scholarly journals Predicting mortality among septic patients presenting to the emergency department–a cross sectional analysis using machine learning

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Adam Karlsson ◽  
Willem Stassen ◽  
Amy Loutfi ◽  
Ulrika Wallgren ◽  
Eric Larsson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Vital Signs ◽  
International Classification Of Diseases ◽  
Mean Value ◽  
Verbal Response ◽  
Abnormal Behaviour ◽  
Cross Sectional ◽  
Final Model ◽  
Level Of Consciousness

Abstract Background Sepsis is a life-threatening condition, causing almost one fifth of all deaths worldwide. The aim of the current study was to identify variables predictive of 7- and 30-day mortality among variables reflective of the presentation of septic patients arriving to the emergency department (ED) using machine learning. Methods Retrospective cross-sectional design, including all patients arriving to the ED at Södersjukhuset in Sweden during 2013 and discharged with an International Classification of Diseases (ICD)-10 code corresponding to sepsis. All predictions were made using a Balanced Random Forest Classifier and 91 variables reflecting ED presentation. An exhaustive search was used to remove unnecessary variables in the final model. A 10-fold cross validation was performed and the accuracy was described using the mean value of the following: AUC, sensitivity, specificity, PPV, NPV, positive LR and negative LR. Results The study population included 445 septic patients, randomised to a training (n = 356, 80%) and a validation set (n = 89, 20%). The six most important variables for predicting 7-day mortality were: “fever”, “abnormal verbal response”, “low saturation”, “arrival by emergency medical services (EMS)”, “abnormal behaviour or level of consciousness” and “chills”. The model including these variables had an AUC of 0.83 (95% CI: 0.80–0.86). The final model predicting 30-day mortality used similar six variables, however, including “breathing difficulties” instead of “abnormal behaviour or level of consciousness”. This model achieved an AUC = 0.80 (CI 95%, 0.78–0.82). Conclusions The results suggest that six specific variables were predictive of 7- and 30-day mortality with good accuracy which suggests that these symptoms, observations and mode of arrival may be important components to include along with vital signs in a future prediction tool of mortality among septic patients presenting to the ED. In addition, the Random Forests appears to be a suitable machine learning method on which to build future studies.

scholarly journals Using modified early warning score to predict need of lifesaving intervention in adult non-trauma patients in a tertiary state hospital

2018 ◽  
Vol 25 (3) ◽  
pp. 146-151 ◽  
Author(s):  
Leong Shian Peng ◽  
Azhana Hassan ◽  
Aida Bustam ◽  
Muhaimin Noor Azhar ◽  
Rashidi Ahmad
Keyword(s):  
Emergency Department ◽  
Critically Ill ◽  
Early Warning ◽  
Demographic Data ◽  
Vital Signs ◽  
Multivariate Logistic Regression Analysis ◽  
Early Warning Score ◽  
Trauma Patients ◽  
Multivariate Logistic Regression ◽  
Level Of Consciousness

Background: Modified early warning score has been validated in many uses in the emergency department. We propose that the modified early warning score performs well in predicting the need of lifesaving interventions in the emergency department, as a predictor of patients who are critically ill. Objective: The study aims to evaluate the use of modified early warning score in sorting out critically ill patients in the emergency department. Methods: The patients’ demographic data and first vital signs (blood pressure, heart rate, temperature, respiratory rate, and level of consciousness) were collected prospectively. Individual modified early warning score was calculated. The outcome was a patient received one or more lifesaving interventions toward the end of stay in emergency department. Multivariate logistic regression analysis was utilized to assess the association between modified early warning score and other potential predictors with outcome. Results: There are a total of 259 patients enrolled into the study. The optimal modified early warning score in predicting lifesaving intervention was ≥4 with a sensitivity of 95% and specificity of 81%. Modified early warning score ≥4 (odds ratio = 96.97, 95% confidence interval = 11.82–795.23, p < 0.001) was found to significantly increase the risk of receiving lifesaving intervention in the emergency department. Conclusion: Modified early warning score is found to be a good predictor for patients in need of lifesaving intervention in the emergency department.

scholarly journals Relationship between Nurses’ Knowledge of Initial Assessment and Application of Early Warning System At Emergency Department of Type A Hospital In Jakarta

2020 ◽  
Vol 4 (1) ◽  
pp. 12
Author(s):  
Sekar Dwi Purnamasari ◽  
Denissa Faradita Aryani
Keyword(s):  
Emergency Department ◽  
Early Warning ◽  
Early Warning System ◽  
Patient Flow ◽  
Vital Signs ◽  
Warning System ◽  
Initial Assessment ◽  
Emergency Nurses ◽  
Cross Sectional ◽  
Nurses Knowledge

<div class="WordSection1"><p class="AbstractContent"><strong>Objective:</strong> Early warning system (EWS) is a physiological scoring to observe the patient’s condition not only in hospital wards but also in Emergency Department (ED). At an overcrowded ER that have slow of patient flow, EWS is use as an early detection of patient’s deterioration by observing the vital signs. The purpose of this study was to identify the relationship between nurses’ knowledge of initial assessment and the application of EWS at emergency department.</p><p class="AbstractContent"><strong>Methods: </strong>This was a quantitative study that used descriptive correlative with cross-sectional design toward 70 emergency nurses.</p><p class="AbstractContent"><strong>Results:</strong> The result showed there was a relationship between nurses’ knowledge of initial assessment and the application of early warning system at emergency room <em>(p</em>=0 .001)<strong></strong></p><p><strong>Conclusion: </strong>The higher the level of nurses’ knowledge, their behavior is better. It is recommended to maintain the use of EWS in ED that already good through training regularly (re-certification).</p><p class="AbstractContent"><strong> </strong></p><div><p class="Keywords"><strong>Keywords: </strong>Early warning system; emergency department; initial assessment; nurses’ knowledge.</p></div></div>

Does the Level of Prehospital Care Influence the Outcome of Patients with Altered Levels of Consciousness?

1996 ◽  
Vol 11 (2) ◽  
pp. 101-104 ◽  
Author(s):  
James Adams ◽  
Gene Aldag ◽  
Robert Wolford
Keyword(s):  
Emergency Department ◽  
Life Support ◽  
Prehospital Care ◽  
Advanced Life Support ◽  
Admission Rate ◽  
Mean Value ◽  
Altered Level ◽  
Levels Of Care ◽  
Level Of Consciousness ◽  
Als Patients

AbstractHypothesis:Significant differences exist in the outcome of patients with altered level of consciousness (ALOC) cared for by advanced life support (ALS) compared with basic life support (BLS) prehospital providers.Methods:Patients transported by ambulance to a community teaching hospital during an 11-month period were studied retrospectively. Study patients were those considered not alert by prehospital personnel. Exclusion criteria included: trauma, intoxication, drowning, shock, and cardiac arrest. Data were abstracted from the ambulance reports and hospital records.Results:Two hundred three patients with an ALOC were identified; 113 were transported by ALS providers (56%) and 90 (44%) by BLS providers. Prehospital levels of consciousness, according to the “alert, verbal, painful, unresponsive” scale (ALS vs BLS) were: “verbal” (40% vs 51%), “painful” (23% vs 23%), and “unresponsive” (37% vs 25%). The mean value for scene time was 15±6 minutes for ALS versus 10±4 minutes for BLS (p <0.001). On arrival in the emergency department, the LOC of 72 (64 %) ALS patients and 58 (64%) BLS patients had improved to “alert.” The level of consciousness in one ALS patient worsened. Fifty-two ALS (46%) and 38 (42%) BLS patients were admitted. Principal final diagnoses were seizure (27% ALS vs 38% BLS), hypoglycemia (23% ALS vs 23% BLS), and stroke (22% ALS vs 20% BLS). Remaining diagnoses each constituted less than 7% of total discharge diagnoses. No statistically significant differences in measures of outcome were noted between ALS or BLS patients. Diagnoses of seizure, stroke, and hypoglycemia were studied individually. No differences in admission rate, mortality rate, or disposition were identified. Hypoglycemic patients conveyed by ALS provider had significantly shorter emergency department treatment times than did those transported by BLS providers (160±62 minutes ALS vs 229±67 minutes BLS [p <0.005]).Conclusion:Advanced life support levels of care of patients with an ALOC does not significantly change outcome compared with those receiving BLS care with the exception of shorter emergency department treatment times for hypoglycemic patients.

scholarly journals Emergency department visits and hospitalisations for emergent asthmatic symptoms from 2014 to 2016: cross-sectional study in Korea

BMJ Open ◽  
2020 ◽  
Vol 10 (8) ◽  
pp. e036237
Author(s):  
Kyungseon Choi ◽  
Sola Han ◽  
Hae Sun Suh
Keyword(s):  
Emergency Department ◽  
Age Groups ◽  
International Classification Of Diseases ◽  
Cross Sectional Study ◽  
Emergency Department Visits ◽  
Resource Utilisation ◽  
Main Diagnosis ◽  
Sectional Study ◽  
Cross Sectional ◽  
Ed Visits

ObjectiveTo evaluate the characteristics of emergent patients with asthma who visited emergency departments (EDs) in Korea, and the consequences of these visits.DesignRetrospective cross-sectional study.SettingWe used data from the National Emergency Department Information System database from 2014 to 2016. The data included reports collected from 408 EDs in Korea.ParticipantsWe analysed the ED cases for asthma-related emergent symptoms that met the following inclusion criteria: (1) had a main diagnosis code of asthma (International Classification of Diseases 10th Revision code: J45/J46), and (2) recorded as an emergent symptom in the EDs.ResultsDuring 2014–2016, there were 58 713 ED visits related to an asthma diagnosis with emergent symptoms. Following an ED visit, 31.69% were hospitalised, of which 89.88% were admitted to the general wards, and 10.12% to the intensive care units (ICUs). More than 50% of the hospitalised cases included in the group ≥70 years of age. The incidence of death during hospitalisation generally increased with age and the proportion of death in ICU exceeded 10% among the group ≥70 years. The ratio of ICU/general ward admission at the arrival time of 0–03:00, in the ≥60 years age group was the highest compared with other times of the day and age groups.ConclusionsWe found that among all age groups, ED visits by older patients resulted in more ICU admissions. Our results can help in providing a better understanding of medical resource utilisation by emergent patients with asthma.

scholarly journals Keywords reflecting sepsis presentation based on mode of emergency department arrival: a retrospective cross-sectional study

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Ulrika Margareta Wallgren ◽  
Eric Larsson ◽  
Anna Su ◽  
Jennifer Short ◽  
Hans Järnbert-Pettersson ◽  
...  
Keyword(s):  
Emergency Department ◽  
Emergency Medical Services ◽  
Vital Signs ◽  
Cross Sectional Study ◽  
Screening Tools ◽  
Medical Services ◽  
Cross Sectional ◽  
Emergency Department Arrival ◽  
Emergency Medical ◽  
Sepsis Screening

Abstract Background Current sepsis screening tools are predominantly based on vital signs. However, patients with serious infections frequently present with normal vital signs and there has been an increased interest to include other variables such as symptoms in screening tools to detect sepsis. The majority of patients with sepsis arrive to the emergency department by emergency medical services. Our hypothesis was that the presentation of sepsis, including symptoms, may differ between patients arriving to the emergency department by emergency medical services and patients arriving by other means. This information is of interest to adapt future sepsis screening tools to the population in which they will be implemented. The aim of the current study was to compare the prevalence of keywords reflecting the clinical presentation of sepsis based on mode of arrival among septic patients presenting to the emergency department. Methods Retrospective cross-sectional study of 479 adult septic patients. Keywords reflecting sepsis presentation upon emergency department arrival were quantified and analyzed based on mode of arrival, i.e., by emergency medical services or by other means. We adjusted for multiple comparisons by applying Bonferroni-adjusted significance levels for all comparisons. Adjustments for age, gender, and sepsis severity were performed by stratification. All patients were admitted to the emergency department of Södersjukhuset, Stockholm, and discharged with an ICD-10 code compatible with sepsis between January 1, and December 31, 2013. Results “Abnormal breathing” (51.8% vs 20.5%, p value < 0.001), “abnormal circulation” (38.4% vs 21.3%, p value < 0.001), “acute altered mental status” (31.1% vs 13.1%, p value < 0.001), and “decreased mobility” (26.1% vs 10.7%, p value < 0.001) were more common among patients arriving by emergency medical services, while “pain” (71.3% vs 40.1%, p value < 0.001) and “risk factors for sepsis” (50.8% vs 30.8%, p value < 0.001) were more common among patients arriving by other means. Conclusions The distribution of most keywords related to sepsis presentation was similar irrespective of mode of arrival; however, some differences were present. This information may be useful in clinical decision tools or sepsis screening tools.

scholarly journals Correlation Between Vital Signs and Amount of Hemoperitoneum in Ruptured Ectopic Pregnancy

2021 ◽  
Vol 17 (3) ◽  
pp. 203-207
Author(s):  
Puja Baniya Chhetri ◽  
Priya Pathak ◽  
Buddhi Kumar Shrestha ◽  
Rubina Shrestha ◽  
Manisha Acharya ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Emergency Department ◽  
Ectopic Pregnancy ◽  
Pearson Correlation ◽  
Strong Association ◽  
Vital Signs ◽  
First Trimester ◽  
Hemodynamic Instability ◽  
Cross Sectional ◽  
Surgical Interventions

IntroductionEctopic pregnancy is a life threatening emergency in first trimester of pregnancy. Hemodynamicstability of the patient remains one of the crucial factors that determine the treatment modalities.The main objective of this study was to study the correlation between the vital signs and amountof hemoperitoneum in ruptured ectopic pregnancy so that early and active interventions can bedone. MethodsWe conducted a cross sectional study of all the pregnant women with ruptured ectopic pregnancywith hemoperitoneum who presented to the emergency department of College of MedicalSciences Teaching Hospital from time period of 1st May 2017-31st May 2020.The different vitalsigns present at the time of initial emergency department and preoperative period prior surgerywere reviewed and used for correlation with amount of hemoperitoneum by using Pearsoncorrelation analysis. ResultsA total of 61 patients were studied. Pearson correlation between different vital signs and amountof hemoperitoneum were: heart rate(r=0.48, p<0.001), systolic blood pressure(r= -0.41,p=0.001),diastolic blood pressure (r= -0.34,p=0.06), mean arterial pressure (r= -0.37,p=0.03), respirationrate(r= 0.33, p=0.08) temperature (r=0.09,p=0.94), and shock index (r=0.55,p<0.001). Only 19 of 36patents with hemoperitoneum ≥750 ml had HR≥100 beats/min and 8 patients had SBP≤90mmHg. ConclusionsNone of the vital signs showed strong association with the amount of hemoperitoneum. Ifdecision for surgical interventions were made based on hemodynamic instability, most of thepatients would have been over-diagnosed and treated differently. Proper and timely diagnosiswith immediate management should be done.

scholarly journals Using Unsupervised Machine Learning to Identify Severity Subgroups Among COVID-19 Patients in the Emergency Department (Preprint)

2020 ◽  
Author(s):  
Julián Benito-León ◽  
Mª Dolores del Castillo ◽  
Alberto Estirado ◽  
Ritwik Ghosh ◽  
Souvki Dubey ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Mortality Rate ◽  
Laboratory Tests ◽  
Vital Signs ◽  
Serum Levels ◽  
Standard Laboratory ◽  
Cluster Assignment ◽  
Unsupervised Machine Learning ◽  
Monocytes And Lymphocytes

BACKGROUND Early detection and intervention are the key factors for improving outcomes in COVID-19. OBJECTIVE To detect severity subgroups among COVID-19 patients, based only on clinical data and standard laboratory tests obtained during the assessment at the emergency department. METHODS We applied unsupervised machine learning to a dataset of 853 COVID-19 patients from HM hospitals in Spain. RESULTS From a total of 850 variables, four tests, the serum levels of aspartate transaminase (AST), lactate dehydrogenase (LDH) and C-reactive protein (CRP), and the number of neutrophils, were enough to segregate the entire patient pool into three separate clusters. Further, the percentage of monocytes and lymphocytes and the levels of alanine transaminase (ALT) distinguished the cluster 3 from the other two clusters. The cluster 1 was characterized by the higher mortality rate and higher levels of AST, ALT, LDH, CRP and number of neutrophils, and low percentage of monocytes and lymphocytes. The cluster 2 included patients with a moderate mortality rate and medium levels of the previous laboratory determinations. The cluster 3 was characterized by the lower mortality rate and lower levels of AST, ALT, LDH, CRP and number of neutrophils, and higher percentage of monocytes and lymphocytes. Age, sex, comorbidities, and vital signs did not allow us to separate the three clusters. An online cluster assignment tool can be found at https://g-nec.car.upm-csic.es/COVID19-severity-group-assessment/. CONCLUSIONS A few standard laboratory tests, deemed to be available in all emergency departments, have shown far discriminative power for characterization of severity subgroups among COVID-19 patients.

scholarly journals Clinico-epidemiological Analysis of Adult Patients With Acute Poisoning

2021 ◽  
Vol 11 (3) ◽  
pp. 33533-33533
Author(s):  
Forogh Soltaninejad ◽  
◽  
Ghazal Beigi ◽  
Parastoo Golshiri ◽  
Nastaran Eizadi-Mood ◽  
...  
Keyword(s):  
Substance Dependence ◽  
Vital Signs ◽  
Study Groups ◽  
Cross Sectional Study ◽  
Acute Poisoning ◽  
Adult Patients ◽  
Cross Sectional ◽  
Self Mutilation ◽  
Significant Difference ◽  
Level Of Consciousness

Background: Patients with acute poisoning sometimes require hospitalization in the Intensive Care Unit (ICU). The correct admission of these patients has resulted to lower mortality. This study compared the characteristics of adult patients with acute poisoning who were admitted to the poisoning ward and the ICU. We also determined the relevant outcome predictive factors. Methods: This cross-sectional study was conducted on adult acutely poisoned patients who were admitted to the emergency room of Khorshid Hospital affiliated with Isfahan University of Medical Sciences from October 2018 to 2019. The clinico-epidemiological variables and outcomes were compared between adult patients hospitalized in the ward (n=100) and ICU (n=100). Binary logistic regression was used for predicting the outcome factors. Results: The Mean±SE age of the study patients in the ICU and ward were 36.6±1.62 (median: 34) and 34.20±1.19 years, (median: 33, P=0.23), respectively. There was no significant difference between the study groups respecting substance dependence, alcohol and drug abuse, disease history, and the type of exposure (P>0.05). However, self-mutilation, the kind of substance, the vital signs and level of consciousness at admission, and outcomes were significantly different between the research groups (P<0.05). Variables predicting outcomes (complication/death) were as follows: gender (male) (OR: 4.51; 95%CI: 1.51-13.42; P=0.007), the kind of substance (pesticides) (OR: 8.84; 95%CI: 1.78-44.07; P=0.008), time to admission (OR: 1.04; 95%CI: 1.02-1.08; P=0.002), hypotension (OR: 14.88; 95%CI: 3.01-71.58; P=0.001), and the place of hospitalization (ward) (OR: 2.85; 95%CI: 1.23-6.62; P=0.01). Conclusion: The self-mutilation, kind of substance, vital signs, level of consciousness at admission, and outcomes were significantly different between the study patients hospitalized in the ICU, compared to the ward. Gender (male), the kind of substance (pesticides), delayed arrival times, hypotension, and the place of hospitalization (ward) were essential factors for outcome (complication/death) prediction.

scholarly journals Impact of Placenta Previa on Fetal Growth

2021 ◽  
pp. 54-63
Author(s):  
Hassan Abubakr Elrewany ◽  
Mohamed Mohsen El Namori ◽  
Shahinaz Hamdy Elshourbagy ◽  
Ahmed Mahmoud Awarah
Keyword(s):  
Fetal Growth ◽  
Gestational Age ◽  
Placenta Previa ◽  
Cerebral Arteries ◽  
Vital Signs ◽  
Placental Tissue ◽  
Mean Value ◽  
Abdominal Circumference ◽  
Cross Sectional ◽  
Femur Length

Background: Placenta Previa refers to the presence of placental tissue that extends over the internal cervical is during pregnancy. The incidence of this condition is reported to be 2% at 20 weeks of gestation and decreases to around 4–6 per 1000 births between 34 and 39 weeks through trophotropism. The aim of the work is to evaluate fetal growth in pregnancies complicated by placenta Previa. Methods: This cross-sectional study was done on 100 pregnant females with placenta Previa aged 18-35 years. Cases were defined as patients with gestational age 24-40 weeks, BMI 18-30 kg/m2, Singleton fetus and diagnosed having placenta Previa; confirmed by trans-vaginal ultrasound in the second and third trimester. Complete history, vital signs and complete obstetric examination, laboratory and radiological investigations (ultrasound done trans-abdominally to evaluate fetal weight, biometry and Doppler studies) were taken. Results: The gestational age ranged from 34-39 weeks with a mean value 36.03 ± 1.23 weeks and a median value 36 weeks (IQR = 35-37 weeks). The femur length ranged from 33.14-39.14 weeks with a mean value 35.44 ± 1.56 weeks and a median value 35.14 weeks (IQR = 34-36.9 weeks).The abdominal circumference ranged from 32.86-39.14 weeks with a mean value 35.43 ± 1.65 weeks with a median value 35.14 weeks (IQR = 33.9-36.7 weeks). As regard to umbilical (UA) and middle cerebral (MCA) arteries Doppler resistant index (RI), UA ranged from 0.48-0.58 with a mean value 0.53 ± 0.03 and a median value 0.53 (IQR = 0.51-0.55). MCA ranged from 0.75-0.85 with a mean value 0.80 ± 0.03 and a median value 0.79 (IQR = 0.77-0.82). Conclusion: Placenta Previa led to preterm delivery (<36 weeks) in about one third of the study cases. Femur length was <36 weeks in 65 patients. Abdominal circumference was <36 weeks in 61 patients. Placenta Previa had insignificant effect on umbilical (UA) and middle cerebral arteries Doppler resistant index.

Keywords Reflecting Sepsis Presentation and Mode of Emergency Department Arrival: A Retrospective Cross-sectional Study

2020 ◽  
Author(s):  
Ulrika Margareta Wallgren ◽  
Eric Larsson ◽  
Anna Su ◽  
Jennifer Short ◽  
Hans Järnbert-Pettersson ◽  
...  
Keyword(s):  
Emergency Department ◽  
Clinical Presentation ◽  
Vital Signs ◽  
Cross Sectional Study ◽  
Screening Tools ◽  
P Value ◽  
Sectional Study ◽  
Cross Sectional ◽  
Emergency Department Arrival ◽  
Sepsis Screening

Abstract Background: Current sepsis screening tools rely predominantly on vital signs. Since patients with serious infections frequently present with normal vital signs there is a need for other variables to be included to detect sepsis. As a first step, it is essential to understand the clinical presentation of septic patients. The aim was to compare the prevalence of keywords reflecting the clinical presentation of sepsis and mode of arrival, among septic patients presenting to the emergency department. Methods: Retrospective cross-sectional study of 479 adult septic patients. Keywords reflecting sepsis presentation upon emergency department arrival were quantified and analyzed based on mode of arrival, i.e. by emergency medical services or by other means. We adjusted for multiple comparisons by applying Bonferroni-adjusted significance levels for all comparisons. Adjustments for age, gender and sepsis severity were performed by stratification. All patients were admitted to the emergency department of Södersjukhuset, Stockholm, and discharged with an ICD-10 code compatible with sepsis between January 1stand December 31st, 2013. Results: “Abnormal breathing” (51.8% vs 20.5%, p-value <0.001), “abnormal circulation” (38.4% vs 21.3%, p-value <0.001), “acute altered mental status” (31.1% vs 13.1%, p-value <0.001) and “decreased mobility” (26.1% vs 10.7%, p-value <0.001) were more common among patients arriving by emergency medical services, while “pain” (71.3% vs 40.1%, p-value <0.001) and “risk factors for sepsis” (50.8% vs 30.8%, p-value <0.001) were more common among patients arriving by other means.Conclusions: The distribution of most keywords related to sepsis presentation was similar irrespective of mode of arrival, however, some differences were present. This information may be useful in clinical decision tools or sepsis screening tools.

Sign in / Sign up

Export Citation Format

Share Document