BACKGROUND:Sepsis is one of the main causes of mortality in intensive care units(ICUs).Early prediction is critical for reducing injury.As approximately 36%of sepsis occur within 24 h after emergency department(ED)adm...BACKGROUND:Sepsis is one of the main causes of mortality in intensive care units(ICUs).Early prediction is critical for reducing injury.As approximately 36%of sepsis occur within 24 h after emergency department(ED)admission in Medical Information Mart for Intensive Care(MIMIC-IV),a prediction system for the ED triage stage would be helpful.Previous methods such as the quick Sequential Organ Failure Assessment(qSOFA)are more suitable for screening than for prediction in the ED,and we aimed to fi nd a light-weight,convenient prediction method through machine learning.METHODS:We accessed the MIMIC-IV for sepsis patient data in the EDs.Our dataset comprised demographic information,vital signs,and synthetic features.Extreme Gradient Boosting(XGBoost)was used to predict the risk of developing sepsis within 24 h after ED admission.Additionally,SHapley Additive exPlanations(SHAP)was employed to provide a comprehensive interpretation of the model's results.Ten percent of the patients were randomly selected as the testing set,while the remaining patients were used for training with 10-fold cross-validation.RESULTS:For 10-fold cross-validation on 14,957 samples,we reached an accuracy of 84.1%±0.3%and an area under the receiver operating characteristic(ROC)curve of 0.92±0.02.The model achieved similar performance on the testing set of 1,662 patients.SHAP values showed that the fi ve most important features were acuity,arrival transportation,age,shock index,and respiratory rate.CONCLUSION:Machine learning models such as XGBoost may be used for sepsis prediction using only a small amount of data conveniently collected in the ED triage stage.This may help reduce workload in the ED and warn medical workers against the risk of sepsis in advance.展开更多
This is a prospective and descriptive study carried out at the gynecology and obstetrics department of the reference health center of Fana from 01 May 2019 to 30 November or 7 months. The main objective was to study t...This is a prospective and descriptive study carried out at the gynecology and obstetrics department of the reference health center of Fana from 01 May 2019 to 30 November or 7 months. The main objective was to study the role of blood transfusion in the management of obstetric emergencies. During the study period we recorded 434 cases of obstetric emergencies of which 116 cases required an emergency blood transfusion or 26.73%. The most frequently found indications for blood transfusion are hemorrhages of the immediate postpartum 46.6% followed by severe malaria on pregnancy 27.6%. Blood remains the most prescribed and available Labile blood product in the department. Maternal prognosis was improved in 92.2%.展开更多
Objective: The aim was to evaluate the frequency of prolonged fevers and to determine their etiologies. Methods: We carried out a cross-sectional study extending from the period of 2009 to 2013 in the Internal Medicin...Objective: The aim was to evaluate the frequency of prolonged fevers and to determine their etiologies. Methods: We carried out a cross-sectional study extending from the period of 2009 to 2013 in the Internal Medicine department of the “G” Point University Hospital in Bamako. Included were all records of hospitalized patients with a central temperature greater than 37°C in the morning and 37°C in the evening, resting for 15 minutes, fasting for more than 2 hours, and absence of antipyretic treatment. We include all the patients of the study period with fever greater than 37.5°C in the morning and 37.8°C in the evening, resting for 15 minutes, fasting for more than 2 hours, and absence of antipyretic treatment, which have more than 21 days and measured on several occasions. The data were collected on a survey sheet. Data entry and analysis was done on SPSS software. Results: We recorded 243 fever cases out of 2155 hospitalizations, a prevalence rate of 11.2%. There were 128 men and 115 women with an average age of 43 years (range, 15 to 84 years), a modal class of 37 to 47 years, and a sex ratio of 1.11. The infectious etiologies accounted for 81% followed by neoplastic causes 09.6% and inflammatory 01.2% of cases. HIV infection was found in 26.4% of patients, malaria 13.5% and urinary tract infections 10.2%). Gram negative bacilli 88% consisted mainly of Escherichia coli (56%) and Klebsiella pneumoniae (20%).展开更多
目的:评价非药物康复干预措施对乳腺癌患者化疗相关认知障碍的治疗效果。方法:检索Pubmed,Cochrane library,Embase,Web of science,中国知网,万方,维普,CBM数据库符合研究目的的随机对照试验,检索时限截止到2022年2月,应用Stata 16.0...目的:评价非药物康复干预措施对乳腺癌患者化疗相关认知障碍的治疗效果。方法:检索Pubmed,Cochrane library,Embase,Web of science,中国知网,万方,维普,CBM数据库符合研究目的的随机对照试验,检索时限截止到2022年2月,应用Stata 16.0软件进行网状Meta分析。结果:纳入研究22项,共10种非药物干预方法,并且纳入的研究均未报告显著不良事件,表明这10种非药物干预措施对于治疗化疗相关认知障碍是安全的。网状结果显示,相比于常规护理,最有效的干预措施排序为正念疗法、认知训练。结论:非药物康复干预对乳腺癌化疗相关认知障碍的治疗安全有效,其中正念疗法和认知训练的干预效果可能最佳,这一结果为临床决策提供了循证数据支持,未来需进行更多高质量研究探索最佳性价比的干预措施。展开更多
基金supported by the National Key Research and Development Program of China(2021YFC2500803)the CAMS Innovation Fund for Medical Sciences(2021-I2M-1-056).
文摘BACKGROUND:Sepsis is one of the main causes of mortality in intensive care units(ICUs).Early prediction is critical for reducing injury.As approximately 36%of sepsis occur within 24 h after emergency department(ED)admission in Medical Information Mart for Intensive Care(MIMIC-IV),a prediction system for the ED triage stage would be helpful.Previous methods such as the quick Sequential Organ Failure Assessment(qSOFA)are more suitable for screening than for prediction in the ED,and we aimed to fi nd a light-weight,convenient prediction method through machine learning.METHODS:We accessed the MIMIC-IV for sepsis patient data in the EDs.Our dataset comprised demographic information,vital signs,and synthetic features.Extreme Gradient Boosting(XGBoost)was used to predict the risk of developing sepsis within 24 h after ED admission.Additionally,SHapley Additive exPlanations(SHAP)was employed to provide a comprehensive interpretation of the model's results.Ten percent of the patients were randomly selected as the testing set,while the remaining patients were used for training with 10-fold cross-validation.RESULTS:For 10-fold cross-validation on 14,957 samples,we reached an accuracy of 84.1%±0.3%and an area under the receiver operating characteristic(ROC)curve of 0.92±0.02.The model achieved similar performance on the testing set of 1,662 patients.SHAP values showed that the fi ve most important features were acuity,arrival transportation,age,shock index,and respiratory rate.CONCLUSION:Machine learning models such as XGBoost may be used for sepsis prediction using only a small amount of data conveniently collected in the ED triage stage.This may help reduce workload in the ED and warn medical workers against the risk of sepsis in advance.
文摘This is a prospective and descriptive study carried out at the gynecology and obstetrics department of the reference health center of Fana from 01 May 2019 to 30 November or 7 months. The main objective was to study the role of blood transfusion in the management of obstetric emergencies. During the study period we recorded 434 cases of obstetric emergencies of which 116 cases required an emergency blood transfusion or 26.73%. The most frequently found indications for blood transfusion are hemorrhages of the immediate postpartum 46.6% followed by severe malaria on pregnancy 27.6%. Blood remains the most prescribed and available Labile blood product in the department. Maternal prognosis was improved in 92.2%.
文摘Objective: The aim was to evaluate the frequency of prolonged fevers and to determine their etiologies. Methods: We carried out a cross-sectional study extending from the period of 2009 to 2013 in the Internal Medicine department of the “G” Point University Hospital in Bamako. Included were all records of hospitalized patients with a central temperature greater than 37°C in the morning and 37°C in the evening, resting for 15 minutes, fasting for more than 2 hours, and absence of antipyretic treatment. We include all the patients of the study period with fever greater than 37.5°C in the morning and 37.8°C in the evening, resting for 15 minutes, fasting for more than 2 hours, and absence of antipyretic treatment, which have more than 21 days and measured on several occasions. The data were collected on a survey sheet. Data entry and analysis was done on SPSS software. Results: We recorded 243 fever cases out of 2155 hospitalizations, a prevalence rate of 11.2%. There were 128 men and 115 women with an average age of 43 years (range, 15 to 84 years), a modal class of 37 to 47 years, and a sex ratio of 1.11. The infectious etiologies accounted for 81% followed by neoplastic causes 09.6% and inflammatory 01.2% of cases. HIV infection was found in 26.4% of patients, malaria 13.5% and urinary tract infections 10.2%). Gram negative bacilli 88% consisted mainly of Escherichia coli (56%) and Klebsiella pneumoniae (20%).
文摘目的:评价非药物康复干预措施对乳腺癌患者化疗相关认知障碍的治疗效果。方法:检索Pubmed,Cochrane library,Embase,Web of science,中国知网,万方,维普,CBM数据库符合研究目的的随机对照试验,检索时限截止到2022年2月,应用Stata 16.0软件进行网状Meta分析。结果:纳入研究22项,共10种非药物干预方法,并且纳入的研究均未报告显著不良事件,表明这10种非药物干预措施对于治疗化疗相关认知障碍是安全的。网状结果显示,相比于常规护理,最有效的干预措施排序为正念疗法、认知训练。结论:非药物康复干预对乳腺癌化疗相关认知障碍的治疗安全有效,其中正念疗法和认知训练的干预效果可能最佳,这一结果为临床决策提供了循证数据支持,未来需进行更多高质量研究探索最佳性价比的干预措施。
