Objective To propose a frequency-domain pulse wave prediction model based on fusion attention mechanism,improving the low classification accuracy and poor generalization performance of hypertension time-domain pulse wave classification based on artificial intelligence technology.Methods Firstly,the time-domain pulse wave was transformed into frequency-domain Mel-scale frequency cepstral coefficient features to enhance its discriminability.Then,temporal convolutional network and Transformer structures were employed to extract the deep features of pulse waves,and self-attention mechanism and selective kernel attention were combined for decision fusion to extract relevant features.Floodings regularization method was used to indirectly control the training loss and prevent overfitting.A 5-fold cross-verification experiment was conducted based on 527 clinical pulse diagnosis data provided by Longhua Hospital,Shanghai University of Traditional Chinese Medicine and Shanghai Traditional Chinese Medicine-Integrated Hospital.Additionally,the extreme gradient boosting algorithm was employed to calculate the contribution rate ranking of frequency-domain pulse wave features,and the key factors affecting the classification accuracy of the model were analyzed to provide reference for the clinical auxiliary diagnosis of traditional Chinese medicine.Results The evaluation metrics accuracy,F1 score,precision,recall rate and area under curve value of the model proposed in this study were 0.939 6,0.924 9,0.940 9,0.929 5,and 0.993 4,respectively.The static characteristics of the pulse wave,the contribution rate of the first-order difference and the second-order difference coefficients were relatively balanced,indicating that the degree of hypertension risk was not only related to the static characteristics of the pulse wave,but also to the dynamic characteristics of the pulse wave.Conclusion The proposed model has higher classification accuracy and generalization performance compared to typical pulse wave classification models.

Objective To study the clinical and CT findings of bronchiolar adenoma. Methods Patients diagnosed with bronchiolar adenoma confirmed by surgical pathology at Linyi People's Hospital and Yantai Yuhuangding Hospital from 2016 to 2021 were collected. Their clinical and CT imaging features were retrospectively analyzed. Results Finally, 25 patients were collected, including 6 males and 19 females, aged 32-73 (58.6±10.1) years. The immunohistochemical Ki-67 (MIB1) of all lesions was <5%. The lesions were located in the upper and middle lobe of both lungs in 9 patients, lower lobes in 16 patients, extrapulmonary zone in 22 patients, intrapulmonary middle zone in 3 patients, round in 11 patients, irregular in 14 patients, well-defined in 22 patients, pure ground-glass/mixed ground-glass nodules in 6 patients, solid nodules in 19 patients. There were 11 patients with central small cavity, 18 patients with single bronchioles sign, 19 patients without adhesion with adjacent pleura, and 24 patients without mediastinal lymph node enlargement. Conclusion Bronchiolar adenomas usually occur in the middle-aged and elderly, mostly in the lower lobe of both lungs and the distribution of the peripheral lung field, most of the patients do not have any clinical symptoms, and the postoperative prognosis is good. CT may show large nodules or masses, pure ground-glass/mixed ground-glass nodules, irregular solid nodules and central small cavities. Irregular stellate nodules, central small cavity shadow, and single bronchiolar vascular bundle connected with the lesions are relatively specific imaging findings of bronchiolar adenoma.

Objective:To analyze clinical characteristics and high-frequency ultrasound features of localized scleroderma, and to construct and validate a non-invasive prediction model for staging of skin lesions based on the high-frequency ultrasound features.Methods:Patients with localized scleroderma were retrospectively collected from the Department of Dermatology and Venereology, Second Xiangya Hospital of Central South University from February 1, 2021 to February 28, 2023, and clinical data as well as high-frequency ultrasound and pathologic features of 85 lesions from these patients were analyzed. Lesions were divided into modeling cohort and validation cohort according to the chronological order of patient enrollment. The univariate analysis and multivariable logistic regression models were used to analyze the independent influential factors in the staging of localized scleroderma lesions in the modeling cohort, construct the regression equation, and to build a nomogram prediction model. The Bootstrap validation method was used for internal validation, and the predictive performance of the nomogram model in the modeling cohort and validation cohort was further evaluated by the calibration curve and receiver operating characteristic (ROC) curve.Results:In the modeling cohort, 60 patients with localized scleroderma, including 16 males and 44 females, were enrolled, with the age [ M ( Q1, Q3) ] being 22.0 (10.0, 39.2) years, and there were 28 lesions in the oedematous phase and 32 lesions in the fibrotic and atrophic phase; in the validation cohort, 25 patients with localized scleroderma, including 8 males and 17 females, were enrolled, with the age being 18.0 (7.0, 30.0) years, and there were 9 lesions in the oedematous phase and 16 lesions in the fibrotic and atrophic phase. Univariate analysis in the modeling cohort showed no significant differences in the age and gender of patients or the location of lesions between the oedematous phase group and the fibrotic and atrophic phase group (all P > 0.05) ; compared with the oedematous phase group, the fibrotic and atrophic phase group showed an increased proportion of patients with disease duration ≥ 2 years (20/32 cases vs. 10/28 cases, χ2 = 4.29, P = 0.038), decreased thicknesses of the subcutaneous fat layer in skin lesions (1.4 [0.0, 26.0] mm vs. 1.8 [0.1, 14.3] mm, Z = -2.14, P = 0.032), increased decrements in the subcutaneous fat layer thickness in the lesional sites compared with non-lesional control sites (1.8 [0.5, 11.0] vs. 0.3 [-1.9, 8.0] mm, Z = -4.72, P < 0.001), increased ratios of the lesional elasticity values to control elasticity values (2.9 [1.8, 6.9] vs. 1.8 [1.1, 5.9], Z = -4.34, P < 0.001), and increased ultrasound-based lesional activity scores (5.0 [3.0, 8.0] points vs. 3.0 [0.0, 5.0] points, Z = -4.76, P < 0.001). Multivariable logistic stepwise regression analysis showed that the disease duration ≥ 2 years ( P = 0.032), increased ratios of the lesional elasticity values to control elasticity values ( P = 0.019), increased ultrasound-based lesional activity scores ( P = 0.013), and increased decrements in the subcutaneous fat layer thickness in the lesions compared with the controls ( P = 0.013) helped to confirm localized scleroderma lesions in the fibrotic and atrophic phase. Based on the results of regression analysis, a total of 4 factors were included in the nomogram prediction model, including the disease duration, the decrement in the subcutaneous fat layer thickness in lesions compared with controls, the ratio of the lesional elasticity values to control elasticity values, and the ultrasound-based lesional activity score; additionally, the constructed logistic regression model formula for predicting the probability (p) of skin lesions in fibrotic and atrophic phase was "ln (p/[1 - p]) = -9.595 + 2.204 × the disease duration + 0.784 × the decrement in the subcutaneous fat layer thickness in the lesions compared with the controls (mm) + 0.887 × the ratio of the lesional elasticity values to control elasticity values + 1.374 × the ultrasound-based lesional activity score". The calibration curve showed a good predictive performance of the model through the Bootstrap validation method, and the ROC curve demonstrated good discrimination and accuracy (modeling cohort: area under the curve = 0.936, 95% CI: 0.879 - 0.994; validation cohort: area under the curve = 0.889, 95% CI: 0.748 - 1.000) . Conclusions:High-frequency ultrasound could provide essential details for staging the localized scleroderma lesions. Based on the disease duration, subcutaneous fat layer thickness, skin elasticity values, and ultrasound-based lesional activity scores, the constructed prediction model could predict the stages of localized scleroderma lesions with excellent discrimination, accuracy, and predictive performance.

Background: No currently available biomarkers or treatment regimens fully meet therapeutic needs of type 1 diabetes mellitus (T1DM). Circular RNA (circRNA) is a recently identified class of stable noncoding RNA that have been documented as potential biomarkers for various diseases. Our objective was to identify and analyze plasma circRNAs altered in T1DM. Methods: We used microarray to screen differentially expressed plasma circRNAs in patients with new onset T1DM (n=3) and age-/gender-matched healthy controls (n=3). Then, we selected six candidates with highest fold-change and validated them by quantitative real-time polymerase chain reaction in independent human cohort samples (n=12). Bioinformatic tools were adopted to predict putative microRNAs (miRNAs) sponged by these validated circRNAs and their downstream messenger RNAs (mRNAs). Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses were performed to gain further insights into T1DM pathogenesis. Results: We identified 68 differentially expressed circRNAs, with 61 and seven being up- and downregulated respectively. Four of the six selected candidates were successfully validated. Curations of their predicted interacting miRNAs revealed critical roles in inflammation and pathogenesis of autoimmune disorders. Functional relations were visualized by a circRNA-miRNA-mRNA network. GO and KEGG analyses identified multiple inflammation-related processes that could be potentially associated with T1DM pathogenesis, including cytokine-cytokine receptor interaction, inflammatory mediator regulation of transient receptor potential channels and leukocyte activation involved in immune response. Conclusion Our study report, for the first time, a profile of differentially expressed plasma circRNAs in new onset T1DM. Further in silico annotations and bioinformatics analyses supported future application of circRNAs as novel biomarkers of T1DM.

No currently available biomarkers or treatment regimens fully meet therapeutic needs of type 1 diabetes mellitus (T1DM). Circular RNA (circRNA) is a recently identified class of stable noncoding RNA that have been documented as potential biomarkers for various diseases. Our objective was to identify and analyze plasma circRNAs altered in T1DM.

Objective:To investigate the relationship between the depressive symptoms and blood biochemical indexes in elderly inpatients.Methods:Totally 201 inpatients without depression were enrolled in this study.Blood tests and the Geriatric Depression Scale-5 (GDS-15) were performed on all of the patients.The patients were divided into non-depressive symptoms group and depressive symptoms group according to GDS-15 score.Differences between two groups were compared, and multiple linear regression analysis was used to screen for risk factors by SPSS 22.0.Results:Serum total protein (TP) [ (60.7±4.3) vs. (63.5±5.6) g/L] and hemoglobin [ (121.6±20.1) vs. (129.7±19.4) g/L] were lower in the depressive symptoms group than in the non-depressive symptoms group (Ps＜0.05).There were no differences between the two groups in age, BMI, fasting blood glucose, total cholesterol, triglyceride, high density lipoprotein cholesterol and low density lipoprotein cholesterol (Ps＞0.05).Multiple linear regression analysis showed that TP was the predictive variable for GDS-15 score (β=-0.4, P＜0.05).Conclusion:Serum total protein and hemoglobin levels in patients with depressive symptoms may be significant lower than those in patients without depressive symptom.There is association between serum total protein and depressive symptoms.

Objective To study the clinical characteristics and treatment outcome of infants with bacterial meningitis (BM) under 6 months.Methods Seventy-two cases of infants with BM under 6 months were retrospectively analyzed.Among them,the infants of age ranging from 29 days to 30 days were assigned into the 1 month age group,60 days to 179 days infants were assigned into the 2 to 5 months old group.Results The incidence of BM was more common in male (51 cases,70.8％) and infants with the age of 1 month (45 cases,62.5％).The clinical manifestations included fever (71 cases,98.6％),procalcitonin increase (55 cases,76.3％),respiratory tract infection (48 cases,66.6％),peripheral blood WBC count abnormal results (34 cases,47.3％),abnormal blood CRP (20 cases,27.8％) and nervous system abnormalities (18 cases,25％).Among the 1 month old group,12 infants had urinary tract infection (16.6％),and 6 had convulsions (8.3％).There were 4 cases (5.5％) with subdural effusion in the 2 ～ 5 months old group.Compared with the 2 ～ 5 months old group,the 1 month old group was more likely to be caused by urinary tract infection,more prone to seizures,the difference was statistically significant (x2 =3.996,3.927,P＜0.05).Compared with the 1 month old group,the 2 ～ 5 months old group was more prone to subdural effusion,and the peripheral blood white blood ceils was higher,the difference was statistically significant (x2 =7.059,4.295,P＜0.05).Conclusion There is no obvious clinical manifestation or laboratory examination for infants under 6 months old BM,so it is necessary to make early cerebrospinal fluid examination for early diagnosis and early treatment.

Objective To analyze the difference of laboratory test results between early-onset and late-onset severe preeclampsia and to investigate their clinical application values.Methods Totally 108 blood samples were collected from patients with severe preeclampsia who were diagnosed according to the Diagnostic Standard of Obstetrics and Gynecology(7th Edition) published by People′s Medical Publishing House,in Shandong Provincial Hospital affiliated to Shandong University from March to November 2016,which consisted of 64 early-onset severe preeclampsia before 34 weeks gestation(early onset group) and 44 late-onset severe preeclampsia after 34 weeks gestation(late onset group).In addition,42 women with normal pregnancies as the control group were selected.General clinical data were collected,and the blood sample was analyzed through detecting Hb,PLT,fibrinogen (FIB),D-dimer,AST,ALT,urea,creatinine (Cr),uric acid,CRP,urine protein.The tested results were analyzed and compared.Flow cytometry was used to analyze the proportion of T helper 1 cells(Th1) and T helper 2 cells(Th2),and the ratio of Th1/Th2 was also calculated.All data and F test were performed by use of statistical software SPSS19.0.Results The pre-pregnancy body mass index(29.55±4.49,30.66±5.13,26.62±3.17,F=9.829,P<0.05),diastolic blood pressure[(105.17±14.46)mmHg(1 mmHg=0.133 kPa),(99.80±12.56)mmHg,(74.36±8.42)mmHg,F=82.088,P<0.05],Hb[(123.22±14.38)g/L,(117.03±16.48)g/L,(112.62±11.24)g/L,F=7.133,P<0.05],urea[(6.56±2.36)mmol/L,(4.51±1.35)mmol/L,(3.04±0.87)mmol/L,F=51.733,P<0.05],Cr[(68.47±18.05)μmol/L,(61.37±14.37)μmol/L,(48.54±8.73)μmol/L,F=23.737,P<0.05],CRP[(7.68±8.76)mg/L,(5.88±6.03)mg/L,(3.56±2.41)mg/L,F=4.735,P<0.05],urine protein[(3.66±0.76)g/L,(2.20±1.05)g/L,(0.19±0.40)g/L,F=249.714,P<0.05]had a statistically significant difference among the early-onset,late-onset and control groups.The flow cytometry results demonstrated that the proportion of Th1 in early-onset group(19.83±3.04)was higher than that in both late-onset (14.49±2.79)and control groups(11.78±1.17),on the contrary,the result of Th2 was much lower(early-onset:1.02±0.12,late-onset: 1.11±0.12,control: 1.56±0.11),there was statistical significance among these three groups(Th1: F=135.110,P<0.05;Th2: F=293.687,P<0.05).Conclusions It′s necessary to real-time monitor the laboratory indicators,such as liver and kidney function,especially the immunologic function indicators for evaluating the disease of early-onset and late-onset severe preeclampsia and personal treatment,and for ensuring the health of mother and fetus and improving the prognostic of mother and fetus.

Objective To observe the efficacy and safety of endoscope and laparoscope in treatment of acutebiliary pancreatitis.Methods 84 patients with acute biliary pancreatitis from January 2010 to January 2014 in our hospital during treatment were randomly divided into the study group and control group according to the random num-ber table methods,42 cases in each group.The control group was treated with conservative treatment of department of internal medicine,while the study group was treated with duodenoscopy combined with laparoscopy.To observe and compare the efficacy and adverse reactions of two groups.Results Temperature returned to normal time,abdominal pain relief time,recovery time of amylase in urine,recovery time of biochemical index,hospitalization time and cost of hospitalization of the study group after treatment were (3.44 ±1.63)d,(4.73 ±1.12)d,(7.82 ±3.31)d,(9.81 ± 6.42)d,(12.43 ±4.61 )d,which were significantly lower than (5.94 ±2.43)d,(7.53 ±2.12)d,(11.72 ± 2.21)d,(18.41 ±8.62)d,(20.33 ±6.21)d of the control group(t =3.90,4.02,4.26,4.50,5.01,all P <0.05). 2 cases of the study group occured biliary tract bleeding,2 cases with pancreatic pseudocyst,1 case with wound infec-tion,there was no recurrence,the incidence rate of adverse reaction was 11.90%;3 cases of the control group after treatment occurred pancreatic pseudocyst,2 cases with abdominal cysts,5 cases with recurrence,1 case with acute respiratory distress syndrome (ARDS),1 case with renal failure,the incidence rate of adverse reactions was 28.57%, which of the control group was significantly higher than the study group (χ2 =4.21,P <0.05 ).Conclusion Duodenal endoscopy combined with laparoscopy has good clinical effect,shorter hospitalization time,less cost,less adverse reaction and the recurrence rate is low in treatment of acute biliary pancreatitis,which has high application value.

Hospital information technology has introduced a new mode of colaborative work based on heterogeneous systems and it wil become the new norm. The article ilustrates some successful typical cases of information exchange in the heterogeneous systems for colaborative work in Chinese PLA general hospital and puts forward some principles in the hospital’s design of heterogeneous information systems.