ObjectiveTo discuss the demands for nursing knowledge among family caregivers for elderly people, in order to provide a basis for nurses to provide effective education for these people. MethodsBetween May and June 2012, a questionnaire which contained the condition of demands for nursing knowledge and the burden of care was used to investigate 1 600 family caregivers for the elderly people. ResultsThe caregivers had a demand for nursing knowledge, which may include the knowledge on medicine, disease and caregiving. The demand for knowledge was correlated with relationship between the caregivers and care recipients, health condition of the caregivers and care burden. ConclusionThe demands for nursing knowledge are higher in those who have spouse and high burden of care, without disease and symptom; we should pay more attention on them and take measures to reduce their burden of care.
Objective To explore the effectiveness of situational experiential teaching mode in emergency internship teaching. Methods Interns from the Department of Emergency, Jiangyou Fifth People’s Hospital from July 2022 to May 2023 were selected as the research subjects. The interns were randomly divided into a trial group and a control group using a random number table method. The trial group adopted a situational experiential teaching mode, while the control group adopted a traditional teaching mode. Theoretical knowledge testing, clinical comprehensive ability assessment, and clinical information feedback were used to evaluate the effectiveness of different teaching methods. Results A total of 90 interns were included, with 45 people in each group, aged 18-23 years old. Both groups consist of 18 clinical medicine students and 27 clinical nursing students. There was no statistically significant difference in academic performance in school between the two groups of interns (P>0.05). The theoretical knowledge test score (92.98±2.71 vs. 85.29±6.24), clinical comprehensive ability assessment score (90.52±2.58 vs. 83.35±5.25) and clinical feedback (44 excellent and 1 fine in the trial group vs. 25 excellent, 5 fine, and 15 poor in the control group) of the trial group were better than those in the control group (P<0.05). Conclusions The situational experiential teaching mode can enhance interns’ learning interest, improve memory effectiveness, help students master theoretical knowledge, and enhance their comprehensive abilities in clinical evaluation and decision-making. It is worth promoting in clinical practice.
Knowledge translation (KT) provides a paradigm to bridge the gap between knowledge and practice, which has critical instructive significance for health promotion. This article expounds on the connotation of KT by comparing it with similar terms. Next, it introduces three kinds of common KT theoretical models, including process models, determinant frameworks, and evaluation frameworks. Finally, its application and experiences in health promotion are summarized to provide references for the ongoing health promotion in China.
The medical literature contains a wealth of valuable medical knowledge. At present, the research on extraction of entity relationship in medical literature has made great progress, but with the exponential increase in the number of medical literature, the annotation of medical text has become a big problem. In order to solve the problem of manual annotation time such as consuming and heavy workload, a remote monitoring annotation method is proposed, but this method will introduce a lot of noise. In this paper, a novel neural network structure based on convolutional neural network is proposed, which can solve a large number of noise problems. The model can use the multi-window convolutional neural network to automatically extract sentence features. After the sentence vectors are obtained, the sentences that are effective to the real relationship are selected through the attention mechanism. In particular, an entity type (ET) embedding method is proposed for relationship classification by adding entity type characteristics. The attention mechanism at sentence level is proposed for relation extraction in allusion to the unavoidable labeling errors in training texts. We conducted an experiment using 968 medical references on diabetes, and the results showed that compared with the baseline model, the present model achieved good results in the medical literature, and F1-score reached 93.15%. Finally, the extracted 11 types of relationships were stored as triples, and these triples were used to create a medical map of complex relationships with 33 347 nodes and 43 686 relationship edges. Experimental results show that the algorithm used in this paper is superior to the optimal reference system for relationship extraction.
Automatic classification of medical questions is of great significance in improving the quality and efficiency of online medical services, and belongs to the task of intent recognition. Joint entity recognition and intent recognition perform better than single task models. Currently, most publicly available medical text intent recognition datasets lack entity annotation, and manual annotation of these entities requires a lot of time and manpower. To solve this problem, this paper proposes a medical text classification model, bidirectional encoder representation based on transformer-recurrent convolutional neural network-entity-label-semantics (BRELS), which integrates medical entity label semantics. This model firstly utilizes an adaptive fusion mechanism to absorb prior knowledge of medical entity labels, achieving local feature enhancement. Then in global feature extraction, a lightweight recurrent convolutional neural network (LRCNN) is used to suppress parameter growth while preserving the original semantics of the text. The ablation and comparison experiments are conducted on three public medical text intent recognition datasets to validate the performance of the model. The results show that F1 score reaches 87.34%, 81.71%, and 77.74% on each dataset, respectively. The results show that the BRELS model can effectively identify and understand medical terminology, thereby effectively identifying users’ intentions, which can improve the quality and efficiency of online medical services.
Objective To investigate the effect of training courses of evidence-based medicine (EBM) on the knowledge, skill, attitude and behavior of medical postgraduates and to explore the barriers to evidence-based practice (EBP), so as to provide knowledge to improve further EBM teaching and EBP. Methods A total of 110 medical postgraduates of Sichuan University who selected EBM courses in the autumn semester of 2004 were given questionnaires that combined both open and closed questions. The KAB (knowledge, attitude and behavior) of EBM and barriers to EBP were compared before and after the training courses. Results Differences were observed in KAB of EBM and barriers to EBP after the training courses, compared to the assessments done before the courses. In “Knowledge”: there was a significant increase in the understanding of specific terms in EBM after the training courses (75% of the items showed a statistically significant improvement). This was especially marked for “absolute risk”, “systematic review”, “meta-analysis” and “publication bias” (Plt;0.01). We also found an improvement in familiarity with medical search engines (Plt;0.05). In “Attitude”: the mean scores for most items (55%) were relatively high both before and after the training courses (gt;4), and a significant improvement was observed in 2 items. These were “Strong evidence is lacking to support most of the interventions I use with my patients” and “EBP needs to take into account patient preferences” (Plt;0.01). The mean scores of 2 items were relatively low both before and after the training courses (lt;3). These were “the adoption of EBP places an reasonable demand on physical therapists” and “EBP does not take into account the limitations of my clinical setting”. Another 2 items had mean scores close to 5: “I need to increase the use of evidence in my daily practice” and “I am interested in learning or improving the skills necessary to incorporate EBP into my practice”. In terms of “Behavior”: the medical postgraduates continued not to think highly of the use of literature after the training courses. About 60% of the postgraduates did not read any literature related to their specialties at all. Although searching of MEDLINE and other electronic databases was relatively frequent (gt;6 times/month: 60.3% before training and 65.7% after training), using professional literature and research findings in the process of clinical decision-making was not equal (gt;6 times/month: 29% before training and 35.1% after training). No significant difference was observed in applying clinical practice guidelines before and after the training courses. As for “Barriers”: the postgraduates considered “poor ability to critically appraise literature” as the most important barrier both before and after the training courses. The second and third most important barriers were different compared to after the training courses. The barrier of “lack of research skills” was larger than that of “lack of information resources” before the training courses, but after that the course, the order of these was reversed. Conclusion The knowledge of medical postgraduates increased significantly after the current training courses of EBM. Some improvement was also found in attitude and behavior. The top three barriers to EBP were “Poor ability to critically appraise literature”, “Lack of information resources”, and “Lack of research skills”
ObjectiveTo propose a lung artery segmentation method that integrates shape and position prior knowledge, aiming to solve the issues of inaccurate segmentation caused by the high similarity and small size differences between the lung arteries and surrounding tissues in CT images. MethodsBased on the three-dimensional U-Net network architecture and relying on the PARSE 2022 database image data, shape and position prior knowledge was introduced to design feature extraction and fusion strategies to enhance the ability of lung artery segmentation. The data of the patients were divided into three groups: a training set, a validation set, and a test set. The performance metrics for evaluating the model included Dice Similarity Coefficient (DSC), sensitivity, accuracy, and Hausdorff distance (HD95). ResultsThe study included lung artery imaging data from 203 patients, including 100 patients in the training set, 30 patients in the validation set, and 73 patients in the test set. Through the backbone network, a rough segmentation of the lung arteries was performed to obtain a complete vascular structure; the branch network integrating shape and position information was used to extract features of small pulmonary arteries, reducing interference from the pulmonary artery trunk and left and right pulmonary arteries. Experimental results showed that the segmentation model based on shape and position prior knowledge had a higher DSC (82.81%±3.20% vs. 80.47%±3.17% vs. 80.36%±3.43%), sensitivity (85.30%±8.04% vs. 80.95%±6.89% vs. 82.82%±7.29%), and accuracy (81.63%±7.53% vs. 81.19%±8.35% vs. 79.36%±8.98%) compared to traditional three-dimensional U-Net and V-Net methods. HD95 could reach (9.52±4.29) mm, which was 6.05 mm shorter than traditional methods, showing excellent performance in segmentation boundaries. ConclusionThe lung artery segmentation method based on shape and position prior knowledge can achieve precise segmentation of lung artery vessels and has potential application value in tasks such as bronchoscopy or percutaneous puncture surgery navigation.
ObjectiveTo conduct a scoping review of studies on the application of knowledge mapping in the field of rare diseases at home and abroad, in order to clarify the content and status of application and provide references for future research in this field. MethodsRelevant studies in PubMed, Web of Science, Embase, MEDLINE, CNKI, WanFang Data, VIP, and CBM databases were searched, using the Joanna Briggs Institute Scoping Review Guidelines in Australia as the methodological framework, and the search time frame was from the establishment of the database to June 1, 2023. ResultsTwenty-five papers were included, and the main applications of knowledge graphs in the field of rare diseases were knowledge management, assisted diagnosis, drug repositioning and decision support, involving techniques such as knowledge representation, knowledge extraction, knowledge reasoning, knowledge fusion and knowledge storage.ConclusionKnowledge graphs have shown positive results in fusing and exploiting multi-source information, aiding disease prediction and diagnosis and drug development, but further technical improvements are needed.
Glaucoma is one of blind causing diseases. The cup-to-disc ratio is the main basis for glaucoma screening. Therefore, it is of great significance to precisely segment the optic cup and disc. In this article, an optic cup and disc segmentation model based on the linear attention and dual attention is proposed. Firstly, the region of interest is located and cropped according to the characteristics of the optic disc. Secondly, linear attention residual network-34 (ResNet-34) is introduced as a feature extraction network. Finally, channel and spatial dual attention weights are generated by the linear attention output features, which are used to calibrate feature map in the decoder to obtain the optic cup and disc segmentation image. Experimental results show that the intersection over union of the optic disc and cup in Retinal Image Dataset for Optic Nerve Head Segmentation (DRISHTI-GS) dataset are 0.962 3 and 0.856 4, respectively, and the intersection over union of the optic disc and cup in retinal image database for optic nerve evaluation (RIM-ONE-V3) are 0.956 3 and 0.784 4, respectively. The proposed model is better than the comparison algorithm and has certain medical value in the early screening of glaucoma. In addition, this article uses knowledge distillation technology to generate two smaller models, which is beneficial to apply the models to embedded device.
目的 了解社区人群对脑卒中危险因素及症状的知晓现状。 方法 随机抽样调查1 208名居民及112名医务人员的人口学特征、对危险因素及预警信号的知晓现状及其影响因素、信息来源及需求情况。 结果 90.1%、100.0%的居民及医务人员可辨识高血压是卒中的危险因素，而社区居民及医务人员对年龄、糖尿病、吸烟等危险因素的认识比例分别为65.0% 和85.0%，且对危险因素的控制策略缺乏了解。87.4%、100.0%社区居民及医务人员将一侧肢体的活动障碍作为卒中的第一大预警信号，其次为头晕、步态不稳、头痛、言语困难、视物模糊。卒中知识得分的单因素及多因素分析示：大学文化、已婚且在职的居民及高学历的医务人员对卒中信息的了解程度高。卒中信息的获取途径依次为电视、社区医生/讲堂、报纸、杂志、网络。 结论 西部城市社区人群卒中知识知晓率低，开展针对低学历医务者的卒中培训及低学历、独居及退休人员的居民讲堂是改善现状的必要途径。同时也为政府建立有效的院前早期识别及快速转诊技术提供了依据。Objective To assess the baseline knowledge of risk factors and warning signs of cerebral apoplexy in communities. Methods A total of 1 208 inhabitants and 112 medical personnel were selected by systematic sampling. The questionnaire included social-demographic data, knowledge of cerebral apoplexy risk and warning signs and influencing factors, the sources and requirement of information about cerebral apoplexy. Results Hypertension was a risk factor in 90.1% of residents and 100.0% of medical personnel. Age, diabetes and smoking were identified as the risk factor in 65.0% of medical personnel and 85.0% of residents. Medical therapy of risk factors was insufficient. The most common warning signs of cerebral apoplexy was hemiplegia, the following were vertigo, ataxia, headache, aphasia and double vision. Stepwise multiple regression analyses showed that residents who had higher educational background, spousal, workers and community worker with higher educational background had higher knowledge scores of cerebral apoplexy. The main sources of information about cerebral apoplexy were television, doctors, newspaper, magazine and network. Conclusions At present, the urban community residents in west China are lacking in knowledge about cerebral apoplexy. Going forward, targeted educational residents and medical workers should be directed at those who was highly educated, living alone, and retired. It is also provide a theoretical basis for establishing a prehospital identification and transfer treatment system based on community in developing countries.