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.

OBJECTIVE: Psoriasis, a common chronic inflammatory skin condition with genetic underpinnings, is traditionally managed with cupping therapy. Although used historically, the precise mechanical effects and therapeutic mechanisms of cupping in psoriasis remain largely unexamined. This study aimed to evaluate cupping therapy's efficacy for psoriasis and investigate its role in modulating inflammatory responses and cellular metabolism. METHODS: Psoriasis was induced in mice using topical imiquimod (IMQ). The effects of cupping on psoriatic lesions were assessed using the Psoriasis Area and Severity Index score, histology, immunohistochemistry, and immunofluorescence staining. polymerase chain reaction sequencing (RNA-seq) and Western blotting were conducted to examine changes in mRNA expression and the AMP-activated protein kinase (AMPK) signaling pathway. RESULTS: Cupping therapy significantly reduced inflammation, epidermal thickness, and inflammatory cell infiltration in mice with IMQ-induced psoriasis. Immunohistochemistry and immunofluorescence showed lower expression of inflammatory markers and a shift in T-cell populations. RNA-seq and Western blotting indicated that cupping upregulated Piezo1 and activated the AMPK pathway, improving energy metabolism in psoriatic skin. CONCLUSION Cupping therapy reduces epidermal hyperproliferation and inflammation in psoriasis, rebalancing the local immune microenvironment. Mechanistically, cupping promotes calcium influx via Piezo1, activates AMPK signaling, and supports metabolic homeostasis, suggesting therapeutic potential for psoriasis. Please cite this article as: Xi RF, Liu X, Wang Y, Lu HZ, Yuan SJ, Guo DJ, Zhu JY, Li FL, Duan YJ. Mechanosensory activation of Piezo1 via cupping therapy: Harnessing neural networks to modulate AMPK pathway for metabolic restoration in a mouse model of psoriasis. J Integr Med. 2025; 23(6):721-732.
Animals ; Psoriasis/chemically induced* ; Mice ; AMP-Activated Protein Kinases/metabolism* ; Disease Models, Animal ; Cupping Therapy/methods* ; Signal Transduction ; Imiquimod ; Ion Channels/genetics* ; Male ; Mechanotransduction, Cellular

OBJECTIVE: To identify the key features of facial and tongue images associated with anemia in female populations, establish anemia risk-screening models, and evaluate their performance. METHODS: A total of 533 female participants (anemic and healthy) were recruited from Shuguang Hospital. Facial and tongue images were collected using the TFDA-1 tongue and face diagnosis instrument. Color and texture features from various parts of facial and tongue images were extracted using Face Diagnosis Analysis System (FDAS) and Tongue Diagnosis Analysis System version 2.0 (TDAS v2.0). Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for feature selection. Ten machine learning models and one deep learning model (ResNet50V2 + Conv1D) were developed and evaluated. RESULTS: Anemic women showed lower a-values, higher L- and b-values across all age groups. Texture features analysis showed that women aged 30-39 with anemia had higher angular second moment (ASM)and lower entropy (ENT) values in facial images, while those aged 40-49 had lower contrast (CON), ENT, and MEAN values in tongue images but higher ASM. Anemic women exhibited age-related trends similar to healthy women, with decreasing L-values and increasing a-, b-, and ASM-values. LASSO identified 19 key features from 62. Among classifiers, the Artificial Neural Network (ANN) model achieved the best performance [area under the curve (AUC): 0.849, accuracy: 0.781]. The ResNet50V2 model achieved comparable results [AUC: 0.846, accuracy: 0.818]. CONCLUSION Differences in facial and tongue images suggest that color and texture features can serve as potential TCM phenotype and auxiliary diagnostic indicators for female anemia.
Humans ; Female ; Tongue/diagnostic imaging* ; Adult ; Anemia/diagnosis* ; Middle Aged ; Face/diagnostic imaging* ; Young Adult ; Machine Learning

OBJECTIVE: To explore the effect of bear bile powder (BBP) on acute lung injury (ALI) and the underlying mechanism. METHODS: The chemical constituents of BBP were analyzed by ultra-high-pressure liquid chromatography-mass spectrometry (UPLC-MS). After 7 days of adaptive feeding, 50 mice were randomly divided into 5 groups by a random number table (n=10): normal control (NC), lipopolysaccharide (LPS), dexamethasone (Dex), low-, and high-dose BBP groups. The dosing cycle was 9 days. On the 12th and 14th days, 20 µL of Staphylococcus aureus solution (bacterial concentration of 1 × 10^-7 CFU/mL) was given by nasal drip after 1 h of intragastric administration, and the mice in the NC group was given the same dose of phosphated buffered saline (PBS) solution. On the 16th day, after 1 h intragastric administration, 100 µL of LPS solution (1 mg/mL) was given by tracheal intubation, and the same dose of PBS solution was given to the NC group. Lung tissue was obtained to measure the myeloperoxidase (MPO) activity, the lung wet/dry weight ratio and expressions of CD14 and other related proteins. The lower lobe of the right lung was obtained for pathological examination. The concentrations of inflammatory cytokines including interleukin (IL)-6, tumour necrosis factor α (TNF-α ) and IL-1β in the bronchoalveolar lavage fluid (BALF) were detected by enzyme linked immunosorbent assay, and the number of neutrophils was counted. The colonic contents of the mice were analyzed by 16 sRNA technique and the contents of short-chain fatty acids (SCFAs) were measured by gas chromatograph-mass spectrometer (GC-MS). RESULTS: UPLC-MS revealed that the chemical components of BBP samples were mainly tauroursodeoxycholic acid and taurochenodeoxycholic acid sodium salt. BBP reduced the activity of MPO, concentrations of inflammatory cytokines, and inhibited the expression of CD14 protein, thus suppressing the activation of NF-κB pathway (P<0.05). The lung histopathological results indicated that BBP significantly reduced the degree of neutrophil infiltration, cell shedding, necrosis, and alveolar cavity depression. Moreover, BBP effectively regulated the composition of the intestinal microflora and increased the production of SCFAs, which contributed to its treatment effect (P<0.05). CONCLUSIONS BBP alleviates lung injury in ALI mouse through inhibiting activation of NF-κB pathway and decreasing expression of CD14 protein. BBP may promote recovery of ALI by improving the structure of intestinal flora and enhancing metabolic function of intestinal flora.
Animals ; Acute Lung Injury/pathology* ; Lipopolysaccharides ; Ursidae ; Gastrointestinal Microbiome/drug effects* ; Bile/chemistry* ; Lipopolysaccharide Receptors/metabolism* ; Powders ; Male ; Lung/drug effects* ; Mice ; Peroxidase/metabolism* ; Signal Transduction/drug effects* ; Cytokines/metabolism*

Objective:To explore the interrelationship between brain functional networks and features in functional magnetic resonance imaging(fMRI)of patients with Alzheimer's disease(AD),and to construct mixed-function networks(MFN),and apply them in machine learning classification models to improve the accuracy of AD classification.Methods:102 AD patients and 227 healthy subjects in the Alzheimer's Neuroimaging Initiative(ADNI)dataset were retrospectively analyzed.The partial correlation brain network of the blood oxygen level dependent(BOLD)signal was calculated and fused with low-frequency wave amplitude(ALFF),fractional low-frequency wave amplitude(fALFF)and local consistency(ReHo)features to construct MFN.Network topology parameters were extracted,and a variety of machine learning classification models were constructed based on MFN topological parameters,accuracy,precision,recall and area under the curve(AUC)were used to evaluate the predictive efficiency of the models.Results:By constructed MFN and calculated intra group to inter group ratio(IIGR),35 features could be obtained from ALFF,fALFF and ReHo feature topological parameter analysis,after rank sum test and FDR correction,there were statistical differences among 28 features(P＜0.05).The classification results show that,all the five classifiers have high classification performance on the test data set.The accuracy,precision and recall rates of random forest(RF),adaptive lifting algorithm(AdaBoost),guided aggregation algorithm(Bagging)and support vector machine(SVM)were all 99.7％,and the AUC values were up to 100％,99.5％,99.1％and 99.5％,respectively.The accuracy(98.5％),precision(98.5％),recall(98.5％),and AUC(99.1％)of the multi-layer perceptron(MLP)were slightly lower than other models,but remained excellent.It was worth noting that RF has the highest AUC value of all models at 100.0％,while Bagging has the lowest AUC value(99.1％)in the integrated approach.The results of performance comparison show that,MFN classification model can significantly improve the recognition and classification of AD disease,and greatly improve the performance of various indicators of the classifier.The results showed that,MFN classification model was superior to intelligent classification based fusion,DBN-based multitask learning,PVT-TSVM,unsupervised learning and clustering,SVM and SVM of degree 3 polynomial kernel function in key indicators such as accuracy(99.13％),AUC(99.42％),recall rate(99.46％)and specificity(99.42％)with plasma proteins,machine learning algorithms.It was further proved that MFN classification model has good generalization ability and robustness in AD disease classification.Conclusion:The AD classification model constructed based on brain mixed function network topology parameters and machine learning can improve the accuracy of AD classification.

Traditional mass measurement methods are not applicable in microgravity environments,and the main challenge for in-orbit body mass measurement technology based on inertial principles is to address the random errors brought about by the weightless environment.These include additional torques due to shifts in the center of mass,nonlinear accelerations due to non-rigid human bodies,mechanical energy consumption due to organ vibrations,and random vibrations of the measurement device itself.To address the above difficulties,the project proposes a technical scheme based on the principle of linear acceleration,designs and constructs a ground-specific air-floating experimental and simulation platform,studies key data such as motion trajectory,acceleration change,and vibration frequency amplitude during the mass measurement process,and simulates the changes in the center of mass and random vibrations of the human body in a weightless environment.The project has designed an adjustable posture bracket to adapt to changes in the center of mass,enhance body restraint,and greatly reduce shaking;it has also developed an integrated four-bar linkage motion guidance mechanism,high-precision integrated photoelectric distance measurement,and modular motion constant force measurement device to ensure the accurate measurement of acceleration and constant force data.The product has undergone simulation calculations,ground human applicability tests,and in-orbit applicability verification in the space station.Ground test results show that the device achieves a body mass measurement accuracy better than 0.5%,and the dispersion is better than 0.38%;after flight mission verification and evaluation,the in-orbit body mass measurement dispersion is less than 0.4%,which is superior to the SLAMMD,a mass measurement device of the same principle on the International Space Station,and is at the forefront internationally,achieving accurate body mass measurement.

This study systematically reviewed the randomized controlled trial(RCT) of traditional Chinese medicine(TCM) treatment of post-stroke depression(PSD) and analyzed the clinical study characteristics and outcome indicators, aiming to optimize the design and establish the core outcome set in the future clinical trials of the TCM treatment of PSD. PubMed, Web of Science, Cochrane Library, EMbase, CNKI, VIP, Wanfang, and SinoMed were searched for the relevant RCT published in recent 3 years. The basic characteristics, intervention measures, and outcome indicators of the included RCT were extracted, and the descriptive analysis was carried out. A total of 76 RCTs were eventually included, with the sample size concentrated in 80-100 cases. The most frequent TCM syndromes were liver depression and Qi stagnation(15 times, 31.91%) and phlegm combined with stasis(5 times, 10.63%). The frequency of intervention methods followed a descending trend of TCM decoction(35 times, 46.05%) and TCM decoction + acupuncture(4 times, 5.26%), Chinese patent medicine(3 times, 3.94%), and the intervention mainly lasted for 1 to 3 months(43 times, 60.56%). The adverse reactions of patients were mainly digestive system reaction(150 patients, 39.37%) and nervous system reaction(112 patients, 29.39%). Most of the included studies had unclear risk of bias, involving 84 outcome indicators, which belonged to 8 indicator domains. The RCTs of TCM treatment of PSD showed a variety of problems, such as non-standard TCM syndrome differentiation, inconsistent names of TCM syndrome scores and measurement tools, low quality, unclear risk of bias, neglect of endpoint indicators, unreasonable selection of substitute indicators, lack of differentiation between primary and secondary outcome indicators, non-standard reporting of safety indicators, insufficient attention to economic indicators, and lack of long-term prognosis evaluation. It is suggested that the future research should improve the quality of methodology and build a standardized core outcome set to promote the development of high-quality clinical research in this field.
Humans ; Randomized Controlled Trials as Topic ; Drugs, Chinese Herbal/administration & dosage* ; Stroke/psychology* ; Depression/etiology* ; Treatment Outcome ; Medicine, Chinese Traditional

This study aims to evaluate the efficacy of Chinese medicine injections in treating transient ischemic attack(TIA) based on network Meta-analysis. Randomized controlled trial(RCT) about Chinese medicine injections in treating TIA were retrieved from PubMed, Web of Science, Cochrane Library, EMbase, CNKI, VIP, Wanfang, and SinoMed with the time interval from inception to March 1, 2024. The methodological quality of the included articles was assessed by ROB 2.0, and the GRADE system was employed to evaluate the quality of evidence. The gemtc package of R 4.1.2 was used to perform the network Meta-analysis. Finally, 63 RCTs with a total sample size of 5 750 cases were included, involving 11 Chinese medicine injections(Shuxuetong Injection, Danhong Injection, Shuxuening Injection, Ginkgo Damo Injection, Shenxiong Glucose Injection, Ligustrazine Injection, Salviae Miltiorrhizae and Ligustrazine Hydrochloride Injection, Salvianolic Acids for Injection, Dengzhan Xixin Injection, Guhong Injection, and Xueshuantong Injection). All patients received conventional western medicine treatment, and the experimental group was additionally treated with Chinese medicine injection. Network Meta-analysis yielded the following results.(1) In terms of improving the clinical total response rate, 11 Chinese medicine injections combined with conventional western medicine outperformed conventional western medicine alone, and Dengzhan Xixin Injection + conventional western medicine had the best effect.(2) In terms of reducing plasma viscosity, 7 Chinese medicine injections combined with conventional western medicine outperformed conventional western medicine alone, and Shenxiong Glucose Injection + conventional western medicine had the best effect.(3) In terms of reducing whole blood high shear viscosity, 6 Chinese medicine injections combined with conventional western medicine outperformed conventional western medicine alone, and Guhong Injection + conventional western medicine had the best effect.(4) In terms of reducing whole blood low shear viscosity, 6 Chinese medicine injections combined with conventional western medicine outperformed conventional western medicine alone, and Shuxuening Injection + conventional western medicine had the best effect.(5) In terms of reducing fibrinogen, 9 Chinese medicine injections combined with conventional western medicine outperformed conventional western medicine alone, and Ginkgo Damo Injection + conventional western medicine had the best effect.(6) In terms of increasing the average blood flow velocity, 3 Chinese medicine injections combined with conventional western medicine outperformed conventional western medicine alone, and Shuxuening Injection + conventional western medicine had the best effect. In summary, compared with conventional western medicine alone, Chinese medicine injections combined with conventional western medicine were effective in improving the clinical total response rate and the average blood flow velocity, as well as reducing plasma viscosity, whole blood high shear viscosity, whole blood low shear viscosity, and fibrinogen. However, due to the limited quality and quantity of the included articles, the above conclusions need to be verified by more high-quality, multi-center, and large-sample RCT.
Humans ; Drugs, Chinese Herbal/administration & dosage* ; Injections ; Ischemic Attack, Transient/drug therapy* ; Randomized Controlled Trials as Topic ; Treatment Outcome

Moringa oleifera, widely utilized in Ayurvedic medicine, is recognized for its leaves, seeds, and velamen possessing traditional effects such as vātahara(wind alleviation), sirovirecaka(brain clearing), and hridya(mental nourishment). This study aims to identify the medicinal part of ■ in the Sārasvata ghee formulation as described in the Bower Manuscript, while investigating the ameliorative effects of different medicinal parts of M. oleifera on learning and memory deficits in mice and elucidating the underlying molecular mechanisms. A total of 144 male ICR mice were randomly assigned to the following groups: control, model(scopolamine hydrobromide, Sco, 2 mg·kg~(-1)), donepezil(donepezil hydrochloride, Don, 3 mg·kg~(-1)), M. oleifera leaf low-, medium-, and high-dose groups(0.5, 1, 2 g·kg~(-1)), M. oleifera seeds low-, medium-, and high-dose groups(0.25, 0.5, 1 g·kg~(-1)), and M. oleifera velamen low-, medium-, and high-dose groups(0.31, 0.62, 1.24 g·kg~(-1)). Learning and memory abilities were assessed using the passive avoidance test and Morris water maze. Nissl and HE staining were employed to examine histopathological changes in the hippocampus. Transcriptomics and targeted metabolomics were used to screen differential genes and metabolites, with MetaboAnalyst 6.0 and O2PLS methods applied to identify key disease-related targets and pathways. RESULTS:: demonstrated that M. oleifera leaf(1 g·kg~(-1)) significantly ameliorated Sco-induced learning and memory deficits, outperforming M. oleifera seeds(0.25 g·kg~(-1)) and M. oleifera velamen(1.24 g·kg~(-1)). This was evidenced by improved behavioral performance, reversal of neuronal damage, and reduced acetylcholinesterase(AChE) activity. Multi-omics analysis revealed that M. oleifera leaf upregulated Tuba1c gene expression through the synaptic vesicle cycle, enhancing glutamate(Glu), dopamine(DA), and acetylcholine(ACh) release via Tuba1c-Glu associations for neuroprotection. M. oleifera seeds targeted the dopaminergic synapse pathway, promoting memory consolidation through Drd2-ACh associations. M. oleifera velamen was associated with the cocaine addiction pathway, modulating dopamine metabolism via Adora2a-DOPAC, with limited relevance to learning and memory. In conclusion, M. oleifera leaf exhibits superior efficacy and mechanistic advantages over M. oleifera seeds and velamen, suggesting that the ■ in the Sārasvata ghee formulation is likely M. oleifera leaf, providing scientific evidence for its identification in ancient texts.
Animals ; Moringa oleifera/chemistry* ; Male ; Mice ; Seeds/chemistry* ; Plant Leaves/chemistry* ; Mice, Inbred ICR ; Memory Disorders/psychology* ; Transcriptome/drug effects* ; Memory/drug effects* ; Learning/drug effects* ; Metabolomics ; Humans ; Drugs, Chinese Herbal/administration & dosage* ; Maze Learning/drug effects*