Accurate prediction of drug-target interactions (DTIs) plays a pivotal role in drug discovery, facilitating optimization of lead compounds, drug repurposing and elucidation of drug side effects. However, traditional DTI prediction methods are often limited by incomplete biological data and insufficient representation of protein features. In this study, we proposed KG-CNNDTI, a novel knowledge graph-enhanced framework for DTI prediction, which integrates heterogeneous biological information to improve model generalizability and predictive performance. The proposed model utilized protein embeddings derived from a biomedical knowledge graph via the Node2Vec algorithm, which were further enriched with contextualized sequence representations obtained from ProteinBERT. For compound representation, multiple molecular fingerprint schemes alongside the Uni-Mol pre-trained model were evaluated. The fused representations served as inputs to both classical machine learning models and a convolutional neural network-based predictor. Experimental evaluations across benchmark datasets demonstrated that KG-CNNDTI achieved superior performance compared to state-of-the-art methods, particularly in terms of Precision, Recall, F1-Score and area under the precision-recall curve (AUPR). Ablation analysis highlighted the substantial contribution of knowledge graph-derived features. Moreover, KG-CNNDTI was employed for virtual screening of natural products against Alzheimer's disease, resulting in 40 candidate compounds. 5 were supported by literature evidence, among which 3 were further validated in vitro assays.
Alzheimer Disease/drug therapy* ; Biological Products/therapeutic use* ; Humans ; Neural Networks, Computer ; Machine Learning ; Drug Discovery/methods* ; Algorithms ; Drug Evaluation, Preclinical/methods*

[Abtract]Nursing safety management is crucial to patient health outcomes,and real-time monitoring and early warning systems play a vital role in enhancing nursing safety and reducing medical incidents.Wearable flexible devices enable non-invasive,continuous monitoring of various physiological parameters and provide timely alerts.These devices not only improve the efficiency and quality of nursing safety management but also offer patients more convenient,accurate,and personalized care services.This article provides a comprehensive review of the application of wearable flexible devices in nursing safety management,examining their application scenarios,advantages,and challenges,and offering insights to facilitate the further integration of this technology into nursing safety practices.

[Objective]To explore the epidemiology and clinical characteristics of kala-azar patients in Kashgar region,so as to improve the diagnosis and treatment.[Methods]A retrospective analysis was conducted on the clinical data of 71 kala-azar patients admitted to the First People's Hospital of Kashgar Region between January 2013 and December 2023.[Results]Among the 71 patients,the majority were aged 0-5 years(52.11%,37/71),with a male-to-female ratio of 0.92:1.Most cases occurred in winter and spring.Common clinical manifestations included fever,fatigue,decreased appetite,splenomegaly and hepatomegaly.Laboratory investigations mainly found pancytopenia,reversed albumin-to-globulin ratio,elevated transaminases,and increased C-reactive protein and procalcitonin.The positive rates of anti-rK39 antibody detection and bone marrow microscopy were 100%(23/23)and 91.38%(53/58),respectively.Metagenomics next-generation sequencing(mNGS)of liver tissue identified Leishmania donovani in one case.The common complications were infectious toxic hepatitis 49.30%(35/71),myocarditis 29.56%(21/71),and bronchopneumonia 23.94%(17/71).[Conclusions]Potential kala-azar should be taken into consideration for patients from the endemic areas with long-term irregular fever accompanied by splenomegaly,hemocytopenia,and reversed albumin-to-globulin ratio.Bone marrow smear microscopy and anti-rK39 antibody detection are recommended for the diagnosis,and mNGS provides a novel diagnostic solution.

Objective:To analyze the effects of different psychological interventions on cancer patients' fear of cancer recurrence(FCR).Methods:Randomized controlled trials examining the effects of various psychological interventions on FCR among cancer patients were searched for in both Chinese and English literature databases.A network meta-analysis was conducted to explore the intervention effects,utilizing standardized mean difference(SMD),95％confidence interval(CI),and surface under the cumulative ranking(SUCRA)of FCR as the effect indicators.Results:A total of 34 studies involving 3 772 participants were included,of which five types of psycho-logical interventions were evaluated,namely acceptance and commitment therapy(ACT),gratitude-expansion thera-py(GET),cognitive behavioral therapy(CBT),mindfulness therapy(MT),and multi-component psychological in-tervention(Mul).According to the time of effect evaluation,three effect evaluation timing were confirmed,with immediate post-intervention group,1-2 months post-intervention group,and 3-6 months post-intervention group identified.Compared with conventional care,in the immediate post-intervention group,ACT(SMD=-1.80,95％CI:-2.47--1.13),GET(SMD=-1.33,95％CI:-2.07--0.59),MT(SMD=-0.59,95％CI:-1.03--0.14)and CBT(SMD=-0.54,95％CI:-0.93--0.15)could effectively reduce FCR,and the SUCRA val-ue of ACT was upmost to 0.96.In the 1-2 months post-intervention group,GET(SMD=-2.32,95％CI:-2.99--1.65)and ACT(SMD=-1.46,95％CI:-2.23--0.70)could effectively reduce FCR,and the SUCRA value of GET was upmost to 0.99.In the 3-6 months post-intervention group,Mul(SMD=-1.82,95％CI:-3.03--0.61)and MT(SMD=-1.43,95％CI:-2.33--0.54)could effectively reduce FCR,and the SU-CRA value of Mul was upmost to 0.90.Conclusion:Different psychological interventions vary in their effectiveness on FCR across effect evaluation time points,highlighting the need for tailored approaches on mitigating FCR in clin-ical practice.

[Abtract]Nursing safety management is crucial to patient health outcomes,and real-time monitoring and early warning systems play a vital role in enhancing nursing safety and reducing medical incidents.Wearable flexible devices enable non-invasive,continuous monitoring of various physiological parameters and provide timely alerts.These devices not only improve the efficiency and quality of nursing safety management but also offer patients more convenient,accurate,and personalized care services.This article provides a comprehensive review of the application of wearable flexible devices in nursing safety management,examining their application scenarios,advantages,and challenges,and offering insights to facilitate the further integration of this technology into nursing safety practices.

Objective:To analyze the effects of different psychological interventions on cancer patients' fear of cancer recurrence(FCR).Methods:Randomized controlled trials examining the effects of various psychological interventions on FCR among cancer patients were searched for in both Chinese and English literature databases.A network meta-analysis was conducted to explore the intervention effects,utilizing standardized mean difference(SMD),95％confidence interval(CI),and surface under the cumulative ranking(SUCRA)of FCR as the effect indicators.Results:A total of 34 studies involving 3 772 participants were included,of which five types of psycho-logical interventions were evaluated,namely acceptance and commitment therapy(ACT),gratitude-expansion thera-py(GET),cognitive behavioral therapy(CBT),mindfulness therapy(MT),and multi-component psychological in-tervention(Mul).According to the time of effect evaluation,three effect evaluation timing were confirmed,with immediate post-intervention group,1-2 months post-intervention group,and 3-6 months post-intervention group identified.Compared with conventional care,in the immediate post-intervention group,ACT(SMD=-1.80,95％CI:-2.47--1.13),GET(SMD=-1.33,95％CI:-2.07--0.59),MT(SMD=-0.59,95％CI:-1.03--0.14)and CBT(SMD=-0.54,95％CI:-0.93--0.15)could effectively reduce FCR,and the SUCRA val-ue of ACT was upmost to 0.96.In the 1-2 months post-intervention group,GET(SMD=-2.32,95％CI:-2.99--1.65)and ACT(SMD=-1.46,95％CI:-2.23--0.70)could effectively reduce FCR,and the SUCRA value of GET was upmost to 0.99.In the 3-6 months post-intervention group,Mul(SMD=-1.82,95％CI:-3.03--0.61)and MT(SMD=-1.43,95％CI:-2.33--0.54)could effectively reduce FCR,and the SU-CRA value of Mul was upmost to 0.90.Conclusion:Different psychological interventions vary in their effectiveness on FCR across effect evaluation time points,highlighting the need for tailored approaches on mitigating FCR in clin-ical practice.

[Objective]To explore the epidemiology and clinical characteristics of kala-azar patients in Kashgar region,so as to improve the diagnosis and treatment.[Methods]A retrospective analysis was conducted on the clinical data of 71 kala-azar patients admitted to the First People's Hospital of Kashgar Region between January 2013 and December 2023.[Results]Among the 71 patients,the majority were aged 0-5 years(52.11%,37/71),with a male-to-female ratio of 0.92:1.Most cases occurred in winter and spring.Common clinical manifestations included fever,fatigue,decreased appetite,splenomegaly and hepatomegaly.Laboratory investigations mainly found pancytopenia,reversed albumin-to-globulin ratio,elevated transaminases,and increased C-reactive protein and procalcitonin.The positive rates of anti-rK39 antibody detection and bone marrow microscopy were 100%(23/23)and 91.38%(53/58),respectively.Metagenomics next-generation sequencing(mNGS)of liver tissue identified Leishmania donovani in one case.The common complications were infectious toxic hepatitis 49.30%(35/71),myocarditis 29.56%(21/71),and bronchopneumonia 23.94%(17/71).[Conclusions]Potential kala-azar should be taken into consideration for patients from the endemic areas with long-term irregular fever accompanied by splenomegaly,hemocytopenia,and reversed albumin-to-globulin ratio.Bone marrow smear microscopy and anti-rK39 antibody detection are recommended for the diagnosis,and mNGS provides a novel diagnostic solution.

Objective To evaluate the apparent diffusion coefficient(ADC)values of different bone marrow infiltration patterns in multiple myeloma(MM)patients with MR whole-body diffusion weighted imaging(WB-DWI)and to determine the ADC thresholds for different bone marrow infiltration patterns.Methods Nineteen MM patients diagnosed for the first time were selected.The lesions types of each site(cervical spine,ribs,sternum,humerus,scapula,sacral spine,ilium,femur,thoracic spine,and lumbar spine)after the WB-DWI images were visually evaluated,which were divided into focal group(including focal lesion in combined focal and diffuse infiltration)[region of interest(ROI)=141],pure diffuse infiltration group(ROI=150),diffuse lesion in combined focal and diffuse infiltration group(ROI=127),"salt-and-pepper"group(ROI=54),and normal appearance group(ROI=68).ADC values were measured and compared between each group and the receiver operating characteristic(ROC)curve was drawn to distinguish different patterns of bone marrow infiltration.Results There was no statistically significant difference in ADC values between the diffuse lesion in combined focal and diffuse infiltration group and the"salt-and-pepper"group(P＞0.99),and there was statistically significant difference in ADC values between the other groups(P＜0.05).The ROC curve showed that the area under the curve(AUC)for identifying focal group and the"salt-and-pepper"group was 0.889[95％confidence interval(CI)0.844-0.934],the AUC for identifying pure diffuse infiltration group and the normal appearance group was 0.968(95％CI 0.949-0.987).ADC values were able to accurately and visually differentiate between the different patterns of bone marrow infiltration.Conclusion The ADC values can be used as a quantitative tool to objectively distinguish different bone marrow infiltration patterns in MM patients.

Glioma is the most common primary central nervous system tumor,mainly derived from glial cells,with strong invasiveness,easy recurrence,and poor prognosis.Glioblastoma is a high-grade glioma with the highest degree of malignancy.The clinical treatment method is mainly surgical resection,supplemented by compre-hensive treatment such as radiotherapy,chemotherapy,and electric field therapy,but the treatment effect is not satisfactory.In recent years,with the rapid development of the field of tumor immunotherapy,CD73 is a novel immune checkpoint related to adenosine metabolism,which can promote tumor progression by inhibiting anti-tumor immune responses and promoting angiogenesis.This article systematically reviews the mechanism of action of CD73 and discusses its biological role and application in glioma,aiming to provide potential treatment options for glioma patients.