Talents are the main force for the development of traditional Chinese medicine（TCM）， and the construction of TCM talents and the reformation of talent evaluation system are essential to promote the inheritance and innovation of TCM. At present， we are still exploring and developing in the fields of the formulation， implementation and evaluation indicators of TCM talent evaluation system. However， there are shortcomings and difficulties. For instance， insufficient stratification in the evaluation， excessive emphasis on the quantity of achievements， neglecting the quality of the achievements and the actual contribution， imperfect assessment indicators， and the weak characteristics of TCM. Therefore， national ministries and commissions have jointly issued a document requesting to break the four only and set a new standard， in order to promote the construction of a scientific and technological talent evaluation system oriented by innovation value， ability and contribution. For the evaluation of TCM clinical talents， China Association for Science and Technology commissioned China Association of Chinese Medicine to build the China Clinical Cases Library of TCM（CCCL-TCM）， which aims at collecting the most authoritative and representative TCM clinical cases and exploring the advantages of applying clinical cases as masterpiece of achievement in TCM clinical talents evaluation. CCCL-TCM can promote the construction of a talent evaluation system that is more in line with the development characteristics of TCM industry， and to carry out relevant pilot in TCM colleges and institutions across the country in order to promote the reformation of TCM talent evaluation system.

Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, Q ^AB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.
Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Tomography, X-Ray Computed ; Magnetic Resonance Imaging/methods* ; Algorithms

Objective:To analyze the risk factors of bronchopulmonary dysplasia(BPD)in very preterm infants(VPI), and to provide scientific basis for the prevention and treatment of BPD in VPI.Methods:A prospective multicenter study was designed to collect the clinical data of VPI in department of neonatology of 28 hospitals in 7 regions from September 2019 to December 2020.According to the continuous oxygen dependence at 28 days after birth, VPI were divided into non BPD group and BPD group, and the risk factors of BPD in VPI were analyzed.Results:A total of 2 514 cases of VPI including 1 364 cases without BPD and 1 150 cases with BPD were enrolled.The incidence of BPD was 45.7%.The smaller the gestational age and weight, the higher the incidence of BPD( P<0.001). Compared with non BPD group, the average birth age, weight and cesarean section rate in BPD group were lower, and the incidence of male infants, small for gestational age and 5-minute apgar score≤7 were higher( P<0.01). In BPD group, the incidences of neonatal respiratory distress syndrome(NRDS), hemodynamically significant patent ductus arteriosus, retinopathy of prematurity, feeding intolerance, extrauterine growth restriction, grade Ⅲ~Ⅳ intracranial hemorrhage, anemia, early-onset and late-onset sepsis, nosocomial infection, parenteral nutrition-associated cholestasis were higher( P<0.05), the use of pulmonary surfactant(PS), postnatal hormone exposure, anemia and blood transfusion were also higher, and the time of invasive and non-invasive mechanical ventilation, oxygen use and total hospital stay were longer( P<0.001). The time of starting enteral nutrition, cumulative fasting days, days of reaching total enteral nutrition, days of continuous parenteral nutrition, days of reaching 110 kcal/(kg·d) total calorie, days of reaching 110 kcal/(kg·d) oral calorie were longer and the breastfeeding rate was lower in BPD group than those in non BPD group( P<0.001). The cumulative doses of amino acid and fat emulsion during the first week of hospitalization were higher in BPD group( P<0.001). Multivariate Logistic regression analysis showed that NRDS, invasive mechanical ventilation, age of reaching total enteral nutrition, anemia and blood transfusion were the independent risk factors for BPD in VPI, and older gestational age was the protective factor for BPD. Conclusion:Strengthening perinatal management, avoiding premature delivery and severe NRDS, shortening the time of invasive mechanical ventilation, paying attention to enteral nutrition management, reaching whole intestinal feeding as soon as possible, and strictly mastering the indications of blood transfusion are very important to reduce the incidence of BPD in VPI.

Objective : To investigate the association between c. 1311C > T and c. 1004C > A of glucose⁃6 ⁃phosphate dehydrogenase (G6PD) gene single nucleotide polymorphism ( SNP) with the risk of G6PD deficiency in Guangxi population. Methods : 417 patients with G6PD deficiency were randomly selected as case group , and 295 healthy patients were selected as control group. The c. 1311C > T and c. 1004C > A were genotyped using the SNPscanTM multiple SNP method , and the haplotype frequency of two sites were analyzed by SHEsis. Results : In the case and control group , there were statistically significant differences in the distribution frequency of genotype TT , CC + CT and allele T at c. 1311C > T locus [TT vs CC :(P = 0. 001 , OR = 0. 373 , 95% CI = 0. 204 - 0. 683) ; TT vs CC + CT :(P = 0. 001 , OR = 0. 371 , 95% CI = 0. 203 - 0. 678) ; T vs C :(P = 0. 002 , OR = 0. 601 , 95% CI = 0. 435 - 0. 829)] ;however, there was no significant difference in genotype and allele distribution frequency at c. 1004C > A locus (P > 0. 05) . The results of the rate method showed that compared with genotype CC , the genotype CT at c. 1311C > T increased the expression level of G6PD enzyme , while the genotype TT decreased the expression level of G6PD enzyme(P < 0. 05) , the haplotype analysis showed that C ⁃C and T ⁃C were associated with G6PD risk (P < 0. 05) . Conclusion In Guangxi population , c. 1311C > T locus genotypes TT , CC + CT and allele T were related to the decreased risk of G6PD deficiency.

Objective : To investigate the association between c. 1311C > T and c. 1004C > A of glucose⁃6 ⁃phosphate dehydrogenase (G6PD) gene single nucleotide polymorphism ( SNP) with the risk of G6PD deficiency in Guangxi population. Methods : 417 patients with G6PD deficiency were randomly selected as case group , and 295 healthy patients were selected as control group. The c. 1311C > T and c. 1004C > A were genotyped using the SNPscanTM multiple SNP method , and the haplotype frequency of two sites were analyzed by SHEsis. Results : In the case and control group , there were statistically significant differences in the distribution frequency of genotype TT , CC + CT and allele T at c. 1311C > T locus [TT vs CC :(P = 0. 001 , OR = 0. 373 , 95% CI = 0. 204 - 0. 683) ; TT vs CC + CT :(P = 0. 001 , OR = 0. 371 , 95% CI = 0. 203 - 0. 678) ; T vs C :(P = 0. 002 , OR = 0. 601 , 95% CI = 0. 435 - 0. 829)] ;however, there was no significant difference in genotype and allele distribution frequency at c. 1004C > A locus (P > 0. 05) . The results of the rate method showed that compared with genotype CC , the genotype CT at c. 1311C > T increased the expression level of G6PD enzyme , while the genotype TT decreased the expression level of G6PD enzyme(P < 0. 05) , the haplotype analysis showed that C ⁃C and T ⁃C were associated with G6PD risk (P < 0. 05) . Conclusion In Guangxi population , c. 1311C > T locus genotypes TT , CC + CT and allele T were related to the decreased risk of G6PD deficiency.

Ischemic stroke is prone to recurrence, which is the leading cause of death and disability in stroke. Using predictive model to assess the recurrence risk in patients with ischemic stroke, stratifying risk, and formulating corresponding interventions to reduce the recurrence rate are the core contents of secondary prevention. In this paper, research progress on the prediction of recurrence risks of ischemic stroke recently is summarized from the predicting content or factors, including clinical factors, imaging factors, biological markers and traditional Chinese Medicine syndrome differentiation, and the methods of constructing prediction models about traditional statistical methods and machine learning, in order to provide a reference for clinical work.

Objective? To investigate the effect of high-intensity interval training on glucose homeostasis and cardiac function in patients with type 2 diabetes mellitus. Methods? A total of 56 inpatients in Endocrine Department of the Fourth Affiliated Hospital of Harbin Medical University from March 2017 to August 2018 were randomly divided by convenient sampling method into an intervention group and a control group, with 28 inpatients in each. The inpatients in the control group received the standardized care process while the intervention group would further received the high intensity interval training. The homeostasis model assessment insulin resistance(HOMA-IR),ejection fractions(EF) and cardiac outpu(t CO) were compared before and after the intervention. Results? After intervention, HOMA-IR in the intervention group was (6.32±1.65)%, lower than that in the control group (7.22±1.40)%, the difference between the two groups was statistically significant (t=2.20, P=0.03). After intervention, there was no significant difference in EF and CO between the two groups (P＞0.05). Conclusions? The high intensity interval training can improve the level of glucose homeostasis in patients with type 2 diabetes, but more evidence is needed for the effect on heart function in the future.

Objective To compare the characteristics,complications and outcomes of the modified lapa-roscopic Swenson(MLSw)and laparoscopic Soave(LS)procedures for children with short-segment Hirschsprung disease(HD). Methods Seventy-seven pediatric patients with HD who underwent surgery from March 2007 to December 2016 were enrolled in this retrospective study. Twenty-six patients were treated with LS and 51 cases un-derwent MLSw. The preoperative,operative and postoperative data was collected,with follow-up periods ranging from 12 to 48 months. The perioperative/operative characteristics,postoperative complications,and outcomes were compared between the two groups. Results On average,the patients in the LS group had a longer operating time than that in the MLSw group(P < 0.05). Blood loss was significantly less in the MLSw group than that in the LS group(P < 0.05). There was no significant difference in feeding time between the two groups(P > 0.05). The MLSw group was discharged after a shorter hospitalization time than that in the LS group(P < 0.05). The MLSw group had lower incidences of postoperative complications than those in the LS group in the early postoperative period,with no significant difference in the rate of complications during the late postoperative period was found between the two groups. Conclusions Both LS and MLSw are suitable for treatment of children with short-segment HD. However,the MLSw operation is much simpler,with less operating time,less intraoperative blood loss,shorter hospitalization time and better bowel control in the early postoperative period. We favor this approach because it allows complete removal of the entire original aganglionic bowel,without leaving behind a cuff.

Objective To investigate the value of renal CT volumetric texture analysis with machine learning radiomics in assessment of pathological grade of clear cell renal cell carcinoma(ccRCC). Methods Thirty-four biopsy-confirmed ccRCC subjects who had four-phase CT scanning (NC:non-contrast, CM: Corticomedullary, N: Nephrographic, E: Excretory) were collected retrospectively from June 2013 to October 2017 for the study.Non-rigid registration was performed on multi-phase CT images in reference to CM-phase.Each lesion was segmented on CM-phase CT images using our in-house volumetric image analysis platform,"3DQI".A set of fifty-nine volumetric textures,including histogram,gradient,gray level co-occurrence matrix(GLCM),run-length(RL),moments,and shape,was calculated for each segment lesion in each phase as parameters for the training/testing of Random Forest (RF) classifier. Four groups according to pathological Fuhrman grade on a scaleⅠtoⅣ,these tumors were then divided into low(Ⅰ+Ⅱ) and high grade ( Ⅲ + Ⅳ) groups. Feature selection was performed by Boruta algorithm. A 10-fold cross-validation method was applied to validate the RF performance by receiver operating characteristic (ROC) curves analysis to determine the diagnostic accuracy of the model. Results Subjects were divided into four groups by Fuhrman grade on a scaleⅠtoⅣ:3 cases gradeⅠ,19 cases gradeⅡ,8 cases gradeⅢand 4 cases gradeⅣ.In CM-phase,kurtosis and long-run-emphasis(RLE)were selected the most important textures for ccRCC staging among 59 features. The area under curve (AUC) of ROC was 0.88 (79% sensitivity and 82% specificity)by using kurtosis and RLE textures.The mean values of kurtosis and RLE were(-20.00±22.00)×10-2and(3.00±0.40)×10-2for low group,whereas(31.00±32.00)×10-2and(5.00± 0.02)×10-2for high group.Within the mean±SD range of statistics,radiomics can distinguish between low and high grade tumors.In multi-phase analysis,three most important features were selected among 236(59× 4) textures: kurtosis (CM-phase), GLCM homogeneity I (HOMO 1) (E-phase), and GLCM homogeneity 2 (HOMO2)(E-phase).The mean values of HOMO 1(E-phase)and HOMO 2(E-phase)were(19.00±0.03)× 10-2and(11.00±0.02)×10-2for low group,whereas(22.00±0.03)×10-2and(14.00±0.02)×10-2for high group. The AUC was 0.92(93% sensitivity and 87% specificity)by using these three textures. Conclusion This study has demonstrated that renal CT volumetric texture analysis with machine learning radiomics could preoperative accurately perform cancer staging for ccRCC.

Objective To explore the effects of structural health education on the self-management and uric acid value of gout patients. Methods From January 2016 to May 2017, a total of 126 cases of gout patients in the Fourth Affiliated Hospital of Harbin Medical University were included by convenience sampling method. According to the random number table method, all the research subjects were divided into the control group and the observation group with 63 patients in each. The patients of the control group received traditional health education intervention, including education manual and health seminars. In the observation group, the structural education programs were implemented, including analyzing the patients' self-management health needs, setting goals combining with propaganda manual, arranging staged health education courses and training health education nurses and patients to focus on individual health education. The uric acid value and self-management ability were compared between two groups before intervention and 3 months after. Results After 3 months' intervention, the uric acid value of the observation group [(394.2±13.1)μmol/L] was lower than that of the control group [(427.3±14.5)μmol/L], and the difference was statistically significant (P＜0.01). The total score of self-management of the observation group (111.2±17.3) was significantly higher than that of the control group (94.5±19.4). In addition, the scores of diet control, regular exercise, drug and adverse drug reactions, follow-up and monitoring and the prevention of complications of the observation group were all higher than those of the control group, with statistical differences (P＜ 0.01). Conclusions The application of structural health education for gout patients can improve the prognosis of the disease and improve gout patients' self-management.