EEG signals classify hypnotic susceptibility using neural networks
EEG-Based Classification of Hypnotic Susceptibility Using Two-Dimensional Convolutional Neural Networks
Machine Learning
Summary
It can be hard for doctors to tell when someone has really entered a relaxed hypnotic state. This study shows that brainwave signals recorded with EEG can help identify who is more easily hypnotized. The researchers used smart computer programs called convolutional neural networks to analyze brain signals without needing to pick out specific features first. They found that signals from the front part of the brain gave the best results when tested on new people. This approach could help reliably assess hypnotic states in the future.
What this means in practice
- •For clinical neurophysiology teams: Provide automated tools to help clinicians detect hypnotic susceptibility using EEG signals without manual feature engineering.
- •For mental health technology developers: Build EEG-based neurofeedback or monitoring systems that identify relaxation states reliably using deep learning models focused on frontal brain regions.$Commercial implications: Makes practical EEG classifiers for hypnotic states that can be integrated into neurofeedback devices or therapeutic tools.
Authors
Krzysztof Wrobel, Grzegorz M. Wojcik, Filip Postepski, Andrzej Kawiak, Katarzyna Zemla, Grzegorz Sedek
Abstract
Guided Imagery (GI) is a mind-based relaxation technique widely used in clinical and therapeutic settings. Objectively assessing whether a patient has entered a relaxed state remains a challenge for clinicians. This study investigates electroencephalography (EEG)-based classification of hypnotic susceptibility using two-dimensional Convolutional Neural Networks (2D CNNs) applied to minimally preprocessed signals, without manual feature extraction. Data were collected from 62 male participants (32 Control, 30 Hypno) using a 256-channel dense array amplifier during Guided Imagery or cognitive task conditions. A sliding-window framework evaluated up to 868 independent models across seven anatomically defined brain regions and 124 ten-second time windows. Segment-level random-split screening was followed by Leave-One-Subject-Out (LOSO) cross-validation to obtain subject-independent performance estimates, and an ensemble approach combined predictions across K = 10 windows. The best single-window model achieved accuracy of 0.82 on the random split. Under LOSO, anterior regions generalised better across subjects: the frontal region achieved mean accuracy of 0.646 (AUC: 0.692). An ensemble of K = 10 windows further improved the prefrontal region to mean accuracy of 0.738. The occipital region, dominant in random-split screening, collapsed to near-chance under LOSO, revealing subject-specific EEG fingerprinting rather than genuine group differences. Bandpass filtering and z-score normalisation suffice for competitive EEG classification without manual feature extraction. Anterior cortical regions are identified as the most generalisable neural markers of hypnotic susceptibility.