目的 评价手卫生健康教育对重症监护病房（ICU）患者家属手卫生依从性的影响。 方法 选取2012年3月－5月ICU患者家属558人，对其进行手卫生健康教育。将健康教育前的1个月定义为第1阶段(基线调查阶段），健康教育当月定义为第2阶段，健康教育结束后的第1个月定义为第3阶段。对ICU患者家属开展手卫生健康教育，第1和第3阶段均采用张贴展板和宣教图片，床旁准备速干手消毒液；第2阶段在此基础上，每周示范六步洗手法3次，由责任护士督促并指导家属使用速干手消毒液进行手卫生。观察3个阶段患者家属手卫生依从性变化情况。 结果 在对“接触患者前”、“接触患者后”和“接触患者周围环境后”3个手卫生时机的依从率比较中，第2阶段明显高于第1阶段（P＜0.01）；第3阶段较第2阶段有明显下降（P＜0.01）；在3个阶段中，使用速干手消毒液进行手卫生的人数均高于使用洗手液的人数。 结论 手卫生健康教育普及了手卫生相关知识，提高了ICU患者家属对手卫生的依从性。
In order to satisfy demands of massive and heterogeneous tumor clinical data processing and the multi-center collaborative diagnosis and treatment for tumor diseases, a Tumor Data Interacted System (TDIS) was established based on grid platform, so that an implementing virtualization platform of tumor diagnosis service was realized, sharing tumor information in real time and carrying on standardized management. The system adopts Globus Toolkit 4.0 tools to build the open grid service framework and encapsulats data resources based on Web Services Resource Framework (WSRF). The system uses the middleware technology to provide unified access interface for heterogeneous data interaction, which could optimize interactive process with virtualized service to query and call tumor information resources flexibly. For massive amounts of heterogeneous tumor data, the federated stored and multiple authorized mode is selected as security services mechanism, real-time monitoring and balancing load. The system can cooperatively manage multi-center heterogeneous tumor data to realize the tumor patient data query, sharing and analysis, and compare and match resources in typical clinical database or clinical information database in other service node, thus it can assist doctors in consulting similar case and making up multidisciplinary treatment plan for tumors. Consequently, the system can improve efficiency of diagnosis and treatment for tumor, and promote the development of collaborative tumor diagnosis model.
Multi-layer perceptron (MLP) neural network belongs to multi-layer feedforward neural network, and has the ability and characteristics of high intelligence. It can realize the complex nonlinear mapping by its own learning through the network. Bipolar disorder is a serious mental illness with high recurrence rate, high self-harm rate and high suicide rate. Most of the onset of the bipolar disorder starts with depressive episode, which can be easily misdiagnosed as unipolar depression and lead to a delayed treatment so as to influence the prognosis. The early identification of bipolar disorder is of great importance for patients with bipolar disorder. Due to the fact that the process of early identification of bipolar disorder is nonlinear, we in this paper discuss the MLP neural network application in early identification of bipolar disorder. This study covered 250 cases, including 143 cases with recurrent depression and 107 cases with bipolar disorder, and clinical features were statistically analyzed between the two groups. A total of 42 variables with significant differences were screened as the input variables of the neural network. Part of the samples were randomly selected as the learning sample, and the other as the test sample. By choosing different neural network structures, all results of the identification of bipolar disorder were relatively good, which showed that MLP neural network could be used in the early identification of bipolar disorder.
Objective To systematically review the performance of postpartum hemorrhage risk prediction models, and to provide references for the future construction and application of effective prediction models. Methods The CNKI, WanFang Data, VIP, CBM, PubMed, EMbase, The Cochrane Library, Web of Science, and CINAHL databases were electronically searched to identify studies reporting risk prediction models for postpartum hemorrhage from database inception to March 20th, 2022. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias and applicability of the included studies. Results A total of 39 studies containing 58 postpartum hemorrhage risk prediction models were enrolled. The area under the curve of 49 models was over 0.7. All but one of the models had a high risk of bias. Conclusion Models for predicting postpartum hemorrhage risk have good predictive performance. Given the lack of internal and external validation, and the differences in study subjects and outcome indicators, the clinical value of the models needs to be further verified. Prospective cohort studies should be conducted using uniform predictor assessment methods and outcome indicators to develop effective prediction models that can be applied to a wider range of populations.