Objective To establish an IT-based follow-up platform, and to explore its application effect in patients with ischemic stroke.Methods By constructing a follow-up model and a recurrence risk warning model for ischemic stroke patients, such a follow-up platform was established.Thanks to the retrospective comparative and analysis method, we built a study group comprising ischemic stroke patients discharged since the platform and a control group comprising 228 such patients discharged prior to the platform.These two groups were followed up by means of IT-based manner and traditional paper-based manner respectively at the first,third,sixth,ninth,and twelfth months since their discharge.These patients were analyzed in terms of their medication adherence,activities of daily living and recurrence rate.Results One year after the follow-up,32 cases were lost of contact in the study group and 42 cases from the control group.Medication adherence of the study group was higher than that of the control group at the sixth month (2.72 ±0.62), ninth month(2.86 ±0.37)and twelfth month(2.83 ±0.40)after discharge, with the differences being statistically significant(P <0.05).The recurrence rate of the study group at the ninth months(6.38%)and twelfth months(10.21%)after follow-up was lower than that of the control group,a difference being statistically significant(P<0.05).The difference of BI scores between the two groups was not statistically significant(P>0.05).Conclusions The IT-based follow-up platform could improve the medication adherence of ischemic stroke patients,and reduce the recurrence rate of ischemic stroke,but the effect of improving activities of daily living was still not significant.

Objective To explore the clinical value of combined detection of Hcy,Cys C,D-D and hs-CRP in predicting prognosis of patients with pregnancy induced hypertension.Methods A total of 105 patients with pregnancy induced hypertension treated in our hospital were selected as pregnancy induced hypertension group,and 60 single pregnant women with the same gestational age were selected as control group.The serum levels of Hcy,Cys C,D-D and hs-CRP were measured in all patients.The preeclampsia pregnancy induced hypertension patients were divided into mild preeclampsia subgroup (n =45) and severe preeclampsia subgroup (n =60) according to the blood pressure.The indicators of each group and its correlation with the degree of pre eclampsia were observed.Results The levels of Hcy,Cys C,D-D and hs-CRP in the pregnancy induced hypertension group were significantly higher than that in the control group (P ＜ 0.05).Severe preeclampsia subgroup had higher Hcy,Cys C,D-D and hs-CRP levels than mild preeclampsia subgroup (P ＜ 0.05).The joint detection of the above indicators had higher sensitivity and specificity than single detection (P ＜0.05).Conclusion The indicators of Hcy,Cys C,D-D and hs-CRP are significantly and positively correlated with the stage of preeclampsia in pregnancy induced hypertension.The sensitivity and specificity of the combined detection of Hcy,Cys C,D-D and Hs-CRP levels are significantly better than that of single detection,so it has better clinical value.

Objective To explore the clinical value of combined detection of Hcy,Cys C,D-D and hs-CRP in predicting prognosis of patients with pregnancy induced hypertension.Methods A total of 105 patients with pregnancy induced hypertension treated in our hospital were selected as pregnancy induced hypertension group,and 60 single pregnant women with the same gestational age were selected as control group.The serum levels of Hcy,Cys C,D-D and hs-CRP were measured in all patients.The preeclampsia pregnancy induced hypertension patients were divided into mild preeclampsia subgroup (n =45) and severe preeclampsia subgroup (n =60) according to the blood pressure.The indicators of each group and its correlation with the degree of pre eclampsia were observed.Results The levels of Hcy,Cys C,D-D and hs-CRP in the pregnancy induced hypertension group were significantly higher than that in the control group (P ＜ 0.05).Severe preeclampsia subgroup had higher Hcy,Cys C,D-D and hs-CRP levels than mild preeclampsia subgroup (P ＜ 0.05).The joint detection of the above indicators had higher sensitivity and specificity than single detection (P ＜0.05).Conclusion The indicators of Hcy,Cys C,D-D and hs-CRP are significantly and positively correlated with the stage of preeclampsia in pregnancy induced hypertension.The sensitivity and specificity of the combined detection of Hcy,Cys C,D-D and Hs-CRP levels are significantly better than that of single detection,so it has better clinical value.

Objective:To aid in the detection of thyroid cancer by using deep learning to differentiate the unique bioimpedance parameter patterns of different thyroid tissues.Methods:An electrical impedance system was designed to measure 331 ex-vivo thyroid specimens from 321 patients during surgery. The impedance data was then analyzed with one dimensional convolution neural (1D-CNN) combining with long short-term memory (LSTM) network models of deep learning. In the process of analysis, we assigned 80% of the data to training set (1072/1340) and the remaining 20% data to the test set (268/1340). The performance of final model was assessed using receiver operating characteristic (ROC) curves. In addition, sensitivity, specificity, positive predictive value, negative predictive value, Youden index were applied to compare impedance model with ultrasound results.Results:The ROC curve of the two-classification (malignant /non-malignant tissue) model showed a good performance (area-under-the-curve AUC=0.94), with an overall accuracy of 91.4%. To better fit clinical practice, we further performed a three-classification (malignant/ benign/ normal tissue) model, of which the areas under ROC curve were 0.91, 0.85, 0.92 for normal, benign, and malignant group, respectively. The results indicated that the area under micro-average ROC curve and the macro-average ROC curve were 0.91 and 0.90, respectively. Moreover, compared with ultrasound, the impedance model exhibited higher specificity.Conclusions:A deep learning model (CNN-LSTM) trained by thyroid electrical impedance spectroscopy (EIS) parameters shows an excellent performance in distinguishing among different in-vitro thyroid tissues, which is promising for applications. In future clinical utility, our study does not replace existing tests, but rather complements others, thus contributing to therapeutic decision-making and management of thyroid disease.

Objective To investigate the current situation of occupational environment identity of nursing clinical practice teachers in an affiliated hospital of a university in Xinjiang Uygur Autonomous Region with the Gallup Q12 so as to propose management model for improvement.Methods Nursing clinical practice teachers were extracted from 1 April 2016 to 30 April 2016 by stratified cluster sampling. The Gallup Q12 was sent out. The proportion of the best answers among 12 items of four dimensions and the average score were analyzed.Results The average score of Q12 of nursing clinical practice teachers was 3.9 higher than the fiftieth percentile (3.78) of Gallup database lower than the seventy-fifth percentile (4.13). The proportion of the best answers among the second and fourth base camp was relatively low with the third, fifth and sixth item for the lowest scores.Conclusions Take aspects with low recognition as management angle to concretely improve management model and build a healthy work environment under the effect of 12 items management of the Gallup Q12. Stabilize the team of nursing clinical practice teaching, and improve the capability of nursing clinical practice teachers, and promote the development of career identity in nursing students so as to play a constructive role in teacher team reconstruction of nursing education.

Purpose To explore the artificial intelligence(AI)-assisted diagnosis system of thyroid cancer based on deep transfer learning and evaluate its clinical application value.Methods The HE sections of 682 cases thyroid disease patients(including benign lesions,papillary carcinoma,follicular carci-noma,medullary carcinoma and undifferentiated carcinoma)in the Pathology Department of the Renmin Hospital of Wuhan Uni-versity were collected,scanned into digital sections,divided into training sets and internal test sets according to the ratio of 8 ∶ 2,and the training sets were labeled at the pixel level by patholo-gists.The thyroid cancer classification model was established u-sing VGG image classification algorithm model.In the process of model training,the parameters of the breast cancer region recog-nition model were taken as the initial values,and the parameters of the thyroid cancer region recognition model were optimized through the transfer learning strategy.Then the test set and 633 intraoperative frozen HE section images of thyroid disease in Jianli County People's Hospital,Jingzhou City,Hubei Province wereused as the external test set to evaluate the performance of the established AI-assisted diagnostic model.Results In the internal test set,without the use of the breast cancer region rec-ognition model transfer learning,the accuracy of the AI-assisted diagnosis model was 0.882,and the area under the Receiver op-erating characteristic(AUC)valuewas0.938;However,inthe use of the Transfer learning model,the accuracy of the AI-assis-ted diagnosis model for was 0.926,and the AUC value was 0.956.In the external test set,the accuracy of the zero learning model was 0.872,the AUC value was 0.915,and the accuracy of the Transfer learning model was 0.905,the AUC value was 0.930.Conclusion The AI-assisted diagnosis method for thy-roid cancer established in this study has good accuracy and gen-eralization.With the continuous development of pathological AI research,transfer learning can help improve the performance and generalization ability of the model,and improve the accura-cy of the diagnostic model.

Isolated pontine infarction (IPI) is the main type of acute brainstem infarction. Due to the application of high-resolution MRI, the research on the etiology of IPI has gradually increased in recent years. This article reviews the latest research progress on the characteristics of basilar artery plaques and disease progression mechanisms of IPI, aiming to provide reference for the etiology research of IPI.

Objective:To investigate the serotype distribution and drug resistance of Streptococcus pneumoniae ( S. pneumoniae) isolated in Urumqi Children′s Hospital and to evaluate the significances of 13-valent pneumococcal conjugate vaccine (PCV13) in preventing infection and controlling drug resistance. Methods:The S. pneumoniae isolates stored in clinical laboratory of Urumqi Children′s Hospital from January to December in 2018 were re-cultured.The serotypes were detected by capsule swelling experiment to assess the coverage rate of PCV13.The minimum inhibitory concentration (MIC) of Penicillin, Amoxicillin, Cefotaxime and Ceftriaxone were detected by E-test method, and the susceptibility of the isolates to Meropenem and other 9 antibiotics was detected by VITEC 2 Compact system. Results:A total of 225 S. pneumoniae strains were identified.The common serotypes were 19F (32.9%), 23F (12.0%), 19A (10.7%), 6B (10.2%) and 6A (8.0%). PCV13 coverage rate was 80.4%.There was no significant difference in serotype distribution and PCV13 coverage between children < 2 years old and ≥ 2 years old, as well as between Han and minority people.The 57.8% and 31.7% strains showed intermediate susceptibility and resistance against oral Penicillin, respectively.Based on the breakpoints for meningitis, 89.4% strains were resistant against pare-nteral Penicillin, and 47.5% and 64.6% strains were non-susceptible (mainly intermediately susceptible) to Ceftria-xone and Cefotaxime, respectively.The resistance rates of strains against Erythromycin, Sulfamethoxazole-trimethoprim and Tetracycline were as high as 98.1%, 67.6% and 89.6%, respectively.More than 90% tested isolates were susceptible to Amoxicillin, Meropenem, Levofloxacin or Moxifloxacin.PCV13 strains were more resistant to Penicillin than non-PCV13 strains. Conclusions:The serotypes 19F, 23F, 19A, 6B and 6A are common among the S. pneumoniae isolated in Urumqi.The coverage rate of PCV13 is about 80%.There was no significant difference in serotype distribution between Han and minority nationality children. S. pneumoniae were frequently resistant against Erythromycin.The high resistance to Penicillin and other beta-lactams should be taken into account when treatment is decided for suspected pneumococcal meningitis.Universal administration of PCV13 would be effective strategy to prevent pneumococcal infection in children and to control the drug resistance of S. pneumoniae.

Objective:To develop a Self-rating Scale for Scientific Research Ability of Nursing Staff and conduct reliability and validity test.Methods:Based on literature review, qualitative interview and expert letter consultation, the first draft of the Self-rating Scale for Scientific Research Ability of Nursing Staff was formed. By the convenient sampling method, a total of 924 nursing staff from Tongji Hospital Affiliated to Tongji Medical College of Huazhong University of Science and Technology were selected as the research objects from February to March 2021 for questionnaire survey to test the reliability and validity of the scale.Results:Two common factors were extracted from exploratory factor analysis, including 13 items, and the cumulative variance contribution rate was 82.088%. Confirmatory factor analysis suggested that the model fit well. Content validity index at item level was 0.833~1.000, and content validity index at scale level was 0.865. The Cronbach's α coefficient of the total scale was 0.971, and the Cronbach's α coefficient of each dimension was 0.913 and 0.974. The total split-half reliability coefficient of the scale was 0.941, and split-half reliability coefficient of each dimension was 0.932 and 0.964.Conclusions:The self-rating scale for scientific research ability of nursing staff has good reliability and validity, which can be used as an evaluation tool of research ability of nursing staff.