Nose, and Throat, The First Affiliated Hospital of Soochow University, Suzhou, China
2. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China

Abstract

Objective: The clinical efficacy of repetitive transcranial magnetic stimulation (rTMS) for tinnitus is variable, necessitating predictive biomarkers. We assessed whether pre-treatment multimodal electroencephalography (EEG) could predict rTMS response.

Methods: Fifty-eight tinnitus patients underwent a 10-session rTMS protocol targeting the dorsolateral prefrontal cortex and left temporo-parietal lobe. Before treatment, we extracted a comprehensive set of 325 features, encompassing event-related potentials (ERPs), spectral power, microstate metrics, and clinical features. Predictive modeling was performed using five machine learning classifiers with 5-fold cross-validation. Feature importance was ranked, and an iterative feature selection procedure was conducted to optimize the feature set. The predictive power of the top-ranking feature was further validated by constructing a univariate model.

Results: Adaptive Boosting performed best. P3 latency was the top predictor. Responders had longer pre-treatment P3 latencies than non-responders (389 ms vs. 370 ms, p < 0.001). The univariate prediction model based on a P3 latency cut-off of ≥384 ms achieved an accuracy of 0.79 and an area under the curve (AUC) of 0.69 ± 0.14. The multimodal model constructed through feature optimization, which incorporated the top 15 features, demonstrated superior predictive efficacy, achieving an accuracy of 0.84 ± 0.10 and an AUC of 0.91 ± 0.09.

Conclusions: Pre-treatment P3 latency robustly predicts clinical response to rTMS in tinnitus patients.

Significance: This study establishes P3 latency as a foundational, clinically actionable neurophysiological biomarker for stratifying rTMS response, facilitating a shift toward precision neuromodulation by optimizing patient selection and avoiding unnecessary interventions.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• doi:10.17632/t4zh638fbz.1, at the source; found in “Data availability”

Data availability

Aggregate data supporting the findings can be found in Mendeley Data (doi:10.17632/t4zh638fbz.1 (http://dx.doi.org/10.17632/t4zh638fbz.1)), which contains demographic information, event-related potentials (ERPs), frequency band power, and microstate parameters for all participants. The original data file contains 335 columns of data. During the construction of the predictive model, we excluded 10 columns of non-predictive data: one column for subject identification numbers, eight columns representing treatment response outcome scores (e.g., ∆VAS, ∆THI) used to define therapeutic response, and one column for the global explained variance (a quality metric) from microstate analysis. Consequently, a total of 325 baseline features were ultimately used for machine learning modeling.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 6 authors, 5 keywords, 6 funders, 57 references.

Cite

This paper

Ding, Z.-L., Zhou, W.-C., Gong, M.-F., Liu, J.-S., Dai, Y.-K., & Tao, D.-D. (2026). Prolonged P3 latency predicts clinical response to repetitive transcranial magnetic stimulation in tinnitus. Clinical neurophysiology practice, 11, 381-392. https://doi.org/10.1016/j.cnp.2026.05.003

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3389/fneur.2026.1808769

Pre-treatment structural brain biomarkers predict response to repetitive transcranial magnetic stimulation in subjective tinnitus.

Journal: Frontiers in neurology

In common: other, clinical / translational, other condition, 9 references

[2] doi:10.1016/j.isci.2026.116995

EEG microstates and dynamic functional connectivity reveal stage-specific brain networks in subjective tinnitus.

Journal: iScience

In common: EEG, other condition, 6 references

[3] doi:

Tutorial on using EEG microstates to study moment-to-moment large-scale functional brain network dynamics in neurodevelopment

Journal: Frontiers in neuroscience

In common: EEG, 3 references

[4] doi:10.1016/j.neurot.2026.e00960 [code]

Personalizing neuromodulation for chronic pain: A connectivity-guided trial.

Journal: Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics

In common: other, EEG, clinical / translational, 2 references

[5] doi:10.1002/brb3.71293

EEG-Based Multifocal Tomographic Neurofeedback in Older Individuals With Chronic Tinnitus Does Not Lead to Persistent Electrophysiological Changes.

Journal: Brain and behavior

In common: EEG, other condition, 2 references

[6] doi:10.1007/s10548-026-01196-5

A Quantitative Comparison of Two Methods for Higher-Order EEG Microstate Syntax Analysis.

Journal: Brain topography

In common: EEG, 2 references

[7] doi:10.1007/s10548-026-01249-9

What Static Connectivity Misses: Dynamic Alpha-Band Brain Network States in First-Episode Psychosis.

Journal: Brain topography

In common: EEG, 2 references

[8] doi:10.1162/imag.a.1224 [code]

Test-retest reliability analysis of resting-state EEG measures and their association with long-term memory in children and adults.

Journal: Imaging neuroscience (Cambridge, Mass.)

In common: EEG, 2 references

[9] doi:10.1038/s41598-026-55029-3

Stimulus statistical context sensitivity of deviant responses to auditory intensity changes.

Journal: Scientific reports

In common: EEG, 2 references

[10] doi:10.1016/j.dcn.2026.101780

Atypical auditory cortical processing in ADHD during early and middle childhood.

Journal: Developmental cognitive neuroscience

In common: EEG, 2 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.