ObjectiveTo explore the method of optimizing the performance of traditional Chinese medicine （TCM） syndrome diagnostic models using Stacking ensemble learning. MethodsTaking the construction of TCM syndrome diagnostic model for lung cancer as an example， 2598 cases of clinical symptoms and signs from lung cancer patients in 9 hospitals were used as independent variables （i.e.， feature variables）， TCM syndrome information as dependent variables， and the clinical data were divided into training set and testing set in 8：2 ratio according to random number table method using Python 3.7 software. The stable features of TCM syndrome of lung cancer were screened using chi-square test， Spearman's correlation test， and Least Absolute Shrinkage and Selection Operator （LASSO） logistic regression analysis； nine machine learning algorithms are trained， including support vector machines （SVMs）， k-nearest neighbors （KNN） algorithm， Random Forest （RF）， Extremely Randomized Trees， Extreme Gradient Boosting （XGBoost）， Lightweight Gradient Boosting （LightGBM）， Adaptive Boosting （AdaBoost）， Gradient Boosting （GB） and the multi-layer perceptron （MLP）， to obtain 9 basic models. Four models with better performance were screened out from the above basic models and fused to form a fusion model by using the Stacking ensemble learning， and the fusion model was trained twice by the above nine machine learning algorithms and evaluated by accuracy rate， micro-average ROC curves， area under the curve （AUC）， and confusion matrix metrics， to screen the optimal diagnostic model. ResultsAfter data processing， 79 stable features and 13 TCM syndromes were obtained. In the basic model training， the comprehensive performance of RF， ExtraTrees， MLP and SVM basic models were better， so the predicted distributions of the syndromes of these four models were used as the secondary training data， and nine fusion models were obtained based on the Stacking ensemble learning （SVM， KNN， RF， ExtraTree， XGBoost， LightGBM， GB， AdaBoost， MLP）. Among them， the XGBoost fusion model performed the best， with an accuracy of 0.850 and 0.838 in the training set and test set， respectively， an overfitting difference of 0.012， and an area under the micro-average ROC curve of 0.996. All fusion models showed an improvement in accuracy and area under the micro-average ROC curve compared with the base model in the test set. ConclusionTaking the TCM syndrome information of lung cancer as an example， the XGBoost fusion model has significant advantages in improving the diagnostic performance of TCM syndrome information of lung cancer through Stacking ensemble learning. It can be seen that the advantages of Stacking ensemble learning to integrate multiple models and effectively improve the diagnostic efficiency of TCM diagnostic models， which provided a methodological reference for similar studies.

Objective:To investigate the early warning value of transcutaneous oxygen pressure and transcutaneous carbon dioxide pressure (TcPO 2/TcPCO 2) monitoring in patients with pressure injury in ICU. Methods:A prospective clinical observation study was conducted. Patients were selected in the department of critical care medicine of Shenzhen Hospital Affiliated to University of Chinese Academy of Sciences from December 2020 to June 2022. The general information of all patients were recorded. The data of TcPO 2 and TcPCO 2 were monitored respectively in left lying position, supine position and right lying position. According to the Braden score of patients, they were divided into low risk group and high risk group, and the monitoring results of TcPO 2/TcPCO 2 were analyzed. Results:The study included a total of 80 patients, with 46 patients in the low risk group and 34 patients in the high risk group. There were no significant differences in gender and age between the two groups (both P>0.05). There were significant differences in the Braden score and the incidence of pressure injury between the two groups (both P<0.05). There were statistically significant differences in TcPO 2 at various time points in the left lying position, supine position and right lying position between the low risk and the high risk groups (all P<0.001). Except for the 15th minute of the left lying position and right lying position, there were statistically significant differences in TcPCO2 at all other time points in the supine and right lying positions between two groups (all P<0.05). There were statistically significant differences in TcPO 2/TcPCO 2 values at various time points in different positions between two groups (all P<0.001). In supine position, TcPO 2 and TcPO 2/TcPCO 2 were positively correlated with the Braden score ( r=0.680, 0.741). TcPCO 2 was negatively correlated with the Braden score ( r=-0.771). The Braden score, TcPO 2, TcPCO 2 and TcPO 2/TcPCO 2 all have moderate diagnostic value. The cut-off values were 12.50, 41.48 mmHg, 52.29 mmHg and 0.91, respectively. And the AUC were 0.899, 0.727, 0.816 and 0.719, respectively. However, there were no significant differences in AUC between the TcPO 2, TcPCO 2, TcPO 2/TcPCO 2 and Braden score (all P>0.05). Conclusions:TcPO 2, TcPCO 2 and TcPO 2/TcPCO 2 values all have higher diagnostic value about pressure injury for patients in ICU. TcPO 2/TcPCO 2 monitoring has early risk warning value for the occurrence of pressure injury in ICU, which is worthy of clinical promotion.

Objective Analyze the risk factors associated with severe subarachnoid hemorrhage(SAH)and rebleeding in small intracranial aneurysms.Methods From July 2014 to January 2020,patients with SAH caused by small ruptured intracranial aneurysms admitted to the Neurosurgery Department of the First Affiliated Hospital,Chongqing Medical University were retrospectively and continuously included.Small intracranial aneurysms refer to intracranial aneurysms with a maximum diameter of less than 5 mm.Baseline data and clinical data of patients were collected,including age,gender,past history(hypertension,diabetes,coronary heart disease),smoking history,drinking history,admission Glasgow coma scale(GCS)score and Hunt-Hess grade.Patient imaging data were collected to clarify the characteristics of aneurysms,including the number of aneurysms(single or multiple),the shape of SAH responsible aneurysms(irregular aneurysms with subcapsular,polycystic,or lobulated aneurysms),and their location(anterior communicating artery,posterior communicating artery,middle cerebral artery,anterior cerebral artery,internal carotid artery,and posterior circulation).Based on the CT images of the head at admission,the distribution of SAH in patients was determined.The modified Fisher grading system was used to classify SAH into 1-4 levels,and the Hijdra score was used to assess the bleeding volume of SAH in patients.The treatment methods of patients(interventional embolization,clipping)were collected.All patients were grouped according to the modified Fisher classification,with grades 1-2 being the minor SAH group and grades 3-4 being the massive SAH group.Baseline data and clinical data and aneurysm characteristics were compared between minor SAH group and massive SAH group.Multiple Logistic regression analysis was conducted using the modified Fisher grades 3-4 as the dependent variable,and factors with P＜0.1 in baseline data that may affect SAH bleeding volume as independent variables,the risk factors associated with the massive SAH in small ruptured intracranial aneurysms were analyzed.New bleeding visible on preoperative CT of the patient,with or without neurological deterioration,is defined as rebleeding.All patients are divided into rebleeding group and non-rebleeding group based on the occurrence of rebleeding.Baseline data and aneurysm characteristics between patients with rebleeding and those without rebleeding were compared.Multivariate Logistic regression analysis was conducted with rebleeding as the dependent variable,and factors with P＜0.1 in baseline data and aneurysm characteristics were used as independent variables,the risk factors associated with rebleeding in small aneurysms were analyzed.Results A total of 363 SAH patients with small ruptured aneurysms were included in this study,including 103 males and 260 females;age range from 25 to 85 years old,with an average age of(55±11)years.According to the modified Fisher classification,there were 198 cases in the massive SAH group and 165 cases in the minor SAH group.Compared with patients in the minor SAH group,patients in the massive SAH group were older(P=0.011),with a higher proportion of males,concomitant hypertension,and smoking history(all P＜0.05).The proportion of admitted Hunt Hess grade Ⅳ to V was higher(26.3％vs.2.4％,P＜0.01),the GCS score was lower([13.1±1.8]points vs.[13.9±0.8]points,P＜0.01),and the Hijdra score was higher([19.7±5.4]points vs.[8.4±2.6]points,P＜0.01).There was no statistically significant difference in the number of aneurysms and the location and morphology of responsible aneurysms between the massive and minor SAH groups(all P＞0.05).According to whether patients experienced rebleeding before surgery,there were 30 cases in the rebleeding group and 333 cases in the non-rebleeding group.Compared with the non-rebleeding group,patients in the rebleeding group had a higher proportion of concomitant hypertension(83.3％vs.49.2％,P＜0.01)and a higher proportion of admitted Hunt Hess grades Ⅳ-V(43.3％vs.12.9％,P＜0.01),lower GCS scores(12[9,14]points vs.14[13,14]points,P＜0.01),and higher Hijdra scores(18[9,26]points vs.14[9,18]points,P=0.024).There was no statistically significant difference in the number of aneurysms,responsible aneurysm morphology,and location between the rebleeding group and the non-rebleeding group(all P＞0.05).There was no statistically significant difference between the coiling and clipping in the two group(both P＞0.05).Multiple Logistic regression analysis was conducted using modified Fisher grading 3-4 and rebleeding as dependent variables respectively.The results showed that age(OR,1.027,95％CI 1.006-1.049,P=0.012)and hypertension(OR,1.858,95％CI 1.196-2.886,P=0.006)were independent risk factors associated with massive SAH in small ruptured aneurysms.Hypertension(OR,3.775,95％CI 1.371-10.391,P=0.010)and lower GCS score(OR,0.677,95％CI 0.561-0.816,P＜0.01)were independent risk factors associated with rebleeding in small ruptured aneurysms.Conclusions Older age and concomitant hypertension are risk factors associated with massive SAH in patients with small ruptured aneurysms.Coexisting hypertension and lower GCS score are risk factors associated with rebleeding in patients with small ruptured aneurysms.

Subarachnoid hemorrhage (SAH) is the third common type of stroke in the world,and its mortality and disability rates have declined over the past few decades due to the advances in neuroimaging technology and endovascular interventional therapy and promotion of healthy physical examination,but long-term neurological deficits and cognitive impairment of the patients have not significantly improved,which may be related to the white matter injury (WMI) after SAH.Little attention has been paid to WMI after SAH in the past,which may be an important reason for the poor prognosis of the patients with SAH.The neuroin-flammation response is an important pathophysiological process after SAH,and the neuroinflammation after SAH can aggravate WMI.This article reviews the relationship between neuroinflammation and WMI after SAH in order to deepen the understanding of its effects on cognitive function after SAH.

Objective    To investigate the clinical characteristics and prognosis of resectable esophageal small cell carcinoma after surgical resection. Methods    A retrospective study of patients with resectable esophageal small cell carcinoma undergoing surgical resection from January 2009 to June 2015 in the Department of Thoracic Surgery, Sichuan Provincial Fourth People's Hospital and Department of Thoracic Surgery, West China Hospital of Sichuan University was performed. Survival analysis was conducted by Kaplan-Meier analysis and log-rank test. Cox regression model was used for identifying independent prognostic factors. Results    A total of 53 patients with resectable esophageal small cell carcinoma were included for analysis. The mean age was 58.4 ± 8.3 years and there were 42 male patients and 11 female patients. Forty-two patients were diagnosed as pure esophageal small cell carcinoma while 11 patients were diagnosed with mixed esophageal small cell carcinoma, who were all mixed with squamous cell carcinoma. Most of the esophageal small   cell carcinomas were located in the middle (58.5%) and lower (32.1%) segments of the esophagus. Thirty patients (56.6%) were found to have lymph node metastasis, and 7 patients (13.2%) were found to have lymphovascular invasion. According to the 2009 TNM staging criteria for esophageal squamous cell carcinoma, there were 12 patients with stage Ⅰ disease, 19 patients with stage Ⅱ disease, and 22 patients with stage Ⅲ disease. Most of the patients underwent left thoracotomy with two-field lymphadenectomy. Postoperatively, only twenty-two patients (41.5%) received adjuvant chemoradiotherapy. The median survival time of these patients was 20.1 months, and the 1- and 3-year survival rate was 75.5% and 33.1%, respectively. For prognosis, age, gender, pathological type, tumor location, and lymphovascular invasion had no significant impact on long-term survival of these patients. However, TNM stage (1 year survival rate: stage Ⅰ: 91.7%; stage Ⅱ: 78.9%; stage Ⅲ: 63.6%; P=0.004) and postoperative adjuvant therapy (1 year survival rate: 81.8% vs. 71.0%; P=0.005) had significant impact on the survival of patients with esophageal small cell carcinoma. In multivariate analysis, TNM stage and postoperative adjuvant therapy were independent prognostic factors for long-term prognosis of patients with esophageal small cell carcinoma. Conclusion    Esophageal small cell carcinoma is very rare, with high malignancy and poor prognosis. For patients with resectable esophageal small cell carcinoma, the TNM staging system of esophageal squamous cell carcinoma can be used to direct the choice of treatment options. For early stage esophageal small cell carcinoma (stage Ⅰ/Ⅱ), surgery plus postoperative adjuvant chemoradiotherapy can be the prior therapeutic choice, while for locally advanced esophageal small cell carcinoma (stage Ⅲ), chemoradiotherapy should be the preferred treatment.

Objective To investigate the effect of long non-coding RNA F19 (lncRNA F19) on secondary brain injury following traumatic brain injury (TBI) in mice. Methods (1) A total of 96 C57BL/6J male wild-type mice were divided into sham group, sham+control lentivirus group, sham+F19 lentivirus group, TBI group, TBI+control lentivirus group and TBI+F19 lentivirus group according to the random number table. Each group consisted of two subgroups of 1 day and 3 days after TBI, with eight mice per subgroup. The expression and silence efficiency of lncRNA F19 were detected. ( 2 ) A total of 96 C57BL/6J male wild-type mice were divided into sham group, TBI+control lentivirus group and TBI + F19 lentivirus group according to the random number table. Each group consisted of two subgroups of 1 day and 3 days after TBI, with 16 mice per subgroup. The effect of lncRNA F19 on neuronal apoptosis after TBI was recorded. The mice TBI model was established using the controlled cortical damage method (CCI). The lncRNA F19 lentivirus or control lentivirus were administrated by intracerebroventricular injection 5 days before injury. The expressions of lncRNA F19 ( 2 -ΔΔct ) were detected by real-time quantitative PCR ( qRT-PCR ) at 1 day and 3 days after injury. The Toll-like receptor 4 (TLR4), B lymphocyte tumor-2 (Bcl-2) and Bcl-2 related protein (Bax) expressions were detected by Western blot. The TUNEL was used to detect apoptosis around the traumatic lesions. Results From the first day after injury, both in the sham operation and TBI groups, the control lentivirus had no effect on the level of lncRAN F19 (P >0. 05). One day after injury, compared with sham +control lentivirus group, the levels of lncRNA F19 in sham + F19 lentivirus group were significantly decreased (0. 07 ± 0. 07:0. 93 ± 0. 17);compared with TBI+control lentivirus group, levels of lncRNA F19 in TBI+F19 lentivirus group were significantly decreased (2. 91 ± 1. 18:0. 52 ± 0. 32) (P<0. 05). There were significantly lower protein levels of TLR4 (0. 51 ± 0. 13:0. 66 ± 0. 15), Bax (0. 45 ± 0. 06:0. 67 ± 0. 16), lower TUNEL-positive neurons ratio [(23. 55 ± 6. 85)％ : (31. 58 ± 7. 52)％], but higher protein levels of Bcl-2 (0. 76 ± 0. 16:0. 47 ± 0. 12) in TBI+F19 lentivirus group compared with the TBI+ control lentivirus group (P <0.05). Three days after injury, compared with sham + control lentivirus group, levels of lncRNA F19 in sham+F19 lentivirus group were significantly decreased (0. 11 ± 0. 09:0. 96 ± 0. 09); compared with TBI+control lentivirus group, levels of lncRNA F19 in TBI+F19 lentivirus group were significantly decreased (0. 54 ± 0. 24:3. 39 ± 0. 90) (P <0. 05). There were significantly lower protein levels of TLR4 (0. 60 ± 0. 20):(0. 85 ± 0. 09)], lower Bax (0. 60 ± 0. 12:0. 88 ±0. 21), lower TUNEL-positive neurons ratio [(29. 10 ± 7. 37)％ :(39. 22 ± 10. 64)％], but higher protein levels of Bcl-2 (0. 66 ± 0. 12:0. 35 ± 0. 16) in TBI+F19 lentivirus group compared with the TBI+control lentivirus group (P<0. 05). Conclusion Inhibition of lncRNA F19 can significantly reduce the TLR4-induced neuronal apoptosis in cortex after TBI in mice and alleviate reduce the secondary brain injury.

OBJECTIVETo explore the concentration-response relationship between ambient concentration of PM2.5 and daily total hospital emergency room visits in Beijing during 2012 and 2013. This study also examined the effects of ambient PM2.5 during heavy polluted days on emergency room visits compared with the light polluted days.

METHODSWe collected the daily meteorological factors monitoring data and concentrations of air pollutants in Beijing during October 1, 2012 to December 31, 2013. We also collected the daily emergency room visits from a tertiary hospital in Beijing in the same time period. Generalized additive model was fitted to estimate the association between the ambient PM2.5 and the hospital emergency room visits, by using the smooth function to adjust long term trend of time, public holidays and day of week. In addition, constrained piecewise linear function was then used to estimate the excess risk for different segment of concentration-response function.

RESULTSThe annual average concentration of PM2.5 was 90.9 µg/m(3) during October 1, 2012 and December 31, 2013. There were total 64 260 cases for total emergency room visits, of which respiratory disease had 9 849 cases and cardiovascular disease had 11 168 cases. PM2.5 was positive related with PM10, NO2 and SO2. The corresponding correlation coefficients were 0.87, 0.78 and 0.62, respectively (P<0.05). And PM2.5 was positively related with relative humidity, with correlation coefficient 0.45 (P<0.05). But PM2.5 was negatively related with mean temperature (r=-0.17, P< 0.05) and wind speed (- 0.32, P<0.05). In the single polluted model, after adjusting the effects of temperature, relative humidity and wind, every 10 µg/m(3) increase of concentration of ambient PM2.5, the corresponding excess risk of daily emergency room visits was 0.25% (95% CI: 0.07-0.43). In the two-pollutant model PM2.5+SO2 and PM2.5+NO2, every 10 µg/m(3) increase of concentration of ambient PM2.5, the corresponding excess risk of daily emergency room visits were 1.07% (95%CI:0.83-1.30) and 0.56% (95%CI: 0.32-0.80) respectively, which were higher than the effect in single pollutant model. Average concentration of ambient particulate matters (PM2.5) was 204.16 µg/m(3) during heavy pollution, higher than control period (85.24 µg/m(3)). When PM2.5 as the primary air pollutants during heavy polluted days, we observed a significant increase in emergency room visits, and the odd ratios was 1.16 (95% CI:1.09-1.22).

CONCLUSIONThere were positive correlation between high concentration of ambient particulate matters (PM2.5) and increasing daily emergency room visits. Especially during the heavy polluted days, the effects of elevated concentration of PM2.5 on hospital emergency room visits were much larger.

Air Pollutants ; analysis ; Beijing ; Cardiovascular Diseases ; diagnosis ; Emergency Service, Hospital ; statistics & numerical data ; Humans ; Meteorological Concepts ; Particulate Matter ; analysis ; Respiratory Tract Diseases ; diagnosis ; Temperature ; Tertiary Care Centers

Objective The purpose of this study is to explore the clinical value of CT angiography( CTA) in the diagnosis of multiple intracranial aneurysms.Methods The data of CTA and DSA from 74 patients with multiple intracra-nial aneurysms from July 2011 to March 2015 were reviewed retrospectively.Results One hundred seventy-seven aneu-rysms were detected by DSA, and 175 aneurysms were detected by CTA.Among the aneurysms identified by CTA, 4 aneu-rysms were false positive and the correct detection rate of CTA was 96.6%.One hundred sixty-five aneurysms identified by CTA were confirmed by DSA and the correct diagnostic rate of CTA was 96.5%.CTA failed to detect 6 aneurysms and mis-diagnosed 10 aneurysms.Conclusions The correct detection rate and diagnostic rate of CT angiography ( CTA) in multiple intracranial aneurysms is relatively high.But previous surgery, spasm of the vessels, the size and number of aneurysms, radiologists'experience can influence the accuracy of ( CTA) in the diagnosis of multiple intracranial aneurysms, indicating that we should combine CTA with DSA to avoid the misdiagnosis and missed diagnosis.

Objective To assess the clinical curative effects of local injection of recombinant oncolytic adenovirus type 5 combined with radiotherapy in the treatment of advanced nasopharyngeal carcinoma.Methods A total of 42 patients who had been definitely diagnosed as advanced nasopharyngeal carcinoma were recruited between 2010 and 2012 from general hospital of PLA.All inpatients were divided into two groups:group A with 22 patients,who were willing to treat the cancer by local injection of recombinant oncolytic adenovirus type 5 combined with radiochemotherapy; group B with 20 patients,who were willing to treat the cancer by radiochemotherapy.The dose and method of radiochemotherapy were same in both groups.The data of follow-up investigation were statistically analyzed.Results There were no significant differences in tumor size (P =0.673) between the two groups before treatment.The tumor shrinkage rate of group A was greater than that of group B after one month treatment,and the difference was statistically significant (P =0.034).Besides,there were no significant differences in side effects (P ＞ 0.05) between the two groups.Conclusion The recombinant oncolytic adenovirus type 5 injection treatment combined with radiochemotherapy obviously enhanced the curative effect and reduced the side effects when it was applied through local injection method in treating advanced nasopharyngeal carcinoma,which opens up a new way of effective treatment of advanced nasopharyngeal carcinoma.

Objective To investigate the effect of gene therapy which was mediated by electroporation on the expression of basic fibroblast growth factor (bFGF) duning mandible distraction.Methods Bilateral mandibular osteotomies were performed in New-Zealand rabbit.After a latency of 3 days,the mandibles were elongated using distractors with a rate of 0.8 mm/d for 7 days.The rabbits were randomly divided into 5 groups:2 μtg recombinant plasmids pIRES-hVEGF165-hBMP2,pIRES-hBMP2,pIRES-hVEGF165,pIRES and normal saline (NS) were injected into the distraction area of groups A,B,C,D and E,after completion of distraction,respectively.The lengthened mandibles were harvested and processed for immunohistochemical detection of bFGF,and the mean optic densities and integral optical density of bFGF positive cells were measured by computerized image analyzer.Results bFGF mainly located in fibroblasts,giant monocytes,polynuclear phagocytes,osetocytes,and osetoblasts in the connective tissue around bone tissue.The strongest expression was observed at the 7th day,and weakened at 14th day of consolidation stage,there were no significant difference among groups A,B and C,at the 7th day of consolidation.However,there were significant differences between gene therapy groups (A,B and C) and control groups (D and E) (P＜0.01).Conclusions Gene therapy can enhance and prolong the expression of bFGF in distraction gap,which promotes the cell differentiation and proliferation,extracellular matrix synthesis and new bone formation during distraction osteogenesis.This is probably one of the molecular mechanisms of the gene therapy promoting new bone formation in distraction gap.