Through analyzing the existing problems and relevant solutions of TCM decoction pieces management, this article expounded the construction of TCM coding system and its construction and application in the hospital information system, attempted to apply technological standards of TCM coding system to routine TCM standardized management work through the means of informatization. At the same time, it also described the basic situation in the construction of TCM coding management information system, and promoted specific ideas, operation methods, and current condition and prospects.

OBJECTIVETo compare the effect of the two methods of back propagation network (BPN) test on TCM syndrome typing of depression.

METHODSTest was carried out by two methods as following: (1) Cross train-test method: 1731 patients with depression typed to 5 syndrome types were randomly divided into 2 groups, and they were trained and tested in turn; (2) Round-Robin method: Test was conducted in an altered cycle mode, that is, in a cycle, one out of the 1731 patients were selected to be tested, while the others were trained, the next cycle started when the test on the selected patient was finished and another one for test was selected. In this way, one cycle after the other, until all patients had been tested.

RESULTThe total training sensitivity of the two methods was 97.9% and 98.2% respectively, and the total testing sensitivity was 72.7% and 74.2% respectively.

CONCLUSION(1) The five TCM syndrome types of depression could be well differentiated by BPN, which is valuable for TCM syndrome typing in certain extent; (2) The sensitivity of Round-Robin method is slightly higher than that of Cross train-test method, but in comparison between them no remarkable significance was shown.

Adolescent ; Adult ; Depressive Disorder ; diagnosis ; Diagnosis, Differential ; Female ; Humans ; Male ; Medicine, Chinese Traditional ; Middle Aged ; Neural Networks (Computer) ; Sensitivity and Specificity

Objective: To explore the relationship between cerebral hemorrhagic transformation (HT) and angiographic early venous filling (EVF) following mechanical thrombectomy for acute ischemic stroke. Methods: A retrospective imaging analysis was performed in the consecutive patients treated from January 2015 to November 2018 for acute anterior circulation large vessel occlusion using mechanical thrombectomy on the Affiliated Hospital of Yangzhou University. The demography, vascular risk factors and other clinical data of the patients were also collected. According to the experimental study of European Cooperative Acute Stroke Study Ⅱ (ECASS Ⅱ), the modified classification of HT after mechanical thrombectomy was divided into HT negative, HT-Ⅰ type and HT-Ⅱ type. The differences in EVF, clinical and demographic characteristics were compared. Multivariate logistic regression analysis was used to identify the independent risk factors for HT and clinical outcome. Diagnostic test characteristics of EVF for HT-Ⅱ type were determined using a receiver operating characteristic curve (ROC) analysis. Results: A total of 98 patients with acute ischemic stroke who received mechanical thrombectomy were enrolled, including HT negative in 48 cases (49.0%, 48/98), HT-Ⅰ in 40 cases (40.8%, 40/98) and HT-Ⅱ in 10 cases (10.2%, 10/98). Significant differences were noted in age, and incidence of atrial fibrillation, EVF and poor outcomes among three groups (P<0.05). Multivariate logistic regression analysis showed that EVF [odds ratio (OR) 5.960, 95%CI 1.750-8.960, P=0.001] and atrial fibrillation (OR 3.485, 95%CI 1.962-18.986, P=0.028) were risk factors for the occurrence of HT-Ⅱ after mechanical thrombectomy. No risk factor for HT-Ⅰ was noted. Baseline National Institute of Health Stroke Scale (NIHSS) score (OR 1.162, 95%CI 1.021-1.345, P=0.038), EVF (OR 5.358, 95%CI 1.665-13.653, P=0.006) and HT-Ⅱ (OR 1.326, 95%CI 1.226-2.038, P=0.032) were independent risk factors for poor outcomes. And the sensitivity and specificity of EVF in prediction for HT-Ⅱ were 80.0% and 86.4% respectively, with the area under the ROC curve of 0.832. Conclusion Presence of EVF after mechanical thrombectomy may be the predictor for HT-Ⅱ, which indicates the poor clinical outcomes for acute ischemic stroke patients.