BACKGROUND Hypernatremia represents a significant electrolyte imbalance associated with numerous adverse outcomes,particularly in cases of intensive care unit(ICU)-acquired hypernatremia(IAH).Nevertheless,its relevanc...BACKGROUND Hypernatremia represents a significant electrolyte imbalance associated with numerous adverse outcomes,particularly in cases of intensive care unit(ICU)-acquired hypernatremia(IAH).Nevertheless,its relevance in patients with septic shock remains uncertain.AIM To identify independent risk factors and their predictive efficacy for IAH to improve outcomes in patients with septic shock.METHODS In the present retrospective single-center study,a cohort of 157 septic shock patients with concurrent hypernatremia in the ICU at The First Affiliated Hospital of Soochow University,between August 1,2018,and May 31,2023,were analyzed.Patients were categorized based on the timing of hypernatremia occurrence into the IAH group(n=62),the non-IAH group(n=41),and the normonatremia group(n=54).RESULTS In the present study,there was a significant association between the high serum sodium concentrations,excessive persistent inflammation,immunosuppression and catabolism syndrome and chronic critical illness,while rapid recovery had an apparent association with normonatremia.Moreover,multivariable analyses revealed the following independent risk factors for IAH:Total urinary output over the preceding three days[odds ratio(OR)=1.09;95%CI:1.02–1.17;P=0.014],enteral nutrition(EN)sodium content of 500 mg(OR=2.93;95%CI:1.13–7.60;P=0.027),and EN sodium content of 670 mg(OR=6.19;95%CI:1.75–21.98;P=0.005)were positively correlated with the development of IAH.Notably,the area under the curve for total urinary output over the preceding three days was 0.800(95%CI:0.678–0.922,P=0.001).Furthermore,maximum serum sodium levels,the duration of hypernatremia,and varying sodium correction rates were significantly associated with 28-day in-hospital mortality in septic shock patients(P<0.05).CONCLUSION The present findings illustrate that elevated serum sodium level was significantly associated with a poor prognosis in septic shock patients in the ICU.It is highly recommended that hypernatremia be considered a potentially important prognostic indicator for the outcome of septic shock.展开更多
Objective: To explore the methodology of the evidence-based expert consensus formulation process of traditional Chinese medicine(TCM) nursing taking stroke as an example.Methods: First, preliminary and comprehensive p...Objective: To explore the methodology of the evidence-based expert consensus formulation process of traditional Chinese medicine(TCM) nursing taking stroke as an example.Methods: First, preliminary and comprehensive presentation of all stroke-related symptoms and corresponding TCM nursing techniques involved were revealed through bibliometric analysis. Then, selection of stroke symptoms and TCM nursing techniques for inclusion in the consensus was performed using an expert consultation method. Next, we determined the search strategy for a precise evidence search;conducted an evaluation of evidence quality and the grade of the evidence;and completed evidence extraction, evidence analysis, and evidence synthesis based on the included symptoms and TCM nursing techniques. The Delphi method was then applied to determine the strength of each recommendation and the choice of nursing care points by referring to the Grading of Recommendations, Assessment, Development, and Evaluations grid. Finally, we conducted an external expert validation of the Delphi results to form an expert consensus guideline.Results: Through the bibliometric analysis, 22 stroke symptoms and 18 TCM nursing techniques were identified in the literature. Then, after expert consultation, 22 symptoms and 111 pairs of symptoms combined with TCM nursing techniques were selected for the evidence search. Evidence integration yielded 10 stroke symptoms corresponding to 29 bodies of evidence;these 10 symptoms were retained through the Delphi consultation, and recommendation strength results for 26 recommendations were obtained. A total of 9 symptoms were further retained for expert external validation to form 24 recommendations, with a recommendation process score range of 7.64-9.99 points and a more scientific and standardized recommendation-formation process.Conclusion: Owing to the current limited conditions of evidence-based resources for TCM nursing, the present consensus-building process represents only a preliminary exploration of an evidence-based expert consensus for TCM nursing to provide a reference for a more scientific and standardized methodology.展开更多
In order to solve the problems of the traditional flame detection method, such as low detection accuracy, slow detection speed and lack of real-time detection ability. An improved high speed flame detection method bas...In order to solve the problems of the traditional flame detection method, such as low detection accuracy, slow detection speed and lack of real-time detection ability. An improved high speed flame detection method based on YOLOv7 is proposed. Based on YOLOv7 and combined with ConvNeXtBlock, CN-B network module was constructed, and YOLOv7-CN-B flame detection method was proposed. Compared with the YOLOv7 method, this flame detection method is lighter and has stronger flame feature extraction ability. 2059 open flame data sets labeled with single flame categories were used to avoid the enhancement effect brought by high-quality data sets, so that the comparative experimental effect completely depended on the performance of the flame detection method itself. The results show that the accuracy of YOLOv7-CN-B method is improved by 5% and mAP is improved by 2.1% compared with YOLOv7 method. The detection speed reached 149.25 FPS, and the single detection speed reached 11.9 ms. The experimental results show that the YOLOv7-CN-B method has better performance than the mainstream algorithm.展开更多
To address the prominent problems faced by customer churn in telecom enterprise management, a telecom customer churn prediction model integrating GA-XGBoost and SHAP is proposed. By using the ADASYN algorithm for data...To address the prominent problems faced by customer churn in telecom enterprise management, a telecom customer churn prediction model integrating GA-XGBoost and SHAP is proposed. By using the ADASYN algorithm for data processing on the unbalanced sample set;based on the GA-XGBoost model, the XGBoost algorithm is used to construct the telecom customer churn prediction model, and the hyperparameters of the model are optimized by using the genetic algorithm. The experimental results show that compared with traditional machine learning methods such as GBDT, decision tree, KNN and single XGBoost model, the improved XGBoost model has better performance in recall, F1 value and AUC value;the GA-XGBoost model is integrated with SHAP framework to analyze and explain the important features affecting telecom customer churn, which is more in line with the telecom industry to predict customer the actual situation of churn.展开更多
Background: Our study aimed to investigate the clinical value of platelet parameters and the number of Monocytes (MONO) in the peripheral blood of patients with Ocular Myasthenia Gravis (OMG). Methods: Fifty patients ...Background: Our study aimed to investigate the clinical value of platelet parameters and the number of Monocytes (MONO) in the peripheral blood of patients with Ocular Myasthenia Gravis (OMG). Methods: Fifty patients discharged from the Department of Neurology of the First People’s Hospital of Jingzhou City with the diagnosis of OMG from January 1, 2020, to December 31, 2023, were selected as the experimental group, and healthy medical examiners were selected as the control group during the same period. The differences in peripheral blood mononuclear cell count and platelet-related parameters between the two groups were compared. ROC curves were drawn to analyze the clinical value of the studied indexes in patients with OMG. Results: Patients with OMG had significantly higher monocyte counts and narrower platelet distributions compared with normal adults;further logistic regression analysis revealed that higher monocyte counts and narrower Platelet Distribution Width (PDW) may be independent influences on the occurrence of OMG (p Conclusion: Peripheral blood mononuclear cell count and PDW have some diagnostic value in OMG.展开更多
Supply chain management usually faces problems such as high empty rate of transportation, unreasonable inventory management, and large material consumption caused by inaccurate market demand forecasts. To solve these ...Supply chain management usually faces problems such as high empty rate of transportation, unreasonable inventory management, and large material consumption caused by inaccurate market demand forecasts. To solve these problems, using artificial intelligence and big data technology to achieve market demand forecasting and intelligent decision-making is becoming a strategic technology trend of supply chain management in the future. Firstly, this paper makes a visual analysis of the historical data of the Stock Keeping Unit (SKU);Then, the characteristic factors affecting the future demand are constructed from the storage level, product level, historical usage of SKU, etc;Finally, a supply chain demand forecasting algorithm based on SSA-XGBoost model has proposed around three aspects of feature engineering, parameter optimization and model integration, and is compared with other machine learning models. The experiment shows that the forecasting result of SSA-XGBoost forecasting model is highly consistent with the actual value, so it is of practical significance to adopt this forecasting model to solve the supply chain demand forecasting problem.展开更多
Objective: To report the incidence and mortality rates of oral and oropharyngeal cancer in Chinese population.Methods: Data were taken from a population-based cancer registry collected by the National Central Cancer R...Objective: To report the incidence and mortality rates of oral and oropharyngeal cancer in Chinese population.Methods: Data were taken from a population-based cancer registry collected by the National Central Cancer Registry of China(NCCRC) in 2015. The data collected from 501 local cancer registries in China were assessed using NCCRC screening methods and criteria. Incidence and mortality rates of oral and oropharyngeal cancer were stratified by age group, gender, and area. Age-standardized incidence and mortality rates were adjusted using the Chinese standard population in 2000 and Segi’s world population.Results: In 2015, it was estimated that there were 51,765 oral and oropharyngeal cancer incident cases and 23,830 deaths in China. The crude incidence rate of oral and oropharyngeal cancer was 3.77/100,000, and the agestandardized incidence rate by Chinese standard population and by Segi’s world standard population were 2.55/100,000 and 2.49/100,000, respectively. The crude mortality rate and the age-standardized mortality rates by Chinese standard population and by Segi’s world standard population were 1.73/100,000, 1.09/100,000 and1.08/100,000, respectively. Both incidence and mortality rates of oral and oropharyngeal cancer were higher in males and in urban areas. Residents in eastern areas had the highest incidence and mortality rates, followed by those from middle areas and western areas. The rates of oral and oropharyngeal cancer increased greatly with age,especially after the age of 40 years.Conclusions: This study reports the latest incidence and mortality rates of oral and oropharyngeal cancer in China. Prevention intervention including early detection, treatment, and regular follow-ups is encouraged to be set up to reduce incidence and mortality rates of oral and oropharyngeal cancer in the future.展开更多
基金Supported by The National Natural Science Foundation of China,No.82072130Key Medical Research Projects in Jiangsu Province,No.ZD2022021Suzhou Clinical Medical Center for Anesthesiology,No.Szlcyxzxj202102。
文摘BACKGROUND Hypernatremia represents a significant electrolyte imbalance associated with numerous adverse outcomes,particularly in cases of intensive care unit(ICU)-acquired hypernatremia(IAH).Nevertheless,its relevance in patients with septic shock remains uncertain.AIM To identify independent risk factors and their predictive efficacy for IAH to improve outcomes in patients with septic shock.METHODS In the present retrospective single-center study,a cohort of 157 septic shock patients with concurrent hypernatremia in the ICU at The First Affiliated Hospital of Soochow University,between August 1,2018,and May 31,2023,were analyzed.Patients were categorized based on the timing of hypernatremia occurrence into the IAH group(n=62),the non-IAH group(n=41),and the normonatremia group(n=54).RESULTS In the present study,there was a significant association between the high serum sodium concentrations,excessive persistent inflammation,immunosuppression and catabolism syndrome and chronic critical illness,while rapid recovery had an apparent association with normonatremia.Moreover,multivariable analyses revealed the following independent risk factors for IAH:Total urinary output over the preceding three days[odds ratio(OR)=1.09;95%CI:1.02–1.17;P=0.014],enteral nutrition(EN)sodium content of 500 mg(OR=2.93;95%CI:1.13–7.60;P=0.027),and EN sodium content of 670 mg(OR=6.19;95%CI:1.75–21.98;P=0.005)were positively correlated with the development of IAH.Notably,the area under the curve for total urinary output over the preceding three days was 0.800(95%CI:0.678–0.922,P=0.001).Furthermore,maximum serum sodium levels,the duration of hypernatremia,and varying sodium correction rates were significantly associated with 28-day in-hospital mortality in septic shock patients(P<0.05).CONCLUSION The present findings illustrate that elevated serum sodium level was significantly associated with a poor prognosis in septic shock patients in the ICU.It is highly recommended that hypernatremia be considered a potentially important prognostic indicator for the outcome of septic shock.
基金supported by the Best Practice Spotlight Organization (Ottawa, Canada)Key Research Project of the Beijing University of Chinese Medicine (2020-JYB-ZDGG-075Beijing, China)
文摘Objective: To explore the methodology of the evidence-based expert consensus formulation process of traditional Chinese medicine(TCM) nursing taking stroke as an example.Methods: First, preliminary and comprehensive presentation of all stroke-related symptoms and corresponding TCM nursing techniques involved were revealed through bibliometric analysis. Then, selection of stroke symptoms and TCM nursing techniques for inclusion in the consensus was performed using an expert consultation method. Next, we determined the search strategy for a precise evidence search;conducted an evaluation of evidence quality and the grade of the evidence;and completed evidence extraction, evidence analysis, and evidence synthesis based on the included symptoms and TCM nursing techniques. The Delphi method was then applied to determine the strength of each recommendation and the choice of nursing care points by referring to the Grading of Recommendations, Assessment, Development, and Evaluations grid. Finally, we conducted an external expert validation of the Delphi results to form an expert consensus guideline.Results: Through the bibliometric analysis, 22 stroke symptoms and 18 TCM nursing techniques were identified in the literature. Then, after expert consultation, 22 symptoms and 111 pairs of symptoms combined with TCM nursing techniques were selected for the evidence search. Evidence integration yielded 10 stroke symptoms corresponding to 29 bodies of evidence;these 10 symptoms were retained through the Delphi consultation, and recommendation strength results for 26 recommendations were obtained. A total of 9 symptoms were further retained for expert external validation to form 24 recommendations, with a recommendation process score range of 7.64-9.99 points and a more scientific and standardized recommendation-formation process.Conclusion: Owing to the current limited conditions of evidence-based resources for TCM nursing, the present consensus-building process represents only a preliminary exploration of an evidence-based expert consensus for TCM nursing to provide a reference for a more scientific and standardized methodology.
文摘In order to solve the problems of the traditional flame detection method, such as low detection accuracy, slow detection speed and lack of real-time detection ability. An improved high speed flame detection method based on YOLOv7 is proposed. Based on YOLOv7 and combined with ConvNeXtBlock, CN-B network module was constructed, and YOLOv7-CN-B flame detection method was proposed. Compared with the YOLOv7 method, this flame detection method is lighter and has stronger flame feature extraction ability. 2059 open flame data sets labeled with single flame categories were used to avoid the enhancement effect brought by high-quality data sets, so that the comparative experimental effect completely depended on the performance of the flame detection method itself. The results show that the accuracy of YOLOv7-CN-B method is improved by 5% and mAP is improved by 2.1% compared with YOLOv7 method. The detection speed reached 149.25 FPS, and the single detection speed reached 11.9 ms. The experimental results show that the YOLOv7-CN-B method has better performance than the mainstream algorithm.
文摘To address the prominent problems faced by customer churn in telecom enterprise management, a telecom customer churn prediction model integrating GA-XGBoost and SHAP is proposed. By using the ADASYN algorithm for data processing on the unbalanced sample set;based on the GA-XGBoost model, the XGBoost algorithm is used to construct the telecom customer churn prediction model, and the hyperparameters of the model are optimized by using the genetic algorithm. The experimental results show that compared with traditional machine learning methods such as GBDT, decision tree, KNN and single XGBoost model, the improved XGBoost model has better performance in recall, F1 value and AUC value;the GA-XGBoost model is integrated with SHAP framework to analyze and explain the important features affecting telecom customer churn, which is more in line with the telecom industry to predict customer the actual situation of churn.
文摘Background: Our study aimed to investigate the clinical value of platelet parameters and the number of Monocytes (MONO) in the peripheral blood of patients with Ocular Myasthenia Gravis (OMG). Methods: Fifty patients discharged from the Department of Neurology of the First People’s Hospital of Jingzhou City with the diagnosis of OMG from January 1, 2020, to December 31, 2023, were selected as the experimental group, and healthy medical examiners were selected as the control group during the same period. The differences in peripheral blood mononuclear cell count and platelet-related parameters between the two groups were compared. ROC curves were drawn to analyze the clinical value of the studied indexes in patients with OMG. Results: Patients with OMG had significantly higher monocyte counts and narrower platelet distributions compared with normal adults;further logistic regression analysis revealed that higher monocyte counts and narrower Platelet Distribution Width (PDW) may be independent influences on the occurrence of OMG (p Conclusion: Peripheral blood mononuclear cell count and PDW have some diagnostic value in OMG.
文摘Supply chain management usually faces problems such as high empty rate of transportation, unreasonable inventory management, and large material consumption caused by inaccurate market demand forecasts. To solve these problems, using artificial intelligence and big data technology to achieve market demand forecasting and intelligent decision-making is becoming a strategic technology trend of supply chain management in the future. Firstly, this paper makes a visual analysis of the historical data of the Stock Keeping Unit (SKU);Then, the characteristic factors affecting the future demand are constructed from the storage level, product level, historical usage of SKU, etc;Finally, a supply chain demand forecasting algorithm based on SSA-XGBoost model has proposed around three aspects of feature engineering, parameter optimization and model integration, and is compared with other machine learning models. The experiment shows that the forecasting result of SSA-XGBoost forecasting model is highly consistent with the actual value, so it is of practical significance to adopt this forecasting model to solve the supply chain demand forecasting problem.
基金supported by the Sanming Project of Medicine in Shenzhen (No. SZSM201911015)the Natural Science Foundation of Guangdong Province (No. 2020A151501478)+1 种基金Major State Basic Innovation Program of the Chinese Academy of Medical Sciences (No. 2018-I2M-3-003)supported by a National Health and Medical Research Council Early Career Fellowship (No. GNT1139826).
文摘Objective: To report the incidence and mortality rates of oral and oropharyngeal cancer in Chinese population.Methods: Data were taken from a population-based cancer registry collected by the National Central Cancer Registry of China(NCCRC) in 2015. The data collected from 501 local cancer registries in China were assessed using NCCRC screening methods and criteria. Incidence and mortality rates of oral and oropharyngeal cancer were stratified by age group, gender, and area. Age-standardized incidence and mortality rates were adjusted using the Chinese standard population in 2000 and Segi’s world population.Results: In 2015, it was estimated that there were 51,765 oral and oropharyngeal cancer incident cases and 23,830 deaths in China. The crude incidence rate of oral and oropharyngeal cancer was 3.77/100,000, and the agestandardized incidence rate by Chinese standard population and by Segi’s world standard population were 2.55/100,000 and 2.49/100,000, respectively. The crude mortality rate and the age-standardized mortality rates by Chinese standard population and by Segi’s world standard population were 1.73/100,000, 1.09/100,000 and1.08/100,000, respectively. Both incidence and mortality rates of oral and oropharyngeal cancer were higher in males and in urban areas. Residents in eastern areas had the highest incidence and mortality rates, followed by those from middle areas and western areas. The rates of oral and oropharyngeal cancer increased greatly with age,especially after the age of 40 years.Conclusions: This study reports the latest incidence and mortality rates of oral and oropharyngeal cancer in China. Prevention intervention including early detection, treatment, and regular follow-ups is encouraged to be set up to reduce incidence and mortality rates of oral and oropharyngeal cancer in the future.
