Electroencephalography (EEG) is a non-invasive neurophysiological monitoring technique. It records the electrical activity of the cerebral cortex using electrodes placed on the scalp surface. Owing to its high safety, portability, and millisecond-level temporal resolution, EEG has been widely utilized in a variety of fields, including clinical diagnosis, brain-computer interfaces (BCIs), and cognitive neuroscience research. However, due to its microvolt-level amplitude, EEG is highly susceptible to various artifacts, including electrooculographic (EOG), electrocardiographic (ECG), electromyographic (EMG), and power line interference (PLI). These artifacts can obscure genuine neural activity and introduce spurious electrophysiological features. Consequently, they may compromise EEG signal quality, thereby reducing the reliability of downstream analyses. To address this issue, numerous EEG artifact removal methods have been developed, including both traditional denoising techniques and deep learning-based approaches. Traditional EEG denoising methods have long served as the primary solutions for artifact removal. Representative approaches include filtering, regression, and blind source separation. Although these methods have demonstrated effectiveness in specific scenarios, they suffer from several inherent limitations. Filtering assumes that artifacts and EEG signals can be separated in the frequency domain, but many artifacts, such as EOG and EMG, overlap with EEG spectra, which may lead to the loss of valuable neural information. Regression methods require high-quality artifact references to estimate and subtract contaminations, limiting their effectiveness in reference-free scenarios. Blind source separation can remove artifacts without external references, but it typically requires the number of EEG channels to exceed the number of sources, restricting its application in single- or low-channel EEG recordings. Deep learning-based EEG denoising methods address these limitations effectively. First, they learn the nonlinear mapping between contaminated and clean EEG directly from data in an end-to-end manner. This approach does not rely on assumptions about spectral separability, thereby preserving neural activity more completely. Second, the reference information is incorporated during the training phase, allowing the trained model to perform artifact removal independently without external references. Third, deep learning models can be flexibly designed to accommodate various recording setups, achieving robust denoising for both high-density and single-channel EEG. Collectively, these advantages enable deep learning-based methods to overcome the main challenges of traditional approaches, providing more accurate and reliable EEG signal recovery. The superior denoising performance of deep learning-based EEG denoising methods has attracted increasing attention in EEG artifact removal research. As a result, many deep learning-based denoising methods have been developed and successfully applied in neural engineering areas. However, a systematic review of the techniques and applications in this field is still lacking. To address this gap, this paper reviews recent advances in deep learning-based EEG denoising from four perspectives: technical principle, benchmark dataset, denoising model, and evaluation method. Representative applications in neural signal analysis and BCI decoding are also summarized. Furthermore, the advantage, existing challenge, and future research direction of deep learning-based EEG denoising are discussed. This review aims to provide valuable theoretical insights and technical guidance for researchers. It is also expected to promote further advances and broader applications of deep learning-based EEG denoising techniques.

Consciousness, which underpins human perception, cognition, and behavioural responses, has long been a major focus of neuroscience and medicine. Alterations in consciousness occur not only during reversible processes such as sleep and anaesthesia, but also in pathological conditions, including disorders of consciousness (DOC) and brain injury. With recent advances in the synchronized acquisition and analysis of multimodal physiological signals, such as electroencephalography (EEG) and electrocardiography (ECG), the dynamic interactions between the heart and brain have become increasingly apparent. A growing body of evidence indicates that heart-brain interactions are closely associated with the maintenance and transition of consciousness states, offering a novel perspective for elucidating their underlying mechanisms and supporting relevant clinical assessments. Current approaches to heart-brain interaction analysis for consciousness-state assessment can be broadly grouped into three categories: ECG-based methods, EEG-based methods, and heart-brain coupling analysis. These approaches characterize heart-brain interactions during changes in consciousness from the complementary perspectives of autonomic regulation, cortical interoceptive processing, and cross-system information transfer, respectively. Nevertheless, this field remains at an early stage. Most studies have focused on a single experimental context or a fixed analytical method, with insufficient systematic consideration of the applicability and limitations of different approaches. Moreover, the mechanisms underlying the emergence and alteration of consciousness remain incompletely understood. Accordingly, this review examines heart-brain interaction methods employed in recent consciousness-state assessment studies in accordance with progressively deeper analytical perspectives, and systematically evaluates the advantages and limitations of these methods across distinct consciousness-related conditions. Heart rate variability (HRV) is one of the classical ECG-based indices used to investigate heart-brain interactions. It refers to fluctuations in consecutive interbeat intervals over a specified time period and is regarded as a physiological measure of autonomic nervous system regulation that may indirectly reflect the strength of heart-brain interactions. Depending on the analytical dimension, HRV analysis is commonly divided into time-domain, frequency-domain, and complexity-index analyses. These approaches characterize autonomic activity in terms of temporal fluctuations, the distribution of frequency components, and nonlinear dynamical properties, respectively. Although extensive research supports their physiological interpretation, they cannot characterize directional interactions from the heart to the brain. Among EEG-based methods for heart-brain interaction analysis, EEG activity directly related to cardiac fluctuations has received particular attention. One of the most widely used measures is the heartbeat-evoked potential (HEP). HEP-based approaches are considered to directly reflect the capacity of the cerebral cortex to process cardiac afferent signals and may be especially advantageous for characterizing rapidly changing consciousness levels, such as those observed during sleep. However, they do not comprehensively capture dynamic bidirectional information exchange between the brain and heart and are susceptible to cardiac artefacts, respiration, and variation in preprocessing procedures. Heart-brain coupling analysis quantifies functional associations between ECG and EEG through cross-system interaction measures, thereby assessing dynamic interactions between the heart and brain. It emphasizes information transfer, feedback regulation, and cross-timescale coordination between the two systems, offering a more comprehensive perspective for investigating changes in consciousness during sleep, anaesthesia, and DOC. However, the neurophysiological mechanisms and physiological interpretation of individual computational indices have not yet been fully established, and the robustness of their results and their potential for clinical generalization require further validation. Finally, this review summarizes the commonalities and differences among the three classes of methods across research domains involving different consciousness states. It further argues that heart-brain interaction research requires deeper investigation at both the mechanistic level of consciousness and the level of clinical application. Current challenges and key issues are identified, and future directions and feasible pathways for heart-brain interaction research are discussed, with the aim of providing new perspectives for researchers in related fields.

AIM To investigate the effects of Yunpi Tongchang Formula on intestinal mucosal barrier damage in rats with opioid-induced constipation(OIC)of Spleen-Kidney Yang Deficiency Syndrome.METHODS In contrast to the 10 rats of the blank group,the 50 rats of the modeling group were induced into models of OIC of Spleen-Kidney Yang Deficiency Pattern by 7 days consecutive administration of both subcutaneous loperamide injection and alternating gavage of activated carbon ice water and vinegar.Following successful modeling,rats were randomly allocated into the model group,the mosapride citrate tablet group(1.35 mg/kg),and the high-dose,medium-dose,and low-dose Yunpi Tongchang Formula groups(15.12,7.56,3.78 g/kg),with 8 mice in each group.Upon the completion of the 14 days treatment,the rats had their TCM Syndrome scores assessed;their fecal water content,initial black stool excretion time,and small intestine propulsion rate measured;their colon tissue morphology observed by HE staining;their serum levels of IL-6,TNF-α,and IL-1β detected by ELISA;their expressions of occludin and zonula occludens-1(ZO-1)in colon tissues detected by immunohistochemistry;their mRNA expressions of MyD88,TLR4 and NF-κB p65 in the colon tissues detected by RT-qPCR;and their protein expressions of MyD88,TLR4 and NF-κB p65 in the colon tissues detected by Western blot.RESULTS Compared to the blank group,the model group had higher TCM Syndrome scores(P＜0.01);lower fecal water content and small intestine propulsion rate(P＜0.05,P＜0.01);longer initial black stool excretion time(P＜0.01);more mucosal edema in colon tissue,obvious inflammatory infiltration,and glandular disorder;increased serum levels of IL-6,TNF-α and IL-1 β(P＜0.05);decreased colon expressions of ZO-1 and occludin(P＜0.01);and increased mRNA and protein expressions of TLR4,MyD88 and NF-κB p65(P＜0.01).Compared to the model group,both the medium-dose Yunpi Tongchang Formula group and the mosapride citrate tablet group demonstrated effectively reduced TCM syndrome scores(P＜0.01);increased fecal water content and small intestine propulsion rate(P＜0.05,P＜0.01);and shorter initial black stool excretion time(P＜0.01);improved colon mucosal edema and inflammatory infiltration;decreased serum levels of IL-6,TNF-α and IL-1β(P＜0.01);upregulated protein expressions of ZO-1 and occludin(P＜0.01);and downregulated mRNA and protein expressions of TLR4,MyD88 and NF-κB p65(P＜0.05,P＜0.01).CONCLUSION Yunpi Tongchang Formula significantly ameliorates constipation symptoms in OIC rat models of Spleen-Kidney Yang Deficiency Syndrome because of its efficacy in attenuating intestinal inflammation and preserving the integrity of intestinal epithelial barrier structure,with its mechanistic action in downregulating TLR4/MyD88/NF-κB signaling pathway activation.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

OBJECTIVE: To investigate the effect of zedoarondiol on neovascularization of atherosclerotic (AS) plaque by exosomes experiment. METHODS: ApoE^-/- mice were fed with high-fat diet to establish AS model and treated with high- and low-dose (10, 5 mg/kg daily) of zedoarondiol, respectively. After 14 weeks, the expressions of anti-angiogenic protein thrombospondin 1 (THBS-1) and its receptor CD36 in plaques, as well as platelet activation rate and exosome-derived miR-let-7a were detected. Then, zedoarondiol was used to intervene in platelets in vitro, and miR-let-7a was detected in platelet-derived exosomes (Pexo). Finally, human umbilical vein endothelial cells (HUVECs) were transfected with miR-let-7a mimics and treated with Pexo to observe the effect of miR-let-7a in Pexo on tube formation. RESULTS: Animal experiments showed that after treating with zedoarondiol, the neovascularization density in plaques of AS mice was significantly reduced, THBS-1 and CD36 increased, the platelet activation rate was markedly reduced, and the miR-let-7a level in Pexo was reduced (P<0.01). In vitro experiments, the platelet activation rate and miR-let-7a levels in Pexo were significantly reduced after zedoarondiol's intervention. Cell experiments showed that after Pexo's intervention, the tube length increased, and the transfection of miR-let-7a minics further increased the tube length of cells, while reducing the expressions of THBS-1 and CD36. CONCLUSION Zedoarondiol has the effect of inhibiting neovascularization within plaque in AS mice, and its mechanism may be potentially related to inhibiting platelet activation and reducing the Pexo-derived miRNA-let-7a level.
Animals ; MicroRNAs/genetics* ; Exosomes/drug effects* ; Plaque, Atherosclerotic/genetics* ; Neovascularization, Pathologic/genetics* ; Human Umbilical Vein Endothelial Cells/metabolism* ; Humans ; Blood Platelets/drug effects* ; Apolipoproteins E/deficiency* ; Thrombospondin 1/metabolism* ; CD36 Antigens/metabolism* ; Platelet Activation/drug effects* ; Male ; Mice ; Mice, Inbred C57BL

OBJECTIVE: To evaluate the efficacy and safety of Shexiang Tongxin Dropping Pill (STDP) in treating stable angina patients with phlegm-heat and blood-stasis syndrome by exercise duration and metabolic equivalents. METHODS: This multicenter, randomized, double-blind, placebo-controlled clinical trial enrolled stable angina patients with phlegm-heat and blood-stasis syndrome from 22 hospitals. They were randomized 1:1 to STDP (35 mg/pill, 6 pills per day) or placebo for 56 days. The primary outcome was the exercise duration and metabolic equivalents (METs) assessed by the standard Bruce exercise treadmill test after 56 days of treatment. The secondary outcomes included the total angina symptom score, Chinese medicine (CM) symptom scores, Seattle Angina Questionnaire (SAQ) scores, changes in ST-T on electrocardiogram and adverse events (AEs). RESULTS: This trial enrolled 309 patients, including 155 and 154 in the STDP and placebo groups, respectively. STDP significantly prolonged exercise duration with an increase of 51.0 s, compared to a decrease of 12.0 s with placebo (change rate: -11.1% vs. 3.2%, P<0.01). The increase in METs was significantly greater in the STDP group than in the placebo group (change: -0.4 vs. 0.0, change rate: -5.0% vs. 0.0%, P<0.01). The improvement of total angina symptom scores (25.0% vs. 0.0%), CM symptom scores (38.7% vs. 11.8%), reduction of nitroglycerin consumption (100.0% vs. 11.3%), and all domains of SAQ, were significantly greater with STDP than placebo (all P<0.01). The changes in Q-T intervals at 28 and 56 days from baseline were similar between the two groups (both P>0.05). Twenty-five participants (16.3%) with STDP and 16 (10.5%) with placebo experienced AEs (P=0.131), with no serious AEs observed. CONCLUSION STDP could improve exercise tolerance in patients with stable angina and phlegm-heat and blood stasis syndrome, with a favorable safety profile. (Registration No. ChiCTR-IPR-15006020).
Humans ; Double-Blind Method ; Drugs, Chinese Herbal/adverse effects* ; Male ; Female ; Middle Aged ; Angina, Stable/physiopathology* ; Aged ; Syndrome ; Treatment Outcome ; Placebos ; Tablets

OBJECTIVE: To evaluate the dynamic changes of glucocorticoid (GC) dose and the feasibility of GC discontinuation in rheumatoid arthritis (RA) patients under the background of Chinese medicine (CM). METHODS: This multicenter retrospective cohort study included 1,196 RA patients enrolled in the China Rheumatoid Arthritis Registry of Patients with Chinese Medicine (CERTAIN) from September 1, 2019 to December 4, 2023, who initiated GC therapy. Participants were divided into the Western medicine (WM) and integrative medicine (IM, combination of CM and WM) groups based on medication regimen. Follow-up was performed at least every 3 months to assess dynamic changes in GC dose. Changes in GC dose were analyzed by generalized estimator equation, the probability of GC discontinuation was assessed using Kaplan-Meier curve, and predictors of GC discontinuation were analyzed by Cox regression. Patients with <12 months of follow-up were excluded for the sensitivity analysis. RESULTS: Among 1,196 patients (85.4% female; median age 56.4 years), 880 (73.6%) received IM. Over a median 12-month follow-up, 34.3% (410 cases) discontinued GC, with significantly higher rates in the IM group (40.8% vs. 16.1% in WM; P<0.05). GC dose declined progressively, with IM patients demonstrating faster reductions (median 3.75 mg vs. 5.00 mg in WM at 12 months; P<0.05). Multivariate Cox analysis identified age <60 years [P<0.001, hazard ratios (HR)=2.142, 95% confidence interval (CI): 1.523-3.012], IM therapy (P=0.001, HR=2.175, 95% CI: 1.369-3.456), baseline GC dose ⩽7.5 mg (P=0.003, HR=1.637, 95% CI: 1.177-2.275), and absence of non-steroidal anti-inflammatory drugs use (P=0.001, HR=2.546, 95% CI: 1.432-4.527) as significant predictors of GC discontinuation. Sensitivity analysis (545 cases) confirmed these findings. CONCLUSIONS RA patients receiving CM face difficulties in following guideline-recommended GC discontinuation protocols. IM can promote GC discontinuation and is a promising strategy to reduce GC dependency in RA management. (Trial registration: ClinicalTrials.gov, No. NCT05219214).
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Arthritis, Rheumatoid/drug therapy* ; Glucocorticoids/therapeutic use* ; Medicine, Chinese Traditional ; Retrospective Studies

Eightly-four novel thioheterocyclic nucleoside derivatives were designed, synthesized, and evaluated for antitumor activity in vitro and in vivo. Most of the compounds inhibited the growth of HCT116 and HeLa cancer cells in vitro, among them 33a and 36b exhibited potent activity against HCT116 cells (IC₅₀ = 0.27 and 0.49 μmol/L, respectively). Both compounds 33a and 36b inhibited cell metastasis, arrested the cell cycle in the G₂/M phase, and induced apoptosis in vitro. Mechanistic studies revealed that 33a and 36b increased ROS levels, led to DNA damage, ER stress, and mitochondrial dysfunction, and inhibited autophagy in HCT116 cells. Biological information analysis, RNA-sequencing, Gene Set Enrichment Analysis (GSEA), drug affinity responsive target stability (DARTS) assay, cellular thermal shift assay (CETSA), and SPR experiments identified that compounds 33a and 36b showed antitumor activity by suppressing the c-MYC pathway. c-MYC silencing assays indicated that c-MYC proteins participated in 33a-mediated anticancer activities in HCT116 cells. More importantly, compound 33a presented favorable pharmacokinetic properties in mice (T _1/2 = 6.8 h) and showed significant antitumor efficacy in vivo without obvious toxicity, showing promising potential for further clinical development.

OBJECTIVE: Rheumatoid arthritis (RA) is a systemic autoimmune disease that affects the small joints of the whole body and degrades the patients' quality of life. Zhengqing Fengtongning (ZF) is a traditional Chinese medicine preparation used to treat RA. ZF may cause liver injury. In this study, we aimed to develop a prediction model for abnormal liver function caused by ZF. METHODS: This retrospective study collected data from multiple centers from January 2018 to April 2023. Abnormal liver function was set as the target variable according to the alanine transaminase (ALT) level. Features were screened through univariate analysis and sequential forward selection for modeling. Ten machine learning and deep learning models were compared to find the model that most effectively predicted liver function from the available data. RESULTS: This study included 1,913 eligible patients. The LightGBM model exhibited the best performance (accuracy = 0.96) out of the 10 learning models. The predictive metrics of the LightGBM model were as follows: precision = 0.99, recall rate = 0.97, F1_score = 0.98, area under the curve (AUC) = 0.98, sensitivity = 0.97 and specificity = 0.85 for predicting ALT < 40 U/L; precision = 0.60, recall rate = 0.83, F1_score = 0.70, AUC = 0.98, sensitivity = 0.83 and specificity = 0.97 for predicting 40 ≤ ALT < 80 U/L; and precision = 0.83, recall rate = 0.63, F1_score = 0.71, AUC = 0.97, sensitivity = 0.63 and specificity = 1.00 for predicting ALT ≥ 80 U/L. ZF-induced abnormal liver function was found to be associated with high total cholesterol and triglyceride levels, the combination of TNF-α inhibitors, JAK inhibitors, methotrexate + nonsteroidal anti-inflammatory drugs, leflunomide, smoking, older age, and females in middle-age (45-65 years old). CONCLUSION This study developed a model for predicting ZF-induced abnormal liver function, which may help improve the safety of integrated administration of ZF and Western medicine. Please cite this article as: Yu Z, Kou F, Gao Y, Lyu CM, Gao F, Wei H. A machine learning model for predicting abnormal liver function induced by a Chinese herbal medicine preparation (Zhengqing Fengtongning) in patients with rheumatoid arthritis based on real-world study. J Integr Med. 2025; 23(1): 25-35.
Humans ; Arthritis, Rheumatoid/drug therapy* ; Drugs, Chinese Herbal/therapeutic use* ; Female ; Middle Aged ; Male ; Retrospective Studies ; Machine Learning ; Adult ; Aged ; Liver/physiopathology* ; Alanine Transaminase/blood*