Oral Glucose Combined with Short-Term Intravenous Nutrition for the Prevention of Hypoglycemia after Painless Endoscopic Gastric Polypectomy

Objective: To explore the application effect of oral glucose combined with short-term intravenous nutrition in preventing postoperative hypoglycemia after painless endoscopic gastric polyp resection, and to provide guidance for better management of patients undergoing such procedures. Methods: A total of 886 patients who underwent painless endoscopic gastric polyp resection in the Department of Gastroenterology, the First Affiliated Hospital of Yangtze University, from January 2020 to December 2021, were selected as the study subjects. According to the random number table method, they were divided into an experimental group and a control group, with 443 cases in each group. Patients in the control group were subjected to routine fasting and water restriction for 8 hours before surgery, and routine fasting for 24 hours after surgery. Short-term intravenous nutrition support was provided through fluid supplementation, and finger blood glucose levels were monitored at 1 hour, 4 hours, and 8 hours after completion of intravenous infusion, or when symptoms such as palpitations and cold sweats occurred. The experimental group received oral administration of 5% glucose solution (500 ml) 2 hours before surgery based on the procedures of the control group. The incidence of preoperative discomfort (hunger, thirst, and fatigue), residual gastric fluid volume, and postoperative hypoglycemia were compared between the two groups. Results: The incidence of postoperative blood glucose Conclusion: Based on the study population, oral glucose combined with short-term intravenous nutrition can effectively prevent the incidence of hypoglycemia in patients undergoing painless endoscopic gastric polyp resection. However, due to the limitations of a single-center study and a small number of cases, its feasibility needs to be further validated with more data from multi-center and large-sample cases.

Oral Glucose Combined with Short-Term Intravenous Nutrition for the Prevention of Hypoglycemia after Endoscopic Colorectal Polypectomy

Objective: To investigate the effect of oral glucose combined with short-term intravenous nutrition on the prevention of hypoglycemia after endoscopic colorectal polypectomy and to provide guidance for better management of such patients. Methods: 860 patients who underwent endoscopic colorectal polypectomy for colorectal polyps in the Department of Gastroenterology of the First Affiliated Hospital of Yangtze University from January 2020 to December 2021 were selected for the study. The patients were divided into experimental and control groups according to the random number table method, with 430 patients in each group. In the control group, 3 L of polyethylene glycol electrolyte dispersion was used for preoperative intestinal preparation and postoperative fasting was performed routinely for 24 h. Short-term intravenous nutrition support was provided by rehydration, and finger blood glucose was monitored at 1, 4, and 8 h after intravenous infusion or when there were symptoms such as panic and cold sweat;in the experimental group, oral glucose intervention was implemented on the basis of the control group. The incidence of postoperative hypoglycemia, quality of bowel preparation, and tolerance of patients during bowel preparation were compared between the 2 groups. Results: The incidence of postoperative blood glucose Conclusion: Based on the present study population, oral glucose combined with short-term intravenous nutrition can effectively prevent the incidence of hypoglycemia in patients after endoscopic colorectal polypectomy;however, this was limited to a single-center study and the number of cases was small.

Associative learning mechanism for drug‐target interaction prediction

As a necessary process of modern drug development,finding a drug compound that can selectively bind to a specific protein is highly challenging and costly.Exploring drug‐target interaction strength in terms of drug‐target affinity(DTA)is an emerging and effective research approach for drug development.However,it is challenging to model drug‐target interactions in a deep learning manner,and few studies provide interpretable analysis of models.This paper proposes a DTA prediction method(mutual transformer‐drug target affinity[MT‐DTA])with interactive learning and an autoencoder mechanism.The proposed MT‐DTA builds a variational autoencoders system with a cascade structure of the attention model and convolutional neural networks.It not only enhances the ability to capture the characteristic information of a single molecular sequence but also establishes the characteristic expression relationship for each substructure in a single molecular sequence.On this basis,a molecular information interaction module is constructed,which adds information interaction paths between molecular sequence pairs and complements the expression of correlations between molecular substructures.The performance of the proposed model was verified on two public benchmark datasets,KIBA and Davis,and the results confirm that the proposed model structure is effective in predicting DTA.Additionally,attention transformer models with different configurations can improve the feature expression of drug/protein molecules.The model performs better in correctly predicting interaction strengths compared with state‐of‐the‐art baselines.In addition,the diversity of drug/protein molecules can be better expressed than existing methods such as SeqGAN and Co‐VAE to generate more effective new drugs.The DTA value prediction module fuses the drug‐target pair interaction information to output the predicted value of DTA.Additionally,this paper theoretically proves that the proposed method maximises evidence lower bound for the joint distribution of the DTA prediction model,which enhances the consistency of the probability distribution between actual and predicted values.The source code of proposed method is available at https://github.com/Lamouryz/Code/tree/main/MT‐DTA.

Application of Nursing Risk Management in Nursing of Severe Peptic Ulcer Bleeding

Objective: To assess and compare the clinical application value of nursing risk management in the diagnosis and treatment of severe peptic ulcer bleeding. Methods: A total of 70 patients with severe peptic ulcer bleeding were selected as the research objects, randomly divided into observation group and control group, 35 cases for each. The nursing risk management and conventional nursing management were implemented for the two groups, respectively. The success rate of hemostasis, average length of stay, cure rate, complication rate, dyspnea rate, nursing dispute rate, SAS score, and SDS score were compared between the two groups. Patients’ satisfaction with nursing quality was also compared. Results: After the implementation of two different nursing management methods, all the above-mentioned metrics were better in the observation group than in the control group, and the differences were statistically significant (P < 0.01 or P < 0.05). Conclusion: The application of nursing risk management in the nursing intervention process of patients with severe peptic ulcer bleeding can effectively reduce the probability of nursing risk events, increase the cure rate, shorten the patient’s hospital stay, but also improve the patients’ psychological state and increase the patient’s satisfaction with nursing quality, which is worth clinical promotion.

Multi-focus image fusion via morphological similarity-based dictionary construction and sparse representation

Sparse representation has been widely applied to multi-focus image fusion in recent years. As a key step, the construction of an informative dictionary directly decides the performance of sparsity-based image fusion. To obtain sufficient bases for dictionary learning, different geometric information of source images is extracted and analysed. The classified image bases are used to build corresponding subdictionaries by principle component analysis. All built subdictionaries are merged into one informative dictionary. Based on constructed dictionary, compressive sampling matched pursuit algorithm is used to extract corresponding sparse coefficients for the representation of source images. The obtained sparse coefficients are fused by Max-L1 fusion rule first, and then inverted to form the final fused image. Multiple comparative experiments demonstrate that the proposed method is competitive with other the state-of-the-art fusion methods.

Convolutional neural network based detection and judgement of environmental obstacle in vehicle operation

Precise real-time obstacle recognition is both vital to vehicle automation and extremely resource intensive. Current deep-learning based recognition techniques generally reach high recognition accuracy, but require extensive processing power. This study proposes a region of interest extraction method based on the maximum difference method and morphology, and a target recognition solution created with a deep convolutional neural network. In the proposed solution, the central processing unit and graphics processing unit work collaboratively. Compared with traditional deep learning solutions, the proposed solution decreases the complexity of algorithm, and improves both calculation efficiency and recognition accuracy. Overall it achieves a good balance between accuracy and computation.

Blockchain and Artificial Intelligence Applications

The emergence and popularity of blockchain,distributed ledger technology distributed computing,and network security and trust techniques are significantly changing the operation and management of computing and communication systems,as these techniques have the potential to disrupt any domain involving coordination among autonomous resources without trusted third parties.These techniques and their applications include finance and payments(e.g.,Facebook Libra),but also networks(e.g.,power grids or telecom networks),computing(e.g.,brokering of edge resources),Internet of Things(e.g.,supply chain or industry 4.0),and service platforms(e.g.,identity management).The market capitalization,investor appetite,and institutional coverage for cryptocurrency(as well as bitcoin and blockchain)have all jumped exponentially.The total market capitalization of the cryptocurrency market has significantly increased in the past three years.The applications of blockchain exhibit a variety of complicated problems and new requirements,which brings more open issues and challenges for artificial intelligence(AI)and related research.

Single-epoch RTK performance assessment of tightly combined BDS-2 and newly complete BDS-3

The BeiDou global navigation satellite system(BDS-3)constellation deployment has been completed on June 23,2020,with a full constellation comprising 30 satellites.In this study,we present the performance assessment of single-epoch Real-Time Kinematic(RTK)positioning with tightly combined BeiDou regional navigation satellite system(BDS-2)and BDS-3.We first investigate whether code and phase Differential Inter-System Biases(DISBs)exist between the legacy B1I/B3I signals of BDS-3/BDS-2.It is discovered that the DISBs are in fact about zero for the baselines with the same or different receiver types at their endpoints.These results imply that BDS-3 and BDS-2 are fully interoperable and can be regarded as one constellation without additional DISBs when the legacy B1I/B3I signals are used for precise relative positioning.Then we preliminarily evaluate the single-epoch short baseline RTK performance of tightly combined BDS-2 and the newly completed BDS-3.The performance is evaluated through ambiguity resolution success rate,ambiguity dilution of precision,as well as positioning accuracy in kinematic and static modes using the datasets collected in Wuhan.Experimental results demonstrate that the current BDS-3 only solutions can deliver comparable ambiguity resolution performance and much better positioning accuracy with respect to BDS-2 only solutions.Moreover,the RTK performance is much improved with tightly combined BDS-3/BDS-2,particularly in challenging or harsh conditions.The single-frequency single-epoch tightly combined BDS-3/BDS-2 solution could deliver an ambiguity resolution success rate of 96.9%even with an elevation cut-off angle of 40°,indicating that the tightly combined BDS-3/BDS-2 could achieve superior RTK positioning performance in the Asia-Pacific region.Meanwhile,the three-dimensional(East/North/Up)positioning accuracy of BDS-3 only solution(0.52 cm/0.39 cm/2.14 cm)in the kinematic test is significantly better than that of the BDS-2 only solution(0.85 cm/1.02 cm/3.01 cm)due to the better geometry of the current BDS-3 constellation.The tightly combined BDS-3/BDS-2 solution can provide the positioning accuracy of 0.52 cm,0.22 cm,and 1.80 cm,respectively.