ObjectiveThis study aims to develop and validate a novel multimodal predictive model， termed criss-cross network（CCNet）-directed graph neural network（DGNN）（CGN）， for accurate assessment of pulmonary nodule progression in high-risk individuals for lung cancer， by integrating longitudinal chest computed tomography（CT） imaging with both traditional Chinese and western clinical evaluation data. MethodsA cohort of 4 432 patients with pulmonary nodules was retrospectively analyzed. A twin CCNet was employed to extract spatiotemporal representations from paired sequential CT scans. Structured clinical assessment and imaging-derived features were encoded via a multilayer perceptron， and a similarity-based alignment strategy was adopted to harmonize multimodal imaging features across temporal dimensions. Subsequently， a DGNN was constructed to integrate heterogeneous features， where nodes represented modality-specific embeddings and edges denoted inter-modal information flow. Finally， model optimization was performed using a joint loss function combining cross-entropy and cosine similarity loss， facilitating robust classification of nodule progression status. ResultsThe proposed CGN model demonstrated superior predictive performance on the held-out test set， achieving an area under the receiver operating characteristic curve（AUC） of 0.830， accuracy of 0.843， sensitivity of 0.657， specificity of 0.712， Cohen's Kappa of 0.417， and F₁ score of 0.544. Compared with unimodal baselines， the CGN model yielded a 36%-48% relative improvement in AUC. Ablation studies revealed a 2%-22% increase in AUC when compared to simplified architectures lacking key components， substantiating the efficacy of the proposed multimodal fusion strategy and modular design. Incorporation of traditional Chinese medicine （TCM）-specific symptomatology led to an additional 5% improvement in AUC， underscoring the complementary value of integrating TCM and western clinical data. Through gradient-weighted activation mapping visualization analysis， it was found that the model's attention predominantly focused on nodule regions and effectively captured dynamic associations between clinical data and imaging-derived features. ConclusionThe CGN model， by synergistically combining cross-attention encoding with directed graph-based feature integration， enables effective alignment and fusion of heterogeneous multimodal data. The incorporation of both TCM and western clinical information facilitates complementary feature enrichment， thereby enhancing predictive accuracy for pulmonary nodule progression. This approach holds significant potential for supporting intelligent risk stratification and personalized surveillance strategies in lung cancer prevention.

To understand the distribution of ticks in the Wuwei Region,enrich tick species data,and provide a basis for the prevention of tick-borne diseases,tick were collected using flagging and tick-picking methods during the highest activity period from April to September in 2021 and 2022 in the mountainous areas of Wuwei City.The ticks were identified based on morpho-logical and molecular biological characteristics,and characteristic sequences were obtained.A systematic evolutionary tree was constructed using the neighbor-joining method in MEGA 11.0 software.In total,7 342 ticks collected in Wuwei,which be-longed to 5 species from 4 genera with in the Ixodidae family,which included Dermacentor nuttalli,Hyalomma asiaticum,Ixodes canisuga,Haemaphysalis longicornis and Haema-physalis danieli.Ticks of the same species clustered together into the same branch of an evolutionary tree.In the Wuwei Re-gion,five common tick species are found across various habi-tats,with each habitat featuring different distributions of tick species and populations.The Dermacentor nuttalli is the dom-inant tick species in this area.

This study investigated the prevalence of Borrelia burgdorferi,Anaplasma phagocy tophilum,Rickettsia typhi,Orientia tsutsugamushi,Leptospira interrogans,Francisella tularensis,and Babesia spp.in small mammals in the Qinghai plateau region,to provide a scientific basis for the prevention and control of local zoonotic diseases.Small mammals were cap-tured with snap traps at six sampling sites in the Qinghai plateau region.Liver,spleen,and kidney tissues were collected for detection of six bacterial pathogens with real-time PCR.Conventional PCR(cPCR)was used for Babesia detection,and the positive PCR products were sequenced and analyzed.The differences in pathogen detection rates among species and habitats were analyzed with x2 test or Fisher's exact test.In to-tal,235 small mammals from 15 species were captured.B.burgdorferi,L.interrogans,and Babesia were detected in 11 spe-cies of small mammals,whereas A.phagocytophilum,R.typhi,O.tsutsugamushi,and F.tularensis were not detected.B.burgdorferi was detected in 41 small mammals from nine species(Cricetulus longicaudatus,Apodemus peninsulae,Ochotona curzoniae,Mus m usc ulus,Meriones meridians,Microtus arvalis,Cricetidae,Ochotona cansus,and Allactaga sibirica),with an infection rate of 17.45％(41/235).L.interrogans was detected in eight small mammals from four species(C.longicaudatus,M.musculus,M.arvalis,and Microtus oeconomus),with an infection rate of 3.40％(8/235).Babesia was detected in only one Mustela altaica,with an infection rate of 0.85％(1/235).Statistically significant differences were ob-served in the detection rates of pathogens among small mammal species(x2=200.54,P＜0.05).Among habitats,the detection rate of B.burgdorferi was highest in the forest(Fisher's exact test,P＜0.05).B.burgdorferi and L.interrogans co-infection was observed in three M.arvalis and two C.longicaudatus.In addition,one Babesia sequence was obtained,which clustered with Babesia vulpes in the phylogenetic tree.B.burgdorferi,L.interrogans,and Babesia were the main pathogens prevalent in small mammals in the Qinghai plateau region and have potential to cause human diseases.Local authori-ties should strengthen the surveillance of corresponding zoonotic diseases,and formulate corresponding prevention and control measures.

Objective:To explore the white matter structural characteristics in patients with bipolar disorder(BD)using diffusion tensor imaging(DTI)and investigate their relationship with cognitive function.Methods:A total of 15 patients with BD type Ⅰ and 26 patients with BD type Ⅱ who met the Diagnostic and Statistical Manual of Mental Disorders,Fourth Edition(DSM-Ⅳ)diagnostic criteria and 37 normal controls were included.Cognitive function was assessed with the Trail Making Test(TMT)and Repeatable Battery for the Assessment of Neuropsy-chological Status(RBANS).The tract-based spatial statistics(TBSS)method was used to explore the differences in fractional anisotropy(FA)and mean diffusivity(MD)among the three groups and perform correlation analyses with cognitive function.Results:Patients with BD Ⅰ and BD Ⅱ had lower scores in attention(P＜0.001),delayed memory(P＜0.01),and total scores(P＜0.001)on the RBANS compared to the normal control group.They also exhibited lower FA values in the corpus callosum and right superior corona radiata compared to the normal control group(P＜0.05).In the BD Ⅰ group,there was a positive correlation between FA values in the genu of corpus cal-losum and visuospatial/constructional scores(r=0.74,P＜0.05),while in the BD Ⅱ group,a positive correlation was found between FA values in the same region and language function scores(r=0.55,P＜0.05).Conclusion:It suggests that patients with bipolar disorder may have impaired white matter integrity in the corpus callosum and right superior corona radiata,which may be associated with cognitive impairment.

Coronary heart disease is a physical and mental disease that is often combined with mental disorders such as depression,anxiety,sleep disorders,and stress,affecting the patient's prognosis.This review introduces the common mental disorders of patients with coronary heart disease,the types,characteristics and application status of digital and intelligent intervention technology,and analyzes the challenges of digital and intelligent intervention technology in the development of mental disorders in coronary heart disease,with a view to providing new information technology-driven nursing practice ideas and directions.

Objective:To investigate the impact of ionizing radiation(IR)on the structure and function of the testis and pro-vide some strategies for the prevention and treatment of IR-induced damage(IRD).Methods:Using radiation dose simulation,se-men analysis,hormone testing,electron microscopy and single-cell transcriptome sequencing,we assessed and analyzed a case of IRD.We established a mouse model of IRD to validate the results of single-cell sequencing,and investigated the specific biological mecha-nisms of IRD and potential strategies for its intervention.Results:IR at 1-2 Gy significantly reduced sperm concentration and mo-tility,which gradually recovered after 12 months but the percentage of morphologically normal sperm remained low.It also caused im-balanced levels of various steroid hormones,decreased testosterone and dehydroepiandrosterone sulfate,increased progesterone,prolac-tin,luteinizing hormone,and follicle-stimulating hormone.Electron microscopy revealed damages to the testis structure,including loss of germ cells,atrophy of the seminiferous tubules,nuclear membrane depression of the spermatocytes,mitochondrial atrophy and de-formation,and reduction of mitochondrial cristae.Single-cell sequencing indicated significant changes in the function of the Leydig cells and macrophages and disrupted lipid-related metabolic pathways after IRD.Administration of L-carnitine to the mouse model im-proved lipid metabolism disorders and partially alleviated IRD to the germ cells.Conclusion:Ionizing radiation can cause disorders of testicular spermatogenesis and sexual hormones and inhibit lipid metabolism pathways in Leydig cells and macrophages.Improving lipid metabolism can alleviate IRD to germ cells.

Objective:To investigate the effect of sertraline hydrochloride combined with compound chamomile lidocaine gel in the treatment of premature ejaculation(PE).Methods:We selected 80 cases of PE treated in our hospital from June 2021 to May 2023 and equally randomized them into a control and an observation group,the former medicated with compound chamomile lidocaine gel while the latter with sertraline hydrochloride in addition,both for 6 weeks.We recorded and compared the intravaginal ejaculation latency time(IELT),the number of successful sexual intercourses per week,the Premature Ejaculation Diagnostic Tool(PEDT)scores,and the incidence of adverse reactions between the two groups of patients.Results:After the treatment,the IELT was signif-icantly longer([5.39±1.17]vs[2.49±0.73]min,P＜0.05),the weekly number of successful sexual intercourses remarkably higher(1.82±0.45 vs 0.93±0.19,P＜0.05)and the PEDT scores markedly lower(7.42±2.04 vs 9.85±2.36,P＜0.05)in the observation than in the control group,but no statistically significant differences were observed in the baseline PEDT scores or the incidence of adverse reactions between the two groups(P＞0.05).Conclusion:Sertraline hydrochloride combined with com-pound chamomile lidocaine gel is definitely effective in the treatment of PE,which can significantly improve the patients'quality of sexual life,with a high safety and low incidence of adverse reactions.

Objective To propose a method for classifying small bowel capsule endoscopy images by combining the Swin Transformer network with an improved Adapt-RandAugment data augmentation approach,aiming to enhance the accuracy and efficiency of small bowel lesion classification and recognition.Methods An Adapt-RandAugment data augmentation approach was formulated based on the RandAugment data enhancement sub-strategy and the principles of no feature loss and no distortion when enhancing small bowel capsule endoscopy images.In the publicly available Kvasir-Capsule dataset of small bowel capsule endoscopic images,the Adapt-RandAugment data augmentation approach was trained based on the Swin Transformer network,and the convolutional neural networks ResNet152 and DenseNet161 were used as the benchmarks to validate the combined Swin Transformer network and Adapt-RandAugment data augmentation approach for small bowel capsule endoscopy image classification.Results The proposed algorithm gained advantages over ResNet152 and DenseNet161 networks in the indicators,which had the macro average precision(MAC-PRE),macro average recall(MAC-REC),macro average F1 score(MAC-Fi-S)being 0.383 2,0.314 8 and 0.290 5 respectively,the micro average precision(MIC-PRE),micro average recall(MIC-REC)and micro average F1 score(MIC-Fi-S)all being 0.755 3,and the Matthews correlation coe-fficient(MCC)being 0.452 3.Conclusion The proposed small bowel capsule endoscopy image classification method based on Swin Transformer network and Adapt-RandAugment data augmentation approach behaves well in classified recognition efficiency and accuracy.[Chinese Medical Equipment Journal,2024,45(6):9-16]

Objective To develop an intelligent horizontal rotating cell culture device with high modularity,easy operation,easy disinfection,low cost and high stability.Methods The cell culture device consisted of a rotating culture module,a dirve module,a control module and control software,with the shells of all the modules being manufactured by 3D printing.The rotating culture module was composed of a tubular electrospun scaffold,a cell culture chamber,a magnetic coupling rotor and polypropylene pipeline;the drive module was made up of a N20 reduction motor and a magnetic coupling rotor;the control module included an ESP-8266 chip and a printed circuit board;the control software was developed with Blinker IoT platform and C++language.The device was used to culture human intrahepatic bile duct epithelial cells to verify its effects.Results Light microscopy and scanning electron microscopy images showed that a uniform and continuous cell layer was formed on the surface of the tubular electrospun scaffold.Conclusion The intelligent horizontal rotating cell culture device achieves uniform growth of cells on the inner surface of tubular electrospun scaffolds,and can be used as an effective platform for cell culture on tubular scaffolds.[Chinese Medical Equipment Journal,2024,45(9):41-45]

Objective To design a portable intelligent cleaner for medical lumen instruments to enhance cleaning efficiency.Methods The portable intelligent cleaner had a box-body shape and a shell made of 304 stainless steel,which was composed of a circuit control board,a micro pump,lithium batteries,a charging interface,a rinse tube and connectors.The circuit control board used a STM32G030C8T6 integraged circuit,which was equipped with a countdown digital tube to display the time left for cleaning;the micro pump and lithium batteries were placed at the inner wall of the box bottom,the charging interface and water inlet/outlet inteface were put on the outside of the front wall of the box bottom,the water inlet/outlet interface was connected with a silicon rinse tube linked to an adapter at its distal end,and the adapters with different calibers were compatible with sizes of medical lumen instruments.Totally 9 672 pieces of lumen instruments received by some hospital's disinfection supply center from May to October 2021 were divided into 2 groups with the convenience sampling method,with 4 836 pieces in each group.The odd-numbered instruments were enrolled into a control group and cleaned with an ultrasonic cleaner and a lumen brush,and the even-numbered instruments were included into an experimental group and cleaned conventionally after pretreatment by the intelligent cleaner.The two groups were compared in terms of eaning efficiency and satisfaction.Results Testing by visual inspection,magnifying glass with light source and white stripe method showed that the experimental group behaved better than the control group in the cleaning qualification rate,whose satisfaction rate(100％)was also higher than that of the control group(86.53％),with all the differences being statistically significant(P＜0.05).Conclusion The portable cleaner with easy operation enhances the cleaning quality and efficiency for medical lumen instruments.[Chinese Medical Equipment Journal,2024,45(10):114-117]