Current epilepsy prediction methods are not effective in characterizing the multi-domain features of complex long-term electroencephalogram (EEG) data, leading to suboptimal prediction performance. Therefore, this paper proposes a novel multi-scale sparse adaptive convolutional network based on multi-head attention mechanism (MS-SACN-MM) model to effectively characterize the multi-domain features. The model first preprocesses the EEG data, constructs multiple convolutional layers to effectively avoid information overload, and uses a multi-layer perceptron and multi-head attention mechanism to focus the network on critical pre-seizure features. Then, it adopts a focal loss training strategy to alleviate class imbalance and enhance the model's robustness. Experimental results show that on the publicly created dataset (CHB-MIT) by MIT and Boston Children's Hospital, the MS-SACN-MM model achieves a maximum accuracy of 0.999 for seizure prediction 10 ~ 15 minutes in advance. This demonstrates good predictive performance and holds significant importance for early intervention and intelligent clinical management of epilepsy patients.
Humans ; Electroencephalography/methods* ; Epilepsy/physiopathology* ; Neural Networks, Computer ; Seizures/physiopathology* ; Signal Processing, Computer-Assisted ; Algorithms

General anesthesia, pivotal for surgical procedures, requires precise depth monitoring to mitigate risks ranging from intraoperative awareness to postoperative cognitive impairments. Traditional assessment methods, relying on physiological indicators or behavioral responses, fall short of accurately capturing the nuanced states of unconsciousness. This study introduces a machine learning-based approach to decode anesthesia depth, leveraging EEG data across different anesthesia states induced by propofol and esketamine in rats. Our findings demonstrate the model's robust predictive accuracy, underscored by a novel intra-subject dataset partitioning and a 5-fold cross-validation method. The research diverges from conventional monitoring by utilizing anesthetic infusion rates as objective indicators of anesthesia states, highlighting distinct EEG patterns and enhancing prediction accuracy. Moreover, the model's ability to generalize across individuals suggests its potential for broad clinical application, distinguishing between anesthetic agents and their depths. Despite relying on rat EEG data, which poses questions about real-world applicability, our approach marks a significant advance in anesthesia monitoring.
Animals ; Machine Learning ; Electroencephalography/methods* ; Ketamine/administration & dosage* ; Rats ; Male ; Propofol/administration & dosage* ; Rats, Sprague-Dawley ; Anesthesia, General/methods* ; Brain/physiology* ; Intraoperative Neurophysiological Monitoring/methods*

Depression is increasingly prevalent among adolescents and can profoundly impact their lives. However, the early detection of depression is often hindered by the time-consuming diagnostic process and the absence of objective biomarkers. In this study, we propose a novel approach for depression detection based on an affective brain-computer interface (aBCI) and the resting-state electroencephalogram (EEG). By fusing EEG features associated with both emotional and resting states, our method captures comprehensive depression-related information. The final depression detection model, derived through decision fusion with multiple independent models, further enhances detection efficacy. Our experiments involved 40 adolescents with depression and 40 matched controls. The proposed model achieved an accuracy of 86.54% on cross-validation and 88.20% on the independent test set, demonstrating the efficiency of multimodal fusion. In addition, further analysis revealed distinct brain activity patterns between the two groups across different modalities. These findings hold promise for new directions in depression detection and intervention.
Humans ; Male ; Female ; Adolescent ; Case-Control Studies ; Depression/diagnosis* ; Early Diagnosis ; Rest ; Electroencephalography/methods* ; Brain-Computer Interfaces ; Models, Psychological ; Reproducibility of Results ; Affect/physiology* ; Photic Stimulation/methods* ; Video Recording ; Brain/physiopathology*

Closed-loop neuromodulation, especially using the phase of the electroencephalography (EEG) rhythm to assess the real-time brain state and optimize the brain stimulation process, is becoming a hot research topic. Because the EEG signal is non-stationary, the commonly used EEG phase-based prediction methods have large variances, which may reduce the accuracy of the phase prediction. In this study, we proposed a machine learning-based EEG phase prediction network, which we call EEG phase prediction network (EPN), to capture the overall rhythm distribution pattern of subjects and map the instantaneous phase directly from the narrow-band EEG data. We verified the performance of EPN on pre-recorded data, simulated EEG data, and a real-time experiment. Compared with widely used state-of-the-art models (optimized multi-layer filter architecture, auto-regress, and educated temporal prediction), EPN achieved the lowest variance and the greatest accuracy. Thus, the EPN model will provide broader applications for EEG phase-based closed-loop neuromodulation.
Humans ; Electroencephalography/methods* ; Brain/physiology* ; Machine Learning ; Signal Processing, Computer-Assisted ; Male ; Adult ; Neural Networks, Computer ; Brain Waves/physiology*

Approximately 30%-40% of epilepsy patients do not respond well to adequate anti-seizure medications (ASMs), a condition known as pharmacoresistant epilepsy. The management of pharmacoresistant epilepsy remains an intractable issue in the clinic. Its early prediction is important for prevention and diagnosis. However, it still lacks effective predictors and approaches. Here, a classical model of pharmacoresistant temporal lobe epilepsy (TLE) was established to screen pharmacoresistant and pharmaco-responsive individuals by applying phenytoin to amygdaloid-kindled rats. Ictal electroencephalograms (EEGs) recorded before phenytoin treatment were analyzed. Based on ictal EEGs from pharmacoresistant and pharmaco-responsive rats, a convolutional neural network predictive model was constructed to predict pharmacoresistance, and achieved 78% prediction accuracy. We further found the ictal EEGs from pharmacoresistant rats have a lower gamma-band power, which was verified in seizure EEGs from pharmacoresistant TLE patients. Prospectively, therapies targeting the subiculum in those predicted as "pharmacoresistant" individual rats significantly reduced the subsequent occurrence of pharmacoresistance. These results demonstrate a new methodology to predict whether TLE individuals become resistant to ASMs in a classic pharmacoresistant TLE model. This may be of translational importance for the precise management of pharmacoresistant TLE.
Epilepsy, Temporal Lobe/diagnosis* ; Animals ; Drug Resistant Epilepsy/drug therapy* ; Electroencephalography/methods* ; Rats ; Anticonvulsants/pharmacology* ; Neural Networks, Computer ; Male ; Humans ; Phenytoin/pharmacology* ; Adult ; Disease Models, Animal ; Female ; Rats, Sprague-Dawley ; Young Adult ; Convolutional Neural Networks

A brain-computer interface (BCI) based on motor imagery (MI) provides additional control pathways by decoding the intentions of the brain. MI ability has great intra-individual variability, and the majority of MI-BCI systems are unable to adapt to this variability, leading to poor training effects. Therefore, prediction of MI ability is needed. In this study, we propose an MI ability predictor based on multi-frequency EEG features. To validate the performance of the predictor, a video-guided paradigm and a traditional MI paradigm are designed, and the predictor is applied to both paradigms. The results demonstrate that all subjects achieved > 85% prediction precision in both applications, with a maximum of 96%. This study indicates that the predictor can accurately predict the individuals' MI ability in different states, provide the scientific basis for personalized training, and enhance the effect of MI-BCI training.
Humans ; Imagination/physiology* ; Electroencephalography/methods* ; Brain-Computer Interfaces ; Male ; Female ; Adult ; Young Adult ; Brain/physiology* ; Movement/physiology* ; Motor Activity/physiology* ; Psychomotor Performance/physiology*

Working memory is an executive memory process that includes encoding, maintenance, and retrieval. These processes can be modulated by transcranial alternating current stimulation (tACS) with sinusoidal waves. However, little is known about the impact of the rate of current change on working memory. In this study, we aimed to investigate the effects of two types of tACS with different rates of current change on working memory performance and brain activity. We applied a randomized, single-blind design and divided 81 young participants who received triangular wave tACS, sinusoidal wave tACS, or sham stimulation into three groups. Participants performed n-back tasks, and electroencephalograms were recorded before, during, and after active or sham stimulation. Compared to the baseline, working memory performance (accuracy and response time) improved after stimulation under all stimulation conditions. According to drift-diffusion model analysis, triangular wave tACS significantly increased the efficiency of non-target information processing. In addition, compared with sham conditions, triangular wave tACS reduced alpha power oscillations in the occipital lobe throughout the encoding period, while sinusoidal wave tACS increased theta power in the central frontal region only during the later encoding period. The brain network connectivity results showed that triangular wave tACS improved the clustering coefficient, local efficiency, and node degree intensity in the early encoding stage, and these parameters were positively correlated with the non-target drift rate and decision starting point. Our findings on how tACS modulates working memory indicate that triangular wave tACS significantly enhances brain network connectivity during the early encoding stage, demonstrating an improvement in the efficiency of working memory processing. In contrast, sinusoidal wave tACS increased the theta power during the later encoding stage, suggesting its potential critical role in late-stage information processing. These findings provide valuable insights into the potential mechanisms by which tACS modulates working memory.
Humans ; Memory, Short-Term/physiology* ; Male ; Female ; Young Adult ; Transcranial Direct Current Stimulation/methods* ; Brain/physiology* ; Adult ; Electroencephalography ; Single-Blind Method

The pain-evoked potential electroencephalogram (EEG) is an effective electrophysiological indicator for pain assessment, yet its extraction is challenging due to interference from background activity and involuntary blinks. Although existing blink artifact-removal methods show efficacy, they face limitations such as the need for reference signals, neglect of individual differences, and reliance on user input, hindering their practical application in clinical pain assessments. In this paper, we propose a novel framework applying adaptive quadrature mirror filter banks (AQMFB) with discrete wavelet transform (DWT) to remove blink artifacts in pain EEG. Unlike traditional DWT methods that apply fixed wavelets across subjects, our method adapts wavelet construction based on the characteristics of EEG. Experimental results demonstrate that AQMFB-DWT outperforms four leading methods in removing blink artifacts with minimal distortion of pain information, all within an acceptable processing time. This technique is a valuable preprocessing step for enhancing the extraction of pain-evoked potentials.
Humans ; Artifacts ; Blinking/physiology* ; Electroencephalography/methods* ; Pain/diagnosis* ; Male ; Wavelet Analysis ; Adult ; Female ; Evoked Potentials/physiology* ; Young Adult ; Brain/physiopathology* ; Pain Measurement/methods* ; Signal Processing, Computer-Assisted

Electroencephalography (EEG) and magnetic resonance imaging (MRI), as neuroimaging technologies, provided objective and visualized technical tools for analyzing the brain effect mechanisms of acupuncture and moxibustion from the perspectives of brain structure, function, metabolism, and hemodynamics. The advancement of artificial intelligence (AI) algorithms can compensate for issues such as the large and scattered nature of neuroimaging data, inconsistent quality, and high heterogeneity of image information. The integration of AI with neuroimaging can facilitate individualized, intelligent, and precise prediction of acupuncture and moxibustion effects, enable intelligent classification of differential acupuncture responses, and identify brain activation patterns. This paper focuses on EEG and MRI, analyzing how machine learning and deep learning optimize multimodal neuroimaging data and their applications in the study of acupuncture and moxibustion brain effects mechanisms. Furthermore, it highlights current research gaps and limitations to provide insights for future studies on acupuncture brain effects mechanisms.
Humans ; Acupuncture Therapy ; Brain/physiology* ; Moxibustion ; Neuroimaging/methods* ; Artificial Intelligence ; Magnetic Resonance Imaging ; Electroencephalography

BACKGROUND: Visual input significantly influences cerebral activity related to locomotor navigation, although the underlying mechanism remains unclear. This study aimed to analyze the effects of chronic visual impairment and its rehabilitation on sensorimotor integration during level walking in patients with age-related cataract. METHODS: This prospective case series enrolled 14 female patients (68.4 ± 4.7 years) with age-related cataract, scheduled for consecutive cataract surgeries at the Department of Ophthalmology in Peking University Third Hospital from June 2019 to June 2020. Electroencephalogram (EEG) signals during level walking were recorded using a portable EEG system before and 4 weeks after visual restoration. Walking speed was assessed using the Footscan system. Spectral power of the theta and alpha bands was analyzed with repeated-measures analysis of variance, with Assignment (rest and walking), Phase (preoperative and postoperative), and Electrode sites (F3, Fz, F4, O1, and O2) as within-subject factors. RESULTS: Compared to the visual impairment state, theta band power significantly decreased after visual restoration (13.16 ± 1.58 μV 2vs. 23.65 ± 3.48 μV 2 , P = 0.018). Theta activity was notably reduced during walking (17.24 ± 2.43 μV 2vs. 37.86 ± 6.62 μV 2 , P = 0.017), while theta power at rest was not significantly different between the two phases (9.44 ± 1.24 μV 2vs. 9.08 ± 1.74 μV 2 , P = 0.864). Changes in walking speed were correlated with alterations in theta power at electrode sites of O1 ( r = -0.574, P = 0.032) and O2 ( r = -0.648, P = 0.012). Alpha band power remained stable during walking and was unaffected by visual status. CONCLUSIONS Chronic visual impairment from age-related cataract triggers enhanced cerebral activation of sensorimotor integration to compensate for visual decline during locomotion. This cerebral over-activation is effectively alleviated by visual restoration.
Humans ; Female ; Walking/physiology* ; Aged ; Electroencephalography/methods* ; Prospective Studies ; Middle Aged ; Cataract/physiopathology* ; Vision Disorders/physiopathology*