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:To investigate effect of comprehensive management intervention based on WeChat multimedia classroom on cardiac function and prognosis in elderly patients with acute myocardial infarction(AMI).Methods:Clinical data of 118 elderly patients diagnosed with AMI in the Second Affiliated Hospital of Chinese PLA Air Force Military Medical University between August 2021 and December 2022 were retrospectively collected.According to nursing way after operation,they were divided into control group(n=60,comprehensive management interven-tion)and intervention group(n=58,comprehensive management intervention based on WeChat multimedia class-room),both groups were intervened for 5 months.Cardiac function,exercise tolerance,compliance to rehabilita-tion management,self-efficacy and healthy behavior were compared between two groups.Kaplan-Meier survival curve was employed to compare incidence of adverse cardiovascular events during follow-up between two groups.Results:After 5-month intervention,compared with patients in control group,those in intervention group had sig-nificant higher left ventricular ejection fraction(LVEF)[(58.14±1.88)％vs.(54.48±1.34)％],6min walking distance(6MWD)[(490.41±59.59)m vs.(394.97±28.20)m],scores of compliance to rehabilitation manage-ment[(6.97±2.03)points vs.(5.03±1.40)points],General Self-Efficacy Scale(GSES)[(30.34±4.67)points vs.(23.55±4.86)points]and Health Promoting Lifestyle Profile-Ⅱ[(137.62±30.17)points vs.(115.95±22.66)points],and significant lower left ventricular end-diastolic volume(LVEDV)[(117.90±4.22)ml vs.(131.28±3.61)ml],left ventriadar end-systolic volume(LVESV)[(54.46±2.10)ml vs.(63.15±2.06)ml],serum brain natriuretic peptide(BNP)[(362.32±25.36)pg/ml vs.(567.58±21.90)pg/ml]and incidence of ad-verse cardiovascular events(6.90％vs.21.67％)(P＜0.05 or＜0.01).Conclusion:Comprehensive management intervention based on the WeChat multimedia classroom could significantly improve cardiac function,exercise toler-ance,compliance to rehabilitation,self-efficacy and healthy behavior,and reduce incidence of adverse cardiovas-cular events after operation in elderly AMI patients.

Objective:To explore the independent risk factors for uremic encephalopathy(UE)in maintenance hemodialysis(MHD)patients and provide evidence for early clinical warning and intervention.Methods:A case-control study was conducted,enrolling 67 MHD patients diagnosed with UE(UE group)at Laibin People's Hospital from January 2010 to December 2024,and 67 non-UE patients during the same period(control group).Demographic characteristics,dialysis parameters,laboratory indicators,and infection events were collected.Univariate and multivariate logistic regression analyses were used to identify independent risk factors for UE.Results:The UE group had significantly higher rates of infection(58.2％vs.29.9％),serum creatinine(789 vs.702 μmol/L),and iPTH levels(568 vs.385 pg/mL)compared to the control group(P＜0.05).Multivariate analysis revealed that concurrent infection(OR=3.022,95％CI:1.312-6.958),elevated serum creatinine(OR=1.004,95％CI:1.000-1.008),and elevated iPTH(OR=1.002,95％CI:1.001-1.003)were independent risk factors for UE(P＜0.05).The combined prediction model achieved an AUC of 0.878(95％CI:0.822-0.934),with 82.1％sensitivity and 80.6％specificity.Conclusion:Infection,elevated serum creatinine,and elevated iPTH significantly increase the risk of UE in MHD patients.Clinical management should emphasize infection prevention,toxin clearance optimization,and parathyroid function regulation to reduce UE incidence.

Objective To compare the differences in dosimetry and treatment efficiency of three radiotherapy plans after left-sided breast-conserving surgery,including modified intensity-modulated radiation therapy(IMRT),cross-field volume-modulated arc therapy(VMAT)or improved VMAT,so as to provide references for clinical practice.Methods Three radiotherapy plans of modified IMRT,cross-field VMAT and improved VMAT were designed for 12 patients after left-sided-breast-conserving surgery.The modified IMRT with five irradiation fields and the improved VMAT with two arcs were modified by not setting cross-fields while determining the start and end angles with the rays passing through the least lung area.The cross-field VMAT had its start and end angles set based on the cross-fields.The doses to the target areas,peripheral organs at risk,heart and its substructures were evaluated,and dose verification was carried out.The three plans were compared in terms of treatment efficiency and gamma pass rate.SPSS 22.0 was used for statistical analysis.Results All the three plans behaved well in dose distribution.In terms of planning gross tumor volume dosimetry dosimetry,the improved VMAT and modified IMRT gained advantages than others in CI and D50,respectively,with the differences being significant(all P<0.05).In terms of planning target volume dosimetry,the modified IMRT had the V107 and D50 lower than those of the others,with the differences being significant(P<0.05).In terms of the protection of peripheral organs at risk,V5 of the left lung,Dmean of the right lung and Dmean of the healthy breast were lower in the modified IMRT plan than in the other 2 plans,with statistically significant differences(P<0.05);V20,V30,V35 and V40 of the left lung were lower in the modified VMAT plan than in the other 2 plans,with statistically significant differences(P<0.05).In terms of protection of heart and its substructures,the left ventricle V20,V30 and Dmean of the improved VMAT plan behaved better than those of other 2 plans,and the difference was statistically significant(all P<0.05).In terms of treatment efficiency,the cross-field VMAT plan had the lowest MU while highest treatment efficiency;the improved VMAT plan had the MU higher while the treatment efficiency lower than the cross-field VMAT plan;the modified IMRT plan had the highest MU while the lowest gamma pass rate,and the differences in the MUs and gamma pass rates among the three plans were statistically significant(P<0.05).Conclusion Under the same standard conditions,the cross-field VMAT and improved VMAT plans show technical advantages.Though the improved VMAT plan has the treatment efficiency lower than the cross-field VMAT,it decreases the possibility of radiocardiac injury in terms of dosimetry and thus can be used for radiotherapy after left-sided breast-conserving surgery.[Chinese Medical Equipment Journal,2025,46(4):45-51]

Objective To design a new type of elastic gloves for burn scar rehabilitation to solve the problems of conventional elastic gloves in pressure distribution,elasticity maintenance and absorption of sweat stains.Methods The new elastic gloves was made of non-woven fabric by spandex material,which was composed of external and internal parts.The main body of the external part was used as the primary structure of the gloves,which was provided with a sealing strip,a storage bag,a drawstring,etc.The internal part consisted of a bonding sheet,an elastic band,a fiber sheet,an absorbent sponge,some breathable holes,etc.Results The new elastic gloves designed could be used for the pressure therapy for the scars on the opisthenar,palm side,finger web and purlicue with scar proliferation inhibitted effectively,and the breathable hole and absorbent sponge contributed to the absorption of the sweat of the patient.Conclusion The new type of elastic gloves gains advantages in elasticity,wearing comfort and effectiveness of the pressure therapy for purlicue and finger web,and can be used for the pressure therapy to inhibit proliferative scarring after burns.[Chinese Medical Equipment Journal,2025,46(8):118-120]

Objective To propose a novel identification algorithm based on ensemble learning for assessing the severity of acute respiratory distress syndrome(ARDS)to achieve continuous monitoring of the disease severity.Methods Firstly,leve-raging the open-source MIMIC-Ⅳ database,a variety of non-invasive physiological parameters of patients were extracted and subjected to preliminary preprocessing.A multivariate feature selection algorithm was employed to rank these parameters and calculate feature importance scores through weighted computation.Secondly,based on the feature importance scores,a subset search algorithm was utilized to identify the subset of features that could yield optimal performance across four machine learning algorithms:neural networks,logistic regression,AdaBoost and XGBoost.Finally,a soft voting ensemble method was designed using a generalized linear regression model to integrate the results of each single machine learning algorithm,and a multivariate ensemble learning algorithm was proposed by combining the optimal feature subsets.The algorithm proposed when used to identify the severity of ADRS was evaluated with MIMIC-Ⅳ database,and compared with the traditional algorithms.Results The sensitivity,specificity,accuracy and AUC of the algorithm were 87.15％,89.23％,88.34％and 0.923 4,respectively,all of which outperformed those of the traditional algorithms.Conclusion The ARDS severity identification algorithm based on ensemble learning is capable of achieving continuous and real-time monitoring of the severity of ARDS,thereby offering robust support for the early identification and warning of ARDS in patients.[Chinese Medical Equipment Journal,2025,46(2):1-9]

Objective:To compare the impact of manual right arm blood pressure measurement with computer-controlled blood pressure meter (CCBPM) on the detection rate of hypertension among elderly individuals.Method:This was a cross-sectional study. Elderly residents undergoing routine health check-up in a village in Jiangxi Province from April to June 2024 were enrolled. Manual blood pressure measurements were performed on the right arm using an electronic sphygmomanometer, while standardized dual-arm synchronized blood pressure assessments were conducted using the CCBPM. Blood pressure data were recorded from three sources: manual measurement on the right arm; the first CCBPM measurement on the arm with higher systolic blood pressure (CCBPM single); and the mean blood pressure of the arm with higher systolic blood pressure from two (if the difference between the first two measurements was less than 5 mmHg, 1 mmHg=0.133 kPa) or three (if the difference exceeded 5 mmHg) CCBPM measurements (CCBPM mean). Hypertension detection rates from these three datasets were compared. Subgroup analysis was performed according to age (60-74 years old as the elderly group,≥75 years old as the senior group) and gender. Intra-group correlation coefficient ( ICC) was analyzed to evaluate the consistency of blood pressure data of different blood pressure measurement methods, and Kappa value was analyzed to evaluate the consistency of hypertension classification determined by different blood pressure measurement methods. Results:A total of 1 498 participants were enrolled, aged (71.30±6.83) years old, including 678 males (45.26%). The blood pressure and heart rate measured by the artificial right arm blood pressure measurement were higher than those measured by CCBPM single (blood pressure: (140.09±17.19)/(82.40±10.93) mmHg vs. (135.31±18.98)/(81.23±10.51) mmHg; heart rate: (75.76±11.72) beats/min vs.(72.94±11.21) beats/min) and CCBPM mean (blood pressure: (140.09±17.19)/(82.40±10.93) mmHg vs. (134.64±18.39)/(80.28±9.78) mmHg; heart rate: (75.76±11.72) beats/min vs. (72.87±10.70) beats/min, all P<0.05). The detection rate of hypertension determined by CCBPM mean was significantly lower than that of artificial right arm (40.25% (603/1 498) vs.54.34% (814/1 498)) and CCBPM single (40.25% (603/1 498) vs. 44.79% (671/1 498), all P<0.05). Subgroup analysis showed that that the detection rate of hypertension determined by CCBPM mean was lower than that measured by artificial right arm regardless of gender and age (all P<0.05). The consistency of blood pressure data between artificial right arm and the CCBPM mean was moderate (systolic blood pressure: ICC=0.70; diastolic blood pressure: ICC=0.62), with less consistent classification ( Kappa=0.37). The consistency of blood pressure data between CCBPM single and CCBPM mean is extremely high (systolic blood pressure: ICC=0.94; diastolic blood pressure: ICC=0.91), with highly consistent classification ( Kappa=0.74). Conclusions:Artificial right arm blood pressure measurement in physical examinations may overestimate the hypertension detection rate, and the standardized dual-arm synchronized blood pressure measurement using CCBPM can reduce irregular blood pressure measurement.

Aim To investigate the regulatory mecha-nisms of donepezil on the expression and enzymatic ac-tivity of cytochrome P450 3A4(CYP3A4),elucidate the synergistic impact of hypoxia on CYP3A4 function,and reveal its potential association with drug-induced cardiotoxicity,particularly QT interval prolongation.Methods Western blot,co-immunoprecipitation,and gene knockdown techniques were employed to evaluate the effects of donepezil and hypoxia on CYP3A4 pro-tein expression.CYP3A4 enzymatic activity was as-sessed using an in vitro incubation system with rat liver microsomes combined with high-performance liquid chromatography(HPLC),and the half-maximal inhib-itory concentration(IC50)was determined.Results Donepezil(10 μmol·L-1)and hypoxia reduced CYP3A4 protein expression to 31.75％and 45.90％of the control levels,respectively.Both interventions activated the gp78-mediated ubiquitin-proteasome path-way,significantly increasing CYP3A4 ubiquitination levels by 2.1-fold compared to the control group,thereby promoting proteasomal degradation.Donepezil inhibited CYP3A4 enzyme activity with an IC50 of 83.4μmol·L-1,and hypoxia synergistically enhanced this inhibitory effect,reducing the IC50 to 20.79 μmol·L-1.Conclusion Donepezil downregulates CYP3A4 function through dual mechanisms involving ubiquitin-mediated proteasomal degradation and direct enzymatic inhibition.Hypoxia potentiates this effect,leading to impaired metabolism of CYP3A4 substrate drugs,ele-vated plasma drug concentrations(1.6-2.3-fold in-crease compared to normal metabolic conditions),and an increased risk of QT interval prolongation and other forms of cardiotoxicity.

AIM To study the chemical constituents from the buds of Aralia chinensis L.var.nuda Nakai and their in vitro anti-inflammatory activities.METHODS The 70％ethanol extract from the buds of A.chinensis var.nuda was isolated and purified by silica gel,Sephadex LH-20,ODS and semi-preparative HPLC,then the structures of compounds were identified by physicochemical properties and spectral data.Their anti-inflammatory activities in vitro were evaluated by RAW264.7 model.RESULTS Sixteen compounds were isolated and identified as 4-(2,2-dibutoxyethyl)phenol(1),trans-linalool-3,7-oxide-6-O-β-D-glucopyranoside(2),2'-O-(9Z,12Z,15Z-octadecatrienoyl)glyceryl β-D-galactopyranoside(3),quercetin-3-O-β-D-glucopyranoside(3'→ O-3''')quercetin-3-O-β-D-galactopyranoside(4),syringaresinol-4'-O-β-D-glucopyranoside(5),p-hydroxybenzaldehyde(6),7α-hydroxystigmasterol 3-O-β-D-glucopyranoside(7),trans-p-hydroxy cinnamic acid methyl ester(8),funingensin A(9),3,4-dihydroxy-acetophenone(10),N-acetyltyramine(11),3,4-di-O-caffeoyl quinic acid(12),chlorogenic acid(13),aralia cerebroside(14),caffeic acid methyl ester(15),tetradecanoic acid(16).The IC50values of compounds 8,10,12 and 13 were(22.19±1.59),(35.25±1.30),(13.38±0.72),(15.73±1.16)μmol/L,respectively.CONCLUSION Compound 1 is a new compound,2-13 are isolated from genus Aralia for the first time.Compounds 8,10,12,13 exhibit significant in vitro anti-inflammatory activities.

Objective To explore the validity and feasibility of the left transthoracic and esophageal hiatal approach for Siewert type Ⅱ adenocarcinoma of the esophagogastric junction under a single position.Methods The clinical data of 64 patients with Siewert type Ⅱ AEG(single position transthoracic approach group)treated with the left transthoracic and esophageal hiatal approach under a single position and 56 patients with the laparoscopic transesophageal slit approach(transabdominal approach group)in the Department of Thoracic Surgery,Huaihe Hospital of Henan University,from January 2017 to December 2018 were retrospectively analyzed.The clinical and pathological data,perioperative indicators(operation time,intraoperative blood loss,postoperative first ambulation time,postoperative first peristalsis time,postoperative drainage volume at 3 d,incidence of postoperative complications,postoperative hospital stay),postoperative complications(positive surgical margin,proximal esophageal resection margin,tumor diameter,total number of dissected lymph nodes,positive lymph node dissection rate,postoperative histopathology,and TNM staging of tumor pathology),and survival indicators(tumor recurrence and metastasis rate and survival at 1 month,3 months,6 months,1 year,3 years,5 years after surgery)were compared between the two groups.Kaplan-Meier method was used to analyze the postoperative survival rate of the two groups.Univariate analysis using χ2 test was employed to analyze factors influencing 5-year postoperative survival rate in Siewert type Ⅱ AEG patients.Results No significant difference was observed in clinical and pathological data,such as gender,age,American Society of Anesthesiologists(ASA)grade,tumor differentiation,pTNM stage,and tumor diameter between the two groups(P>0.05).No significant differences were noted in intraoperative blood loss,incidence of postoperative complications,and survival rates at 1 month,3 months,6 months,1 year,and 3 years after surgery between the two groups(P>0.05).The single position transthoracic approach group exhibited a higher postoperative drainage volume at 3 d compared to the transabdominal approach group(P<0.001),a shorter surgical time(P<0.001),a longer time to first mobilization,first intestinal peristalsis,and hospital stay after surgery(P<0.01),a longer proximal esophageal margin(P<0.001),a higher total number of lymph node dissections(P<0.001),and a higher positive lymph node dissection rate(P<0.05)than the transabdominal approach group.The 5-year recurrence-free survival rate of the single position transthoracic approach group was higher than that of the transabdominal approach group,with a statistically significant difference(P=0.013).The Kaplan-Meier survival curve showed no statistically significant difference in the 5-year overall survival rate between the two groups of patients after surgery(P=0.456).The results of univariate analysis indicated that there are significant relationships between tumor differentiation degree,pTNM stage,tumor diameter,and lymph node positivity rate with the 5-year postoperative survival rate in Siewert type Ⅱ AEG patients(P<0.05).Conclusion Siewert type Ⅱ AEG patients can be treated with the left transthoracic and esophageal hiatal approach under a single position,achieving the same effect as laparoscopic transesophageal slit approach,and it can be actively promoted as a complementary choice of operation in the clinic.