Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces. Here we have developed a deep learning algorithm, GPT2 Ion Channel Classifier (GPT2-ICC), which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins. GPT2-ICC integrates representation learning with a large language model (LLM)-based classifier, enabling highly accurate identification of potential ion channels. Several potential ion channels were predicated from the unannotated human proteome, further demonstrating GPT2-ICC's generalization ability. This study marks a significant advancement in artificial-intelligence-driven ion channel research, highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data. Moreover, it provides a valuable computational tool for uncovering previously uncharacterized ion channels.

Current experimental and computational methods have limitations in accurately and efficiently classi-fying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set con-taining approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC's generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.

Purpose/Significance To study the extraction method of adverse drug event(ADE)data from medical texts,and to pro-vide support for clinical drug risk management and scientific decision-making.Method/Process Based on pre-trained model,by com-bining the correlation between the two subtasks of entity recognition and relation extraction,a entity relation joint extraction method for ADE monitoring is designed.Result/Conclusion Experiments on the published ADE extraction dataset show that the proposed method is superior to existing methods and can effectively extract ADE information and its relation from medical texts,providing a powerful means for the discovery and monitoring of ADE.

The current interdisciplinary research on traditional Chinese medicine （TCM） often comes from the simple combination of TCM application needs and mature engineering technology. Actually， higher goal of cross-disciplinary research should be the win-win development of TCM and interdisciplinary majors. In detail， to enhance the innovative development of original thinking mode of TCM， meanwhile， to stimulate the innovation of interdisciplinary majors with medical tasks. Previously， we successfully performed the research on the objective representation of pre-disease and disease state of dyslipidemia in population with phlegm-dampness constitution. Taking this project as an example， this paper discusses the methodology on scientific issue positioning， key medical tasks selection， interdisciplinary theory， and technology exploration， to expounds the research design and ideas which could be generalized in other cross-disciplinary research of TCM.

Objective:To summarize the evidence of cognitive training in breast cancer patients with chemotherapy-related cognitive impairment, so as to provide evidence-based evidence for clinical decision-making and practice.Methods:The literature about the relevant cognitive training in breast cancer patients with chemotherapy-related cognitive impairment were searched for CNKI, VIP database, Wanfang, SinoMed, PubMed, Web of Science, CINAHL, Embase, Cochrane Library, JBI as well as home and abroad official website of relevant professional institutes, including clinical decisions, guidelines, evidence summaries, systematic reviews, best practice information manuals, expert consensuses, and high-quality original studies. The literature retrieval period was from the database construction to March 1, 2023. Two researchers screened and evaluated the quality of the included literature, and extracted, generalized and summarized evidence according to the topic.Results:A total of 17 articles were involved, including 3 clinical decisions, 4 guidelines, 2 evidence summaries, and 8 systematic reviews. Finally, 6 evidence topics and 25 pieces of best evidences were formed, including screening and evaluation, training principles, training time, training place, training content, training effect.Conclusions:Cognitive training can effectively improve cognitive function in breast cancer patients with chemotherapy-related cognitive impairment. Medical staff should carefully select the best evidence, early screen and dynamically evaluate the cognitive changes of patients, follow the principle of step by step and dynamic adjustment, and carry out individualized cognitive training as soon as possible according to the treatment cycle and patients wishes, so as to prevent or delay chemotherapy-related cognitive impairment and improve the quality of life of patients.

Objective:To analyze the research hotspots of self-management in patients with chronic obstructive pulmonary disease (COPD) at home and abroad.Methods:Related literature on self-management of COPD patients were searched in China National Knowledge Infrastructure and Web of Science databases, and the searched period was from January 1, 2013 to June 30, 2023. CiteSpace 5.8 software was used for keyword cluster analysis.Results:A total of 641 articles in Chinese and 1 192 in English were obtained. Domestic research hotspots about self-management of COPD patients mainly focused on health education, continuing care, rehabilitation care, etc. Foreign research hotspots about self-management of COPD patients mainly focused on mobile health, telemedicine and so on.Conclusions:This paper analyzes the research hotspots of self-management of COPD patients at home and abroad and provides reference for future research on self-management of COPD patients.

Objective:To retrieve, evaluate, and summarize the best domestic and international evidence on non-pharmacological management of sleep disorders in breast cancer patients undergoing chemotherapy, providing evidence-based guidance for healthcare professionals to conduct standardized assessment and management of sleep disorders in these patients.Methods:Clinical questions were translated into evidence-based questions using the PIPOST model. A systematic search of domestic and international databases and professional association websites was conducted for literature related to non-pharmacological management of sleep disorders in breast cancer patients undergoing chemotherapy, including clinical decisions, evidence summaries, guidelines, and systematic reviews. The search covered publications up to December 17, 2022. Two researchers trained in evidence-based nursing independently completed the quality assessment, evidence extraction, and summary of the included literature.Results:A total of 16 publications were included, comprising two clinical decisions, one evidence summary, five guidelines, six systematic reviews, and two randomized controlled studies. The best evidence was summarized from seven aspects: multidisciplinary collaboration, identification of risk factors, assessment and monitoring, referral, psychological behavioral interventions, exercise management, and complementary therapies, resulting in 25 key recommendations.Conclusions:This study summarizes the current best evidence for non-pharmacological management of sleep disorders in breast cancer patients undergoing chemotherapy. Healthcare professionals can follow these best evidence practices to standardize the assessment of patient sleep disorder symptoms and choose appropriate intervention plans based on clinical context and patient preferences, thereby improving patient sleep quality.

Objective:To investigate imaging characteristics of papulopustular rosacea (PPR) by high-frequency ultrasound combined with color Doppler flow imaging.Methods:From August 2021 to August 2022, 30 patients with PPR were enrolled from the Department of Dermatology, the First Affiliated Hospital of Baotou Medical College in the Inner Mongolia Autonomous Region, and 30 healthy volunteers served as controls. The 22-MHz high-frequency ultrasound combined with color Doppler blood flow imaging was performed to measure the skin thickness, echo and blood flow parameters at the cheek, and the ultrasound results were compared between the two groups. Comparisons between groups were conducted by using t test or chi-square test. The diagnostic value was analyzed using the area under the curve (AUC) in the receiver operating characteristic (ROC) curve. Results:In the case group, there were 12 males and 18 females, and their ages ranged from 22 to 65 years (42.3 ± 12.8 years) ; in the control group, there were 10 males and 20 females, and their ages ranged from 24 to 62 years (41.0 ± 8.4 years) . The epidermal and dermal thicknesses at the cheek were significantly higher in the case group (132.64 ± 12.29 μm, 1 812.29 ± 85.52 μm, respectively) than in the control group (104.34 ± 14.45 μm, 1 671.77 ± 146.55 μm, respectively, both P < 0.05) . High-frequency ultrasound images showed that the case group was mainly characterized by irregular hypoechoic areas in the cheek dermis (80%) , while banded moderately echoic areas were common in the cheek dermis in the control group (90%) ; subepidermal low-echogenic bands and dermal irregular hypoechoic areas were more likely to appear in the case group than in the control group (93.33% vs. 43.33%, 80% vs. 10%, respectively, both P < 0.001) . Compared with the control group, the case group showed a significantly increased proportion of patients with abundant blood flow signals (93.3% vs. 10%, P < 0.05) , and significantly increased blood vessel diameters (1.60 ± 0.42 mm vs. 0.95 ± 0.32 mm, P < 0.05) ; there was no significant difference in peak systolic blood flow velocity and vascular resistance index between the two groups (both P > 0.05) . The AUC of high-frequency ultrasound combined with color Doppler flow imaging quantitative parameters (including epidermal thicknesses, dermal thicknesses, and blood vessel diameters) was 0.989 (95% CI: 0.970 - 1.000) for the diagnosis of PPR, and the sensitivity and specificity were both 96.7%, which were higher than those of single parameter-based diagnostic model. Conclusion:High-frequency ultrasound combined with color Doppler flow imaging can help improve the accuracy of the diagnosis of PPR, by accurately and non-invasively measuring skin thickness and blood flow parameters.

BACKGROUND: Limited data are available on the comparison of clinical outcomes of complete vs. incomplete percutaneous coronary intervention (PCI) for patients with chronic total occlusion (CTO) and multi-vessel disease (MVD). The study aimed to compare their clinical outcomes. METHODS: A total of 558 patients with CTO and MVD were divided into the optimal medical treatment (OMT) group ( n = 86), incomplete PCI group ( n = 327), and complete PCI group ( n = 145). Propensity score matching (PSM) was performed between the complete and incomplete PCI groups as sensitivity analysis. The primary outcome was defined as the occurrence of major adverse cardiovascular events (MACEs), and unstable angina was defined as the secondary outcome. RESULTS: At a median follow-up of 21 months, there were statistical differences among the OMT, incomplete PCI, and complete PCI groups in the rates of MACEs (43.0% [37/86] vs. 30.6% [100/327] vs. 20.0% [29/145], respectively, P = 0.016) and unstable angina (24.4% [21/86] vs. 19.3% [63/327] vs. 10.3% [15/145], respectively, P = 0.010). Complete PCI was associated with lower MACE compared with OMT (adjusted hazard ratio [HR] = 2.00; 95% confidence interval [CI] = 1.23-3.27; P = 0.005) or incomplete PCI (adjusted HR = 1.58; 95% CI = 1.04-2.39; P = 0.031). Sensitivity analysis of PSM showed similar results to the above on the rates of MACEs between complete PCI and incomplete PCI groups (20.5% [25/122] vs. 32.6% [62/190], respectively; adjusted HR = 0.55; 95% CI = 0.32-0.96; P = 0.035) and unstable angina (10.7% [13/122] vs. 20.5% [39/190], respectively; adjusted HR = 0.48; 95% CI = 0.24-0.99; P = 0.046). CONCLUSIONS For treatment of CTO and MVD, complete PCI reduced the long-term risk of MACEs and unstable angina, as compared with incomplete PCI and OMT. Complete PCI in both CTO and non-CTO lesions can potentially improve the prognosis of patients with CTO and MVD.
Humans ; Treatment Outcome ; Percutaneous Coronary Intervention/methods* ; Coronary Occlusion/surgery* ; Prognosis ; Angina, Unstable/surgery* ; Chronic Disease ; Risk Factors

Objective:To explore the mechanism of Xijiao Dihuang Ddecoction (XJDHT) against sepsis-induced liver injury based on transcriptomics.Methods:Sixty C57BL/6 mice were randomly (random number) divided into the sepsis group, sepsis treatment with XJDHT and control group, with 20 mice in each group. The sepsis mouse model was established by intraperitoneal (i.p.) injection of lipopolysaccharide (LPS). The control group was intraperitoneally injected with the same amount of normal saline. The sepsis treatment with XJDHT group was injected with XJDHT (crude drug 187.5 mg) twice a day 2 days before modeling. After modeling, gastric feeding was continued twice a day, while the control group and sepsis group were gavaged with the same amount of normal saline. At 72 h after LPS intervention, 9 mice in each group were randomly selected. After anesthesia, part of the liver were taken for small RNA and RNA sequencing and analysis, and part of the liver were taken for pathological examination.Results:XJDHT could improve the histopathological changes of liver in septic mice, and alleviate some abnormally expressed microRNAs (mmu-mir-292a-5p, mmu-mir-871-3p, mmu-mir-653-5p, mmu-mir-293-5p, mmu-mir-155-3p, mmu-mir-346-5p, mmu-mir-187-5p, mmu-mir-3090-3p) and their target genes.Conclusions:XJDHT can reduce the liver histopathological changes in septic mice, and its mechanism may be related to XJDHT regulating the expression of important key genes of liver of sepsis like mmu-mir-187-5p and its target genes such as ADAM8, irak3 and PFKFB3