Alzheimer''s disease (AD) has brought to us huge medical and economic burdens, and so discovery of its therapeutic drugs is of great significance.In this paper, we utilized knowledge graph embedding (KGE) models to explore drug repurposing for AD on the publicly available drug repurposing knowledge graph (DRKG).Specifically, we applied four KGE models, namely TransE, DistMult, ComplEx, and RotatE, to learn the embedding vectors of entities and relations on DRKG.By using three classical knowledge graph evaluation metrics, we then evaluated and compared the performance of these models as well as the quality of the learned embedded vectors.Based on our results, we selected the RotatE model for link prediction and identified 16 drugs that might be repurposed for the treatment of AD.Previous studies have confirmed the potential therapeutic effects of 12 drugs against AD, i.e., glutathione, haloperidol, capsaicin, quercetin, estradiol, glucose, disulfire, adenosine, paroxetine, paclitaxel, glybride and amitriptyline.Our study demonstrates that drug repurposing based on KGE may provide new ideas and methods for AD drug discovery.Moreover, the RotatE model effectively integrates multi-source information of DRKG, enabling promising AD drug repurposing.The source code of this paper is available at https://github.com/LuYF-Lemon-love/AD-KGE.

Knowledge graph technology has promoted the progress of new drug research and development, but domestic research starts late and domain knowledge is mostly stored in text, resulting in low rate of knowledge graph reuse.Based on multi-source and heterogeneous medical texts, this paper designed a Chinese named entity recognition model based on Bert-wwm-ext pre-training model and also integrated cascade thought, which reduced the complexity of traditional single classification and further improved the efficiency of text recognition.The experimental results showed that the model achieved the best performance with an F1-score of 0.903, a precision of 89.2%, and a recall rate of 91.5% on the self-built dataset.At the same time, the model was applied to the public dataset CCKS2019, and the results showed that the model had better performance and recognition effect.Using this model, this paper constructed a Chinese medical knowledge graph, involving 13 530 entities, 10 939 attributes and 39 247 relationships of them in total.The Chinese medical entity extraction and graph construction method proposed in this paper is expected to help researchers accelerate the new discovery of medical knowledge, and shorten the process of new drug discovery.

The peak period of cardiovascular disease (CVD) is around the time of awakening in the morning, which may be related to the surge of sympathetic activity at the end of nocturnal sleep. This paper chose 140 participants as study object, 70 of which had occurred CVD events while the rest hadn't during a two-year follow-up period. A two-layer model was proposed to investigate whether hypnopompic heart rate variability (HRV) was informative to distinguish these two types of participants. In the proposed model, the extreme gradient boosting algorithm (XGBoost) was used to construct a classifier in the first layer. By evaluating the feature importance of the classifier, those features with larger importance were fed into the second layer to construct the final classifier. Three machine learning algorithms, i.e., XGBoost, random forest and support vector machine were employed and compared in the second layer to find out which one can achieve the highest performance. The results showed that, with the analysis of hypnopompic HRV, the XGBoost+XGBoost model achieved the best performance with an accuracy of 84.3%. Compared with conventional time-domain and frequency-domain features, those features derived from nonlinear dynamic analysis were more important to the model. Especially, modified permutation entropy at scale 1 and sample entropy at scale 3 were relatively important. This study might have significance for the prevention and diagnosis of CVD, as well as for the design of CVD-risk assessment system.
Algorithms ; Cardiovascular Diseases ; Heart Rate ; Humans ; Machine Learning ; Sleep

Objective:To promote evidence-based practice in the pre-chemotherapy nursing assessment among adult cancer patients.Methods:The Joanna Briggs Institute Practical Application of Clinical Evidence System and Getting Research into Practice audit tools were used. The project was conducted in Shanghai Cancer Center of Fudan University from May to October 2018, 12 audit criteria were developed in the program including nursing training, patient medical and allergic history, medical diagnosis, lab data and so on.Results:A baseline audit of pre-chemotherapy nursing assessment among adult cancer patients was conducted, with a sample size of 68 patients and 36 nursing staff, during this stage, the compliance of audit 11 and 12 were 100%. After the implementation of systematic strategies, a follow-up audit involving similar sample as first audit was conducted using the same audit criteria. In the follow-up audit, except criterion 4 and 10, the compliance of the remaining 8 criteria had significantly improved, and χ2 value was 10.29-132.06, P<0.01. The result of history adverse reaction in the follow-up audit showed that among 68 patients, 3 had experienced chemotherapy infusion reactions in the past (The drugs were oxaliplatin, gemcitabine and paclitaxel), 39 had chemotherapy-related symptoms before admission (most of them were relieved at admission), of which the top five were loss of appetite, fatigue, nausea, neurotoxicity and vomiting. Conclusions:The aims of the project were fulfilled. We achieved increased compliance with evidence-based best practice recommended by JBI in most of audit criteria. Further audit will need to be carried out to improve the validity and quality of nursing assessment.

This paper reviewed the academic contribution of famous doctor of traditional Chinese medicine belonging to Yishui sects, and analyzed the change of chronic non-communicable disease in the 21st century. On this basis, the paper put forward that we should exert the advantages of traditional Chinese medicine, explore the regularity of treating chronic non-communicable disease, refresh the academic innovation, and generate new ideas and new treatment.

Objective To study whether the usage of antibiotics and white -blood -cell counts affect the effects of 2~12-year-old children with acute otitis media (AOM ) .Methods A total of 126 children (2~12 years old)with AOM ,from Jan 2013 to Dec 2013 ,were retrospectively analyzed .Usage of antibiotics and white -blood-cell count were recorded at first ,and the relationships between two factors and outcomes of children with AOM were studyed in one week ,one month and three months after treatment ,respectively .Results White blood cell counts were higher than normal in 59 .52% (75/126) 2~12 -year -old children with AOM ,and antibiotics were used in 73 .81% (93 /126) .Ninty three cases were followed -up until 3 month or more .Antibiotics were used in 74 cases ,and watchful waiting were used in the other 19 patients .The effective rates of two groups were 59 .45% and 52 .63% ,75 .68% and 84 .21% ,85 .14% and 78 .95% in one week ,one month and 3 months after treatment ,re‐spectively .There were no statistically significant differences(χ2 values were 0 .295 ,0 .903 ,0 .799 ,P>0 .05) .But the effective rates were signifantly higher in 1 and 3 months than that of in one week (P<0 .05) .There was no sig‐nificant difference (P>0 .05) between one and three months .Whether white-blood-cell count higher than normal or not ,the difference in efficacy was not statistically significant in 1 week ,1 month and 3 months after treatment (P >0 .05) .Conclusion In 2~12-year-old children with acute otitis media (AOM ) ,the final outcomes were inde‐pendent of the usage of antibiotics and white -blood-cell count .

Objective To explore the correlations of lung resistance protein (LRP) and glutathione S transferase π (GST-π) to chemotherapy resistance and prognosis of epithelial ovarian cancer.Methods The expressions of LRP and GST-π in epithelial ovarian cancer were examined with immunohistochemistry.Correlations of LRP and GST-π to chemotherapy efficacy and survival time after operation were analyzed.Results The short-term efficacy rates of ovarian cancer were lower in patients with positive expressions of LRP and GST-π than those with negative expressions [61.2％,61.7％ vs 94.1％,89.5％,x2 =6.47,4.94,P =0.011,P =0.026].The positive rates of LRP and GST-π were significant higher in patients with chemotherapy resistance than in those sensitive to chemotherapy [91.3％,87.0％ vs 65.1％,62.8％,P ＜ 0.05].Log-rank test showed that patients with positive LRP and GST-π had shorter survival time than those negative,and patients with both positive LRP and GST-π had shorter survival time than those both negative (P ＜ 0.05).Conclusions The expressions of LRP and GST-π in epithelial ovarian cancer could be used to predict chemotherapy resistance and prognosis of patients.

Objectives To screen the high-risk population of stroke in China using color Doppler flow imaging (CDFI)and to establish a stroke risk prediction model in Chinese population in order to prevent and treat stroke early. Methods Forty-one base hospitals and 715 286 people in the project areas of the first 6 provinces of China conducted routine physical examinations and investigated the related risk factors for cardiocerebrovascular diseases from July 2011 to April 2012 using a cross-sectional study,among them 61 860 patients underwent carotid CDFI screening,and 49 386 of them were high-risk population (exposed to≥3 risk factors). The bilateral common carotid interma-media thickness (IMT),the number of plaques and the degree of carotid stenosis were screened and documented. And whether carotid IMT thickening or not,with or without carotid plaques,and degree of carotid artery stenotic rate 0-49% and≥50% were performed by multivariate logistic regression analysis with the risk factors for stroke,respectively. Results (1)Logistic regression analysis showed that hypertension,atrial fibrillation,smoking,and lack of physical exercise were the independent risk factors for carotid IMT thickening (hypertension:OR,1. 17;95%CI 1. 12-1. 22;atrial fibrillation:OR,1. 15;95%CI 1. 09-1. 21;smoking:OR,1. 13;95%CI 1. 08-1. 17;and lack of physical exercise:OR,1. 12;95%CI 1.08-1. 16). (2)Hypertension,atrial fibrillation, smoking,and diabetes were the independent risk factors for carotid plaque and carotid artery stenosis rate≥50%(carotid plaque,hypertension:OR,1. 55;95%CI 1. 47-1. 62;atrial fibrillation:OR,1. 13;95%CI 1.06-1. 21;smoking:OR,1. 16;95%CI 1. 11-1. 22;and diabetes:OR,1. 30;95%CI 1. 24-1. 37). Carotid stenosis rate≥50%,hypertension:OR,1. 78;95%CI 1.55-2. 03;atrial fibrillation:OR,1. 59;95%CI 1. 39-1. 81;smoking:OR,1. 33;95%CI 1. 20-1. 48;and diabetes:OR,1. 30;95%CI 1. 17-1. 45. Simple obesity did not increase the incidences of carotid atherosclerotic plaque and carotid artery stenosis ≥50%(OR,0. 78, 0.83;95%CI 0. 75-0. 82 ,0. 75-0. 92,respectively). Conclusions Neck vascular ultrasound can be used as a valuable means for screening high-risk population and detecting risk factors of stroke. It has an important clinical significance for the early diagnosis and treatment of carotid atherosclerosis disease.

Objective:Surgery intervention and its effect on pregnancy heart disease were explored. Meth-ods:Retrospective review of 34 cases of pregnancy heart disease who needed surgery intervention from Jan, 2000 to Dec,2007 was done. Results:17 patients had percutaneous balloon mitral valve (PBMV) dilatation, the area of mitral valve enlarged markedly postoperatively ( P <0.01 ). 9 patients had open chest surgery un-der extracorpory circulation,7 of them had re-replacement mechanical valve due to mechanical valve throm-bosis. One patient had left atrium mucomamectomy. One patient had Wad's sinus breakout and repairmen. 5 patients had Radiofrequency catheter ablation (RFCA) for supraventricular tachycardia. 3 patients had int-racardiac device (ICD) for Ⅲ grade atrioventicular block. 22 patients had cardiac function as grade Ⅲ～Ⅳ and postoperatively recovered to grade Ⅰ～Ⅱ . All 34 patients were alive after treatment, 23 fetus were alive (67.6%), and no adverse results were found during the follow-up. Conclusions:When patients who had pregnancy heart disease need surgery intervention, individualized treatment plan should be made by multidis-cipline experienced doctors according to different heart disease and cardiac function.

Objective To explore the effect of therapeutic touch(massage)on the neuTobehavior of preterm infants.Methods Sixty preterm infants( gestafional age in 31-36 weeks),through natural delivery or caesarean section were randomly assigned to therapeutic touch group(n=30)and control group(n=30).Both groups re-ceived routine pharmacothempy and nursing care and followed up for half a year from discharge.Touch group re-ceived additional whole-body massage.All subjects were evaluated with neonatal behavioral neurological assessment (NBNA)in one month after birth-and mental development index(MDI), psyehomotor development index(PDI)in 3 months and 6 months after birth.Results The NBNA scores(P<0.01),as well as MDI and PDI(P<0.05)were significantly higher in therapeutic touch group than the control.Conclusion Therapeutic touch intervention im-proves nervous system of preterm infants.