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.

This study was aimed at establishing a method of ultra-fast quantitative PCR for Brucella detection.We used an exogenous recombinant plasmid as the internal reference and targeted the T4SS secretion system,an important Brucella viru-lence factor,to design specific primers and probes.The sensitivity,specificity,and repeatability of this method were evaluated,and a standard curve was constructed.The coincidence rate of detection findings with this method versus quantitative PCR was determined.This method markedly decreased the detection time to only 10 minutes.The standard curve demonstrated a good linear relationship(Y=-3.410 7x+38.357,R2=0.998 5)with a low minimum detection limit of 10 copies/μL.The method exhibited good specificity and did not specifically amplify several common clinical bacteria other than Brucella.The de-tection of three concentrations of positive plasmids yielded coefficients of variation(CVs)of 0.20％to 0.91％,thus demonstra-ting the method's excellent repeatability.Furthermore,140 clinical samples were analyzed concurrently with the fluorescence PCR method,which yielded a 100％compliance rate and consistent results.Our findings indicated that the Brucella ultra-fast quantitative PCR was ultrafast;had high sensitivity,high specificity,and good specificity;and can be used for the clinical de-tection of Brucella and emergency investigation of epidemics.Therefore,this method is valuable for the early diagnosis of Bru-cella.

OBJECTIVE: To explore clinical efficacy of autologous platelet-rich plasma(PRP) in treating Rockwood type Ⅲ acromioclavicular dislocation. METHODS: From January 2019 to July 2021, 32 patients with Rockwood type Ⅲ acromioclavicular dislocation were treated with minimally invasive adjustable titanium plate internal fixation, and were divided into PRP group and control group according to whether PRP treatment was performed, with 16 patients in each group. In PRP group, there were 10 males and 6 females, aged from 28 to 47 years old with an average of (36.75±7.14) years old;the time from injury to surgery ranged from 1 to 31 h with an average of (26.13±3.98) h;5 patients on the left side and 11 patients on the right side;PRP was injected once during operation and the 4th and 8th weeks after operation respectively. In control group, there were 8 males and 8 females, aged from 30 to 52 years old with an average of (38.50±5.48) years old; the time from injury to surgery ranged from 1 to 29 h with an average of (25.48±3.11) h;7 patients on the left side and 9 patients on the right side; minimally invasive surgical treatment was performed. Visual analogue scale(VAS) was used to evaluate pain and Constant-Murley score for shoulder joint function was used to evaluate the recovery of shoulder joint movement function before operation and 1, 3, 6, and 12 months after operation respectively. RESULTS: All patients were followed up for 12 to 28 months with an average of (18.3±5.2) months. All incisions patients healed well without adverse events such as infection. Postoperative VAS of PRP group at 1, 3, and 6 months were (5.5±1.2), (3.7±1.6), and (2.4±1.2), respectively, while were lower than those of control group (6.6±1.4), (4.9±1.1), and (3.7±1.3), respectively;and had statistical differences between two groups (P<0.05). There was no statistically significant difference in VAS between two groups before operation and 12 months after operation (P>0.05). Postoperative Constant-Murley scores of PRP group at 1, 3, and 6 months were (64.09±11.61), (73.19±12.89), and (82.61±14.81) points, respectively, which were higher than those of control group were (52.32±17.42), (61.65±14.43), and (72.52±11.04) respectively;and the differences were statistically significant (P<0.05). There was no statistically significant difference in Constant-Murley scores at 12 months after operation between two groups (P>0.05). In PRP group, there was no statistically significant difference at 6 months and 12 months after operation (P>0.05), while there were statistically significant differences at the other time points (1 month after operation compared with before operation, 3 months after operation compared with 6 months after operation, and 3 months after operation compared with 1 month after operation) (P<0.05). In control group, there was no statistically significant difference when comparing 1 month and 3 months after operation (P>0.05), while at the other time points (1 month after operation with before operation, 3 months after operation with 6 months after operation, and 6 months after operation with 12 months after operation), the differences were all statistically significant (P<0.05). CONCLUSION Adjustable titanium plate fixation combined with postoperative injection of PRP for the treatment of Rockwood type III acromioclavicular joint dislocation has effect of promoting the recovery of shoulder joint function and reducing pain.
Humans ; Male ; Female ; Adult ; Middle Aged ; Platelet-Rich Plasma ; Acromioclavicular Joint/surgery* ; Bone Plates ; Titanium ; Joint Dislocations/therapy* ; Fracture Fixation, Internal/methods*

OBJECTIVES: To assess the preliminary efficacy and safety of a dose-intensified C5VD regimen (cisplatin, 5-fluorouracil, vincristine, and doxorubicin) in children with locally advanced hepatoblastoma. METHODS: This prospective study enrolled 24 children with newly diagnosed, locally advanced hepatoblastoma who received the dose-intensified C5VD regimen at Shanghai Children's Medical Center, Shanghai Jiao Tong University School of Medicine, and Shanghai Children's Hospital between January 2020 and December 2023. Clinical characteristics, treatment outcomes, and chemotherapy-related toxicities were analyzed. RESULTS: Of the 24 patients, 13 were male and 11 were female, with a median age at diagnosis of 18.7 months (range: 3.5-79.4 months). All patients achieved complete macroscopic resection of hepatic lesions without liver transplantation. Serum alpha-fetoprotein levels decreased significantly after two chemotherapy cycles. During a median follow-up of 38.4 months (range: 15.8-50.7 months), all patients maintained continuous complete remission, with 3-year event-free survival and overall survival rates of 100%. Across 144 chemotherapy cycles, the incidence rates of grade 3-4 neutropenia, thrombocytopenia, and infections were 97%, 77%, and 71%, respectively; no treatment-related deaths occurred. Notably, 5 patients (21%) developed Brock grade ≥3 hearing loss, of whom 1 required a hearing aid. CONCLUSIONS The dose-intensified C5VD regimen demonstrates significant efficacy with an overall favorable safety profile in the treatment of newly diagnosed, locally advanced pediatric hepatoblastoma. Grade 3-4 myelosuppression and infection are the predominant toxicities. However, high‑dose cisplatin-induced ototoxicity remains a concern, highlighting the need for improved otoprotective strategies.
Humans ; Hepatoblastoma/pathology* ; Male ; Female ; Infant ; Liver Neoplasms/pathology* ; Antineoplastic Combined Chemotherapy Protocols/therapeutic use* ; Child, Preschool ; Prospective Studies ; Doxorubicin/adverse effects* ; Child ; Cisplatin/adverse effects* ; Vincristine/adverse effects* ; Fluorouracil/adverse effects*

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]

This study was aimed at establishing a method of ultra-fast quantitative PCR for Brucella detection.We used an exogenous recombinant plasmid as the internal reference and targeted the T4SS secretion system,an important Brucella viru-lence factor,to design specific primers and probes.The sensitivity,specificity,and repeatability of this method were evaluated,and a standard curve was constructed.The coincidence rate of detection findings with this method versus quantitative PCR was determined.This method markedly decreased the detection time to only 10 minutes.The standard curve demonstrated a good linear relationship(Y=-3.410 7x+38.357,R2=0.998 5)with a low minimum detection limit of 10 copies/μL.The method exhibited good specificity and did not specifically amplify several common clinical bacteria other than Brucella.The de-tection of three concentrations of positive plasmids yielded coefficients of variation(CVs)of 0.20％to 0.91％,thus demonstra-ting the method's excellent repeatability.Furthermore,140 clinical samples were analyzed concurrently with the fluorescence PCR method,which yielded a 100％compliance rate and consistent results.Our findings indicated that the Brucella ultra-fast quantitative PCR was ultrafast;had high sensitivity,high specificity,and good specificity;and can be used for the clinical de-tection of Brucella and emergency investigation of epidemics.Therefore,this method is valuable for the early diagnosis of Bru-cella.

Objective To investigate the risk factors for pneumonia complicating infectious mononucleosis(IM)in adults and construct a nomogram prediction model.Methods A retrospective analysis was conducted on 198 IM patients admitted to the Second Affiliated Hospital of Air Force Medical University from January 2015 to December 2021.Patients were divided into pneumonia group(n=52)and non-pneumonia group(n=146)based on whether pulmonary infection occurred during hospitalization.The baseline data(age,gender,place of onset,etc.),clinical manifestations(maximum body temperature,lymph node enlargement,splenomegaly,etc.),and inflammatory indicators[white blood cell count(WBC),C-reactive protein(CRP),etc.]were compared between the two groups.Kaplan-Meier curves were plotted to analyze the key indicators affecting the hospital stay of IM patients.Multivariate logistic regression was used to analyze the independent risk factors for pneumonia complicating IM in adults and construct a nomogram prediction model based on the identified risk factors.The predictive efficacy of the model was evaluated using the receiver operating characteristic(ROC)curve and the consistency of the model was assessed using the calibration curve.The fit of the model was evaluated using the Hosmer-Lemeshow test.Additionally,the sensitivity,specificity,and accuracy of the model were assessed using confusion matrix.Results Compared with non-pneumonia group,the pneumonia group had a significantly higher proportion of patients from rural areas,with body mass index(BMI)≥24 kg/m2,smoking history,hepatomegaly,fever duration of≥7 d,as well as increased total hospitalization costs and average daily hospitalization costs,and prolonged hospital stay(P<0.05).The proportion of patients with a history of antibiotic use was lower in the pneumonia group(P<0.05).Kaplan-Meier survival analysis showed that patients from rural areas,with BMI≥24 kg/m2,smoking history,no prophylactic use of antibiotics,fever duration≥7 d,and hepatomegaly had significantly prolonged hospital stays(P<0.05).Multivariate logistic regression analysis revealed that living in a rural area(OR=4.089,P<0.05),hepatomegaly(OR=4.082,P<0.05),and elevated WBC(OR=1.205,P<0.05)were independent risk factors for pneumonia complicating IM in adults,while the prophylactic use of antibiotics(OR=0.142,P<0.05)was an independent protective factor.The area under the ROC curve of the constructed nomogram prediction model was 0.827(95%CI 0.762-0.892),and the slope of the calibration curve was close to 1,and the Hosmer-Lemeshow test showed χ2=5.299,P=0.725,indicating good consistency and fit of the prediction model.The results of the confusion matrix assessment showed that the sensitivity of the model was 0.669(0.624-0.773),the specificity was 0.827(0.724-0.930),and the accuracy was 0.732(0.665-0.793).Conclusion The nomogram prediction model based on place of onset,hepatomegaly,the prophylactic use of antibiotics and WBC has excellent fit and discrimination,providing an effective quantitative tool for prognosis assessment of IM.

Nonunion of osteoporotic vertebral fractures (OVF), predominantly affecting the elderly, can lead to intractable pain, vertebral collapse, progressive kyphotic deformity, and neurological impairment, significantly compromising patients′ quality of life. There exists considerable debate on diagnosis and management of OVF, encompassing key issues such as clinical diagnosis and staging criteria for nonunion, surgical indications and procedure selection, and postoperative rehabilitation planning. Currently, there lacks standardized clinical guideline and expert consensus on the diagnosis and management of OVF nonunion in China. To address this gap, Minimally Invasive Surgery Group of Chinese Orthopedic Association, Osteoporosis Committee of Chinese Association of Orthopedic Surgeons, Prevention and Rehabilitation Committee for Osteoporosis of Chinese Association of Rehabilitation Medicine and Minimally Invasive Orthopedic Surgery Branch of China Association for Geriatric Care jointly organized domestic experts in spinal surgery, endocrinology, and rehabilitation to formulate the Clinical guideline for the diagnosis and treatment for nonunion of osteoporotic vertebral fractures ( version 2025), based on existing literature and clinical experience and adhering to principles of scientific rigor and practicality. The guideline provided 13 evidence-based recommendations encompassing diagnosis and treatment of OVF nonunion, aiming to standardize its clinical management.

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]