Objective To explore the continuous care needs of stroke patients when discharge,and analyze the related influenced factors.Methods One hundred and twenty cases with first stroke attack were selected,and their continuous care needs were investigated by methods of filling in questionnaires when discharged.The National Institutes of Health Stroke Scale and Barthel Index were applied to assess the severity of acute stroke and their ability of daily life when cases were admitted and discharged,respectively.We investigated the continuous care needs of stroke patients,and analyzed the relationship of that with the severity of acute stroke and their ability of daily life.Results The top five continuous care needs were knowledge of stroke,safety administration,methods of rehabilitation,self control and monitoring blood pressure,and diet direction.Those ratios of needs ranged from 87.25%to 94.12%.The score of continuous care needs had a positive relationship with that of NIHSS(r=0.271,<0.05),and had a negative relationship with that of BI both at the time of discharge(r=-0.226,<0.05).Conclusion The various continuous care needs are very common in patients with first stroke attack for varied reasons.More serious the neurological dysfunction and lower ability of daily life,higher the level of needs for continuous care.

Objective To present a named entity recognition method referred to as BioBERT-Att-BiLSTM-CRF for eligibility criteria based on the BioBERT pretrained model.The method can automatically extract relevant information from clinical trials and provide assistance in efficiently formulating eligibility criteria.Methods Based on the UMLS medical semantic network and expert-defined rules,the study established medical entity annotation rules and constructed a named entity recognition corpus to clarify the entity recognition task.BioBERT-Att-BiLSTM-CRF converted the text into BioBERT vectors and inputted them into a bidirectional long short-term memory network to capture contextual semantic features.Meanwhile,attention mechanisms were applied to extract key features,and a conditional random field was used for decoding and outputting the optimal label sequence.Results BioBERT-Att-BiLSTM-CRF outperformed other baseline models on the eligibility criteria named entity recognition dataset.Conclusion BioBERT-Att-BiLSTM-CRF can efficiently extract eligibility criteria-related information from clinical trials,thereby enhancing the scientific validity of clinical trial registration data and providing assistance in the formulation of eligibility criteria for clinical trials.

AIM: To evaluate the clinical efficacy and safety of He-wei-zhi-xie (HWZX) capsules in diarrhea patients. METHODS: The clinical study was conducted in 35 clinical trials centers from October 2015 to December 2017 by multicenter, prospective, open and uncontrolled design methods. The primary efficacy endpoint is the effective rate of diarrhea, the secondary endpoints include recovery rate of diarrhea, recovery time of diarrhea, number of irregular stools and Leeds dyspepsia questionnaire. The pharmacodynamics model of time course was established by nonlinear mixed effect model, and the effect of covariates on pharmacodynamic parameters was investigated. The safety measures were the incidence of adverse events, adverse reactions and the laboratory test indicators. RESULTS: A total of 2 285 cases were included in full analysis set. The effective rate of diarrhea was 90.8%, and the diarrhea recovery rate was 77.3%. The median time of recovery was 3 days, and the Leeds score was reduced by 3.6 points. It is found that baseline has a significant effect on model parameter E

Objective:To study the relationship between morphologic classification and prognosis of patients with intrahepatic cholangiocarcinoma (ICC).Methods:The clinicopathologic data of 125 ICC patients who underwent R 0 resection at the Ningbo Medical Center Li Huili Hospital from January 2011 to May 2019 were retrospectively analyzed. This cohort consisted of 67 males and 58 females, aged 26.0 to 82.0 (63.5±9.5) years old. Based on the resected specimens, the patients were divided into the mass forming type, periductal infiltrating type and mixed type. The survival rates and recurrence-free survival outcomes of the patients among the three types were compared, and the risk factors that influenced prognosis were analyzed. Results:Using the predetermined inclusion and exclusion criteria, 16 patients with missing data and other causes of death were excluded from the initial 125 patients. Also, as the number of the mixed type was small, these patients were excluded. Finally 62 patients in the mass forming type and 42 patients in the periductal infiltrating type were analyzed. In the mass forming group, there were 32 males and 30 females, aged (63.1±9.1) years. In the perivascular infiltration group, there were 22 males and 20 females, aged (64.1±10.2) years. The 1-, 3-, 5-year survival rates of the mass forming group were 78.1%, 33.2%, 18.9% (median survival 25 months). The 1-, 3-, 5-year survival rates of the periductal infiltrating type were 63.3%, 8.3%, 6.1% (median survival 15 months). There were statistically significant differences between the two groups ( P<0.05). The median recurrence-free survival for the mass forming and the periductal infiltrating groups were 18 and 11 months, respectively, with a statistically significant differences between them ( P<0.05). Univariate and multivariate analysis showed that TNM staging Ⅲ~Ⅳ ( HR=2.966, 95% CI: 1.549-5.679) and periductal infiltrating type ( HR=2.403, 95% CI: 1.236-4.670) were independent risk factors for survival of these patients after operations. TNM staging Ⅲ~Ⅳ ( HR=2.466, 95% CI: 1.325-4.589), low grade differentiation ( HR=0.528, 95% CI: 0.299-0.934) and periductal infiltrating type ( HR=2.432, 95% CI: 1.295-4.565) were independent risk factors for relapse-free survival of these patients ( P<0.05). Conclusions:Morphological classification was found to be an independent risk factor for prognosis of ICC patients in this study, with significantly worse long-term prognosis when compared with the mass forming type.

With the booming development of medical information technology and computer science, the medical services industry is gradually transiting from information technology to intelligence. The medical knowledge graph plays an important role in intelligent medical applications such as knowledge questions and answers and intelligent diagnosis, and is a key technology for promoting wise medical care and the basis for intelligent management of medical information. In order to fully exploit the great potential of knowledge graphs in the medical field, this paper focuses on five aspects: inter-drug relationship discovery, assisted diagnosis, personalized recommendation, decision support and intelligent prediction. The latest research progress on medical knowledge graphs is introduced, and relevant suggestions are made in light of the current challenges and problems faced by medical knowledge graphs to provide reference for promoting the wide application of medical knowledge graphs.
Pattern Recognition, Automated ; Medical Informatics

Objective: To analyze the differentially expressed microRNA (miRNA) and their target genes in peripheral blood and bone tissue of postmenopausal osteoporosis (PMOP), and provide basis for the study of pathogenesis as well as biomarkers identification of PMOP. Methods: Two miRNA datasets of PMOP from the public platform NCBI-GEO DataSets were obtained, including GSE64433 (the miRNA expression profile of peripheral blood samples, including 23 PMOP patients and 25 controls) and GSE74209 (the miRNA expression profile of the femoral neck bone tissue sample, including six PMOP patients and six controls). R/Bioconductor was performed for data analysis and differentially expressed miRNA screening, and miRNAs with fold change>2 & P<0.05 between osteoporosis and controls were selected as differentially expressed miRNA. The miRNA target gene prediction was performed by combining TargetScan, miRDB and miRTarBase databases. The miRNA-target gene regulatory network was constructed and analyzed by Cytoscape. Results: There were 224 differentially expressed miRNAs (75 up-regulated miRNAs and 149 down-regulated miRNAs) in the peripheral blood samples of PMOP group (GSE64433 dataset) and 132 differentially expressed miRNAs (58 up-regulated miRNAs and 74 down-regulated miRNAs) in the femoral neck bone tissue of PMOP group (GSE74209 dataset). We combined the results from the two datasets and obtained 8 miRNAs down-regulated in both datasets, and the 8 miRNAs regulated a total of 327 target genes, and 10 of these target genes were co-regulated by two miRNAs. Conclusions The core miRNAs and the target genes regulated by multiple miRNAs in the regulatory network may play important roles in the pathogenesis of PMOP and have potential application values as molecular biomarkers of disease. These findings are meaningful for the studies of PMOP pathogenesis, biomarkers screening and prevention of osteoporotic fractures.