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
BACKGROUND:It is not clear whether Emergency Severity Index(ESI)is valid to triage heart failure(HF)patients and if HF patients benefi t more from a customized triage scale or not.The aim of study is to compare the ef...BACKGROUND:It is not clear whether Emergency Severity Index(ESI)is valid to triage heart failure(HF)patients and if HF patients benefi t more from a customized triage scale or not.The aim of study is to compare the effect of Heart Failure Triage Scale(HFTS)and ESI on mistriage among patients with HF who present to the emergency department(ED).METHODS:A randomized clinical trial was conducted from April to June 2017.HF patients with dyspnea were randomly assigned to HFTS or ESI groups.Triage level,used resources and time to electrocardiogram(ECG)were compared between both groups among HF patients who were admitted to coronary care unit(CCU),cardiac unit(CU)and discharged patients from the ED.Content validity was examined using Kappa designating agreement on relevance(K*).Reliability of both scale was evaluated using inter-observer agreement(Kappa).RESULTS:Seventy-three and 74 HF patients were assigned to HFTS and ESI groups respectively.Time to ECG in HFTS group was signifi cantly shorter than that of ESI group(2.05 vs.16.82 minutes).Triage level between HFTS and ESI groups was signifi cantly different among patients admitted to CCU(1.0 vs.2.8),cardiac unit(2.26 vs.3.06)and discharged patients from the ED(3.53 vs.2.86).Used resources in HFTS group was significantly different among triage levels(H=25.89;df=3;P<0.001).CONCLUSION:HFTS is associated with less mistriage than ESI for triaging HF patients.It is recommended to make use of HFTS to triage HF patients in the ED.展开更多
BACKGROUND: Although the Australasian Triage Scale(ATS) has been developed two decades ago, its reliability has not been def ined; therefore, we present a meta-analyis of the reliability of the ATS in order to reveal ...BACKGROUND: Although the Australasian Triage Scale(ATS) has been developed two decades ago, its reliability has not been def ined; therefore, we present a meta-analyis of the reliability of the ATS in order to reveal to what extent the ATS is reliable.DATA SOURCES: Electronic databases were searched to March 2014. The included studies were those that reported samples size, reliability coefficients, and adequate description of the ATS reliability assessment. The guidelines for reporting reliability and agreement studies(GRRAS) were used. Two reviewers independently examined abstracts and extracted data. The effect size was obtained by the z-transformation of reliability coefficients. Data were pooled with random-effects models, and meta-regression was done based on the method of moment's estimator.RESULTS: Six studies were included in this study at last. Pooled coefficient for the ATS was substantial 0.428(95%CI 0.340–0.509). The rate of mis-triage was less than fifty percent. The agreement upon the adult version is higher than the pediatric version.CONCLUSION: The ATS has shown an acceptable level of overall reliability in the emergency department, but it needs more development to reach an almost perfect agreement.展开更多
BACKGROUND: Triage system in children seems to be more challenging compared to adults because of their different response to physiological and psychosocial stressors. This study aimed to determine the best triage syst...BACKGROUND: Triage system in children seems to be more challenging compared to adults because of their different response to physiological and psychosocial stressors. This study aimed to determine the best triage system in the pediatric emergency department.METHODS: This was a prospective observational study. This study was divided into two phases. The fi rst phase determined the inter-rater reliability of fi ve triage systems: Manchester Triage System(MTS), Emergency Severity Index(ESI) version 4, Pediatric Canadian Triage and Acuity Scale(CTAS), Australasian Triage Scale(ATS), and Ramathibodi Triage System(RTS) by triage nurses and pediatric residents. In the second phase, to analyze the validity of each triage system, patients were categorized as two groups, i.e., high acuity patients(triage level 1, 2) and low acuity patients(triage level 3, 4, and 5). Then we compared the triage acuity with actual admission.RESULTS: In phase I, RTS illustrated almost perfect inter-rater reliability with kappa of 1.0(P<0.01). ESI and CTAS illustrated good inter-rater reliability with kappa of 0.8–0.9(P<0.01). Meanwhile, ATS and MTS illustrated moderate to good inter-rater reliability with kappa of 0.5–0.7(P<0.01). In phase II, we included 1 041 participants with average age of 4.7±4.2 years, of which 55% were male and 45% were female. In addition 32% of the participants had underlying diseases, and 123(11.8%) patients were admitted. We found that ESI illustrated the most appropriate predicting ability for admission with sensitivity of 52%, specifi city of 81%, and AUC 0.78(95%CI 0.74–0.81).CONCLUSION: RTS illustrated almost perfect inter-rater reliability. Meanwhile, ESI and CTAS illustrated good inter-rater reliability. Finally, ESI illustrated the appropriate validity for triage system.展开更多
BACKGROUND:Most current triage tools have been tested among hospital nurses groups but there are not similar studies in university setting.In this study we analyzed if a course on a new fourlevel triage model,triage e...BACKGROUND:Most current triage tools have been tested among hospital nurses groups but there are not similar studies in university setting.In this study we analyzed if a course on a new fourlevel triage model,triage emergency method(TEM),could improve the quality of rating in a group of nursing students.METHODS:This observational study was conducted with paper scenarios at the University of Parma,Italy.Fifty students were assigned a triage level to 105 paper scenarios before and after a course on triage and TEM.We used weighted kappa statistics to measure the inter-rater reliability of TEM and assessed its validity by comparing the students' predictions with the triage code rating of a reference standard(a panel of five experts in the new triage method).RESULTS:Inter-rater reliability was K=0.42(95%Cl:0.37-0.46) before the course on TEM,and K=0.61(95%CI:0.56-0.67) after.The accuracy of students' triage rating for the reference standard triage code was good:81%(95%Cl:71-90).After the TEM course,the proportion of cases assigned to each acuity triage level was similar for the student group and the panel of experts.CONCLUSION:Among the group of nursing students,a brief course on triage and on a new inhospital triage method seems to improve the quality of rating codes.The new triage method shows good inter-rater reliability for rating triage acuity and good accuracy in predicting the triage code rating of the reference standard.展开更多
Traditional triage cannot meet the needs of modern warfare. This paper describes the design of triage and evacuation equipment for casualties at sea that can quickly address mass-casualty triage and store and transmit...Traditional triage cannot meet the needs of modern warfare. This paper describes the design of triage and evacuation equipment for casualties at sea that can quickly address mass-casualty triage and store and transmit information during battlefield treatment and medical evacuation. This equipment consists of a high-capacity medical information card, a simulated patient generator, a triage classifier and a multifunctional airbag triage vest.展开更多
BACKGROUND: Bombing is a unique incident which produces unique patterns, multiple and occult injuries. Death often is a result of combined blast, ballistic and thermal effect injuries. Various natures of injury, self ...BACKGROUND: Bombing is a unique incident which produces unique patterns, multiple and occult injuries. Death often is a result of combined blast, ballistic and thermal effect injuries. Various natures of injury, self referrals and arrival by private transportation may lead to "wrong triage" in the emergency department. In India there has been an increase in incidence of bombing in the last 15 years. There is no documented triage tool from the National Disaster Management Authority of India for Bombings. We have tried to develop an ideal bombing specific triage tool which will guide the right patients to the right place at the right time and save more lives.METHODS: There are three methods of studying the triage tool: 1) real disaster; 2) mock drill; 3) table top exercise. In this study, a table top exercise method was selected. There are two groups, each consisting of an emergency physician, a nurse and a paramedic.RESULTS: By using the proportion test, we found that correct triaging was significantly different(P=0.005) in proportion between the two groups: group B(80%) with triage tool performed better in triaging the bomb blast victims than group A(50%) without the bombing specific triage tool performed.CONCLUSION: Development of bombing specific triage tool can reduce under triaging.展开更多
When the troops are attacked by nuclear weapons, the number of the wounded and thetype and the condition of the wounds will change with the equivalence and the way of explosion, thenumber of soldiers taking part, the ...When the troops are attacked by nuclear weapons, the number of the wounded and thetype and the condition of the wounds will change with the equivalence and the way of explosion, thenumber of soldiers taking part, the area of the disposition of the troops, and the conditions of protectionof the personnel. Whether the wounded by nuclear weapons who is pouring in enormous amountcan be correctly classified in time has a very important relation in enhancing the effect of the first-aidand the treatment later on. We worked out a programme about the defined types and criteria of thewounded by nuclear weapons beforehand to be stored into the microcomputer. After nuclear cxplo-sion, it is necessary only to input the known data into the microcomputer from the key-board, thecomputer will immediately tell the number of the wounded of various types, the number of peopleand the time needed to perform the triage task and the surgical personnel needed to performthe operations, so that medical supporting programme can be selected or adjusted on time and the ef-ficiency and quality of the triage and first-aid work can be improved.展开更多
BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early pre...BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment(CETAT)database,which was collected between January 1^(st),2020,and June 25^(th),2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron(MLP)classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve(AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8(Scenario I),and a scenario requiring specificity greater than 0.8(Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression(LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score(NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation(SpO_(2)),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.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.
基金the Vice Chancellor of Research in Mashhad University of Medical Sciences(Grant No.950170)
文摘BACKGROUND:It is not clear whether Emergency Severity Index(ESI)is valid to triage heart failure(HF)patients and if HF patients benefi t more from a customized triage scale or not.The aim of study is to compare the effect of Heart Failure Triage Scale(HFTS)and ESI on mistriage among patients with HF who present to the emergency department(ED).METHODS:A randomized clinical trial was conducted from April to June 2017.HF patients with dyspnea were randomly assigned to HFTS or ESI groups.Triage level,used resources and time to electrocardiogram(ECG)were compared between both groups among HF patients who were admitted to coronary care unit(CCU),cardiac unit(CU)and discharged patients from the ED.Content validity was examined using Kappa designating agreement on relevance(K*).Reliability of both scale was evaluated using inter-observer agreement(Kappa).RESULTS:Seventy-three and 74 HF patients were assigned to HFTS and ESI groups respectively.Time to ECG in HFTS group was signifi cantly shorter than that of ESI group(2.05 vs.16.82 minutes).Triage level between HFTS and ESI groups was signifi cantly different among patients admitted to CCU(1.0 vs.2.8),cardiac unit(2.26 vs.3.06)and discharged patients from the ED(3.53 vs.2.86).Used resources in HFTS group was significantly different among triage levels(H=25.89;df=3;P<0.001).CONCLUSION:HFTS is associated with less mistriage than ESI for triaging HF patients.It is recommended to make use of HFTS to triage HF patients in the ED.
文摘BACKGROUND: Although the Australasian Triage Scale(ATS) has been developed two decades ago, its reliability has not been def ined; therefore, we present a meta-analyis of the reliability of the ATS in order to reveal to what extent the ATS is reliable.DATA SOURCES: Electronic databases were searched to March 2014. The included studies were those that reported samples size, reliability coefficients, and adequate description of the ATS reliability assessment. The guidelines for reporting reliability and agreement studies(GRRAS) were used. Two reviewers independently examined abstracts and extracted data. The effect size was obtained by the z-transformation of reliability coefficients. Data were pooled with random-effects models, and meta-regression was done based on the method of moment's estimator.RESULTS: Six studies were included in this study at last. Pooled coefficient for the ATS was substantial 0.428(95%CI 0.340–0.509). The rate of mis-triage was less than fifty percent. The agreement upon the adult version is higher than the pediatric version.CONCLUSION: The ATS has shown an acceptable level of overall reliability in the emergency department, but it needs more development to reach an almost perfect agreement.
文摘BACKGROUND: Triage system in children seems to be more challenging compared to adults because of their different response to physiological and psychosocial stressors. This study aimed to determine the best triage system in the pediatric emergency department.METHODS: This was a prospective observational study. This study was divided into two phases. The fi rst phase determined the inter-rater reliability of fi ve triage systems: Manchester Triage System(MTS), Emergency Severity Index(ESI) version 4, Pediatric Canadian Triage and Acuity Scale(CTAS), Australasian Triage Scale(ATS), and Ramathibodi Triage System(RTS) by triage nurses and pediatric residents. In the second phase, to analyze the validity of each triage system, patients were categorized as two groups, i.e., high acuity patients(triage level 1, 2) and low acuity patients(triage level 3, 4, and 5). Then we compared the triage acuity with actual admission.RESULTS: In phase I, RTS illustrated almost perfect inter-rater reliability with kappa of 1.0(P<0.01). ESI and CTAS illustrated good inter-rater reliability with kappa of 0.8–0.9(P<0.01). Meanwhile, ATS and MTS illustrated moderate to good inter-rater reliability with kappa of 0.5–0.7(P<0.01). In phase II, we included 1 041 participants with average age of 4.7±4.2 years, of which 55% were male and 45% were female. In addition 32% of the participants had underlying diseases, and 123(11.8%) patients were admitted. We found that ESI illustrated the most appropriate predicting ability for admission with sensitivity of 52%, specifi city of 81%, and AUC 0.78(95%CI 0.74–0.81).CONCLUSION: RTS illustrated almost perfect inter-rater reliability. Meanwhile, ESI and CTAS illustrated good inter-rater reliability. Finally, ESI illustrated the appropriate validity for triage system.
文摘BACKGROUND:Most current triage tools have been tested among hospital nurses groups but there are not similar studies in university setting.In this study we analyzed if a course on a new fourlevel triage model,triage emergency method(TEM),could improve the quality of rating in a group of nursing students.METHODS:This observational study was conducted with paper scenarios at the University of Parma,Italy.Fifty students were assigned a triage level to 105 paper scenarios before and after a course on triage and TEM.We used weighted kappa statistics to measure the inter-rater reliability of TEM and assessed its validity by comparing the students' predictions with the triage code rating of a reference standard(a panel of five experts in the new triage method).RESULTS:Inter-rater reliability was K=0.42(95%Cl:0.37-0.46) before the course on TEM,and K=0.61(95%CI:0.56-0.67) after.The accuracy of students' triage rating for the reference standard triage code was good:81%(95%Cl:71-90).After the TEM course,the proportion of cases assigned to each acuity triage level was similar for the student group and the panel of experts.CONCLUSION:Among the group of nursing students,a brief course on triage and on a new inhospital triage method seems to improve the quality of rating codes.The new triage method shows good inter-rater reliability for rating triage acuity and good accuracy in predicting the triage code rating of the reference standard.
基金the funding from the Military Program during the 12th Five-year Plan Period,Proposal No.2011YY027
文摘Traditional triage cannot meet the needs of modern warfare. This paper describes the design of triage and evacuation equipment for casualties at sea that can quickly address mass-casualty triage and store and transmit information during battlefield treatment and medical evacuation. This equipment consists of a high-capacity medical information card, a simulated patient generator, a triage classifier and a multifunctional airbag triage vest.
文摘BACKGROUND: Bombing is a unique incident which produces unique patterns, multiple and occult injuries. Death often is a result of combined blast, ballistic and thermal effect injuries. Various natures of injury, self referrals and arrival by private transportation may lead to "wrong triage" in the emergency department. In India there has been an increase in incidence of bombing in the last 15 years. There is no documented triage tool from the National Disaster Management Authority of India for Bombings. We have tried to develop an ideal bombing specific triage tool which will guide the right patients to the right place at the right time and save more lives.METHODS: There are three methods of studying the triage tool: 1) real disaster; 2) mock drill; 3) table top exercise. In this study, a table top exercise method was selected. There are two groups, each consisting of an emergency physician, a nurse and a paramedic.RESULTS: By using the proportion test, we found that correct triaging was significantly different(P=0.005) in proportion between the two groups: group B(80%) with triage tool performed better in triaging the bomb blast victims than group A(50%) without the bombing specific triage tool performed.CONCLUSION: Development of bombing specific triage tool can reduce under triaging.
文摘When the troops are attacked by nuclear weapons, the number of the wounded and thetype and the condition of the wounds will change with the equivalence and the way of explosion, thenumber of soldiers taking part, the area of the disposition of the troops, and the conditions of protectionof the personnel. Whether the wounded by nuclear weapons who is pouring in enormous amountcan be correctly classified in time has a very important relation in enhancing the effect of the first-aidand the treatment later on. We worked out a programme about the defined types and criteria of thewounded by nuclear weapons beforehand to be stored into the microcomputer. After nuclear cxplo-sion, it is necessary only to input the known data into the microcomputer from the key-board, thecomputer will immediately tell the number of the wounded of various types, the number of peopleand the time needed to perform the triage task and the surgical personnel needed to performthe operations, so that medical supporting programme can be selected or adjusted on time and the ef-ficiency and quality of the triage and first-aid work can be improved.
基金Applicable Funding Source University of Science and Technology of China(to YLL)National Natural Science Foundation of China(12126604)(to MPZ)+1 种基金R&D project of Pazhou Lab(Huangpu)(2023K0609)(to MPZ)Anhui Provincial Natural Science(grant number 2208085MH235)(to KJ)。
文摘BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment(CETAT)database,which was collected between January 1^(st),2020,and June 25^(th),2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron(MLP)classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve(AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8(Scenario I),and a scenario requiring specificity greater than 0.8(Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression(LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score(NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation(SpO_(2)),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.
