Setting up standards: A methodological proposal for pediatric Triage machine learning model construction based on clinical outcomes
تنظیم استانداردها: یک پیشنهاد روش شناختی برای ساخت مدل یادگیری ماشین تراشی کودکان براساس نتایج بالینی-2019
Triage is a critical process in hospital emergency departments (ED). Specifically, we consider how to achieve fast and accurate patient Triage in the ED of a pediatric hospital. The goal of this paper is to establish methodological best practices for the application of machine learning (ML) to Triage in pediatric ED, providing a comprehensive comparison of the performance of ML techniques over a large dataset. Our work is among the first attempts in this direction. Following very recent works in the literature, we use the clinical outcome of a case as its label for supervised ML model training, instead of the more uncertain labels provided by experts. The experimental dataset contains the records along 3 years of operation of the hospital ED. It consists of 189,718 patients visits to the hospital. The clinical outcome of 9271 cases (4.98%) wa hospital admission, therefore our dataset is highly class imbalanced. Our reported performance comparison results focus on four ML models: Deep Learning (DL), Random Forest (RF), Naive Bayes (NB) and Support Vector Machines (SVM). Data preprocessing includes class imbalance correction, and case re-labeling. We use different well known metrics to evaluate performance of ML models in three different experimental settings: (a) classification of each case into the standard five Triage urgency levels, (b) discrimination of high versus low case severity according to its clinical outcome, and (c) comparison of the number of patients assigned to each standard Triage urgency level against the Triage rule based expert system currently in use at the hospital. RF achieved greater AUC, accuracy, PPV and specificity than the other models in the dychotomic classification experiments. On the implementation side, our study shows that ML predictive models trained according to clinical outcomes, provide better Triage performance than the current rule based expert system in operation at the hospital.
Keywords: Machine learning | Emergency department | Triage | Data science | Clinical decision support systems
PALLIATIVE CARE SYMPTOM MANAGEMENT IN THE EMERGENCY DEPARTMENT: THE ABC’S OF SYMPTOM MANAGEMENT FOR THE EMERGENCY PHYSICIAN
مدیریت علائم مراقبت از بیمار در بخش اورژانس: مدیریت علائم ABC برای بیمارستانی-2018
Background: Palliative care is a rapidly evolving area of emergency medicine. With an estimated 5,000 to 10,000 baby boomers per day reaching retirement age, emergency departments (EDs) are treating more patients with chronic and serious disease. Palliative care offers comprehensive care for patients with advanced medical illness, aims to alleviate suffering and improve quality of life, and plays an important role in caring for these patients in the ED. Objectives: We sought to increase the emergency physician’s knowledge of and comfort with symptom control in palliative and hospice patients. Discussion: Having the skills to deliver efficient and appropriate palliative and hospice care is imperative for emergency physicians. Palliative care should be considered in any patient suffering from symptoms of a life-limiting illness, whereas hospice care should be considered in the patient with likely <6 months left to live. Palliative care is appropriate earlier in the course of disease, and is appropriate when the practitioner would not be surprised if the patient died in the next 2 years (‘‘The Surprise Question’’). This article discusses management in the ED of pain, nausea, dyspnea, agitation, and oral secretions in patients appropriate for hospice and palliative care. Conclusion: The need for palliative and hospice care in the ED is increasing, requiring that emergency physicians be familiar with palliative and hospice care and competent in the delivery of rapid symptom management in patients with severe and life-limiting disease. 2017 Elsevier Inc. All rights reserved.
Keywords: emergency medicine; end of life; palliative care; symptom management
Crisis in the Emergency Department The Evaluation and Management of Acute Agitation in Children and Adolescents
بحران در بخش اورژانس ارزیابی و مدیریت هیجان حاد در کودکان و نوجوانان-2018
KEYWORDS : Agitation ، Aggression ، Restraint/seclusion ، Emergency department ، Delirium
Sickle Cell Disease in the Emergency Department: Complications and Management
بیماری سلولی سقط در بخش اورژانس: عوارض و مدیریت-2018
Sickle cell disease is the most com mon blood disorder in the United States, affecting 100 000 people. A genetic mutation creates hemoglobin S. In the deoxygenated state, hemo globin S polymerizes, creating sickled hemoglobin. Sickled hemoglobin causes a cascade of complex patho physiologic events that lead to hemo lysis, chronic anemia and endothelial damage. This results in clinical com plications, end organ dysfunction and a shortened life expectancy. The acute nature of many sickle cell complica tions makes the emergency depart ment a common setting where sickle cell patients present. Common com plications (vaso-occlusive episode, fe ver, acute chest syndrome, stroke) and less common complications (splenic sequestration, priapism, aplastic cri sis, ocular emergencies) will be dis cussed. Public health implications will be discussed briefly.
Keywords: sickle cell disease; anemia; compli cations; vaso occlusive crisis; vaso occlusive episode; acute chest syn drome; stroke; splenic sequestra tion; priapism; aplastic crisis
Presentations for hypoglycemia associated with diabetes mellitus to emergency departments in a Canadian province: A database and epidemiological analysis
ارائه برای هیپوگلیسمی مرتبط با دیابت به بخش اورژانس در استان کانادا: پایگاه داده و تجزیه و تحلیل اپیدمیولوژیک-2017
Aims: The prevalence of diabetes mellitus was reportedly 9% in 2014, making it one of the most common global chronic conditions. Hypoglycemia is an important complication of diabetes treatment. The objective of this study was to quantify and characterize hypo glycemia presentations associated with type 1 or 2 diabetes made to emergency depart ments (EDs) by adults in a Canadian province. Methods: A retrospective cohort study was conducted using reliable administrative data from Alberta for a five-year period (2010/11–2014/15). Records of interest were those with an ICD-10-CA diagnosis of diabetes-associated hypoglycemia (e.g., E10.63). A descriptive analysis was conducted. Results: Data extraction yielded 7835 presentations by 5884 patients. The majority (56.2%) of presentations were made by males, median patient age was 62, and 60.5% had type 2 dia betes. These episodes constituted 0.08% of presentations to Alberta EDs. The annual rate of presentations decreased by 11.8% during the five-year period. Most presentations (63.4%) involved transportation to ED via ambulance. Median length-of-stay was four hours. For 27.5% of presentations, an X-ray was obtained. Most hypoglycemic episodes (65.2%) were considered to be moderate, while 34.3% were considered to be severe. Conclusions: Diabetes-associated hypoglycemia presentations to Alberta EDs are more com monly made by patients with type 2 diabetes, who are more likely to be transported via ambulance and also admitted. Each year, approximately one percent of Albertans with diabetes presented with a hypoglycemia episode; however, knowledge of the variation across regions can guide a strategy for improved care.
Keywords: Diabetes mellitus | Hypoglycemia | Emergency department | Epidemiology | Administrative database
Effect of Certificate of Need Law on the intensity of competition: The market for emergency care
تأثیر قانون صدور گواهینامه بر کثرت رقابت: بازار خدمات اورژانسی-2017
Purpose: This article aims to contribute to the academic literature in better understanding the impact of Certificate of Need (CON) Law on Emergency Department (ED) care. Impact of CON Law on ED compe tition remains an unanswered empirical question. Methods: We examine the impact of CON Law and its stringency on the intensity of competition (rivalry among competitors) between EDs measured by the Herfindahl-Hirschman Index (HHI). We then esti mate the effects of CON Law on HHI by treating CON as an exogenous (endogenous) variable. Findings: On average the CON legislation enhances ED competition. A possible reason is that the law hinders predatory behavior, and therefore acts as an effective anti-trust tool. Other findings indicate that competition is found to be positively related to a states population size and median income and negatively related with the prevalence of employer provided insurance and magnitude of illegal immigration in a state. Practical implications: This article sheds some light on how political regulations could affect healthcare market and hence may provide public policy makers some insights on reducing healthcare cost. Originality: Our analysis of the impact of CON regulation on ED competition significantly contributes to the healthcare and strategy literature. The law potentially serves as an anti-trust tool in the hands of the government. We extend the empirical literature by treating CON Law and its stringency as exogenous (endogenous). Our comprehensive analysis considers a host of control variables such as population demographics, their health status and access to health care, healthcare facilities, political environment, in addition to the CON features.
Keywords: CON Law | Health policy | Competition | Herfindahl-Hirschman Index | Emergency department
Unhealthy alcohol use in older adults: Association with readmissions and emergency department use in the 30 days after hospital discharge
مصرف الکل ناسالم در افراد مسن: مرتبط با بستری مجدد و استفاده بخش اورژانس در 30 روز پس از ترخیص از بیمارستان-2016
Background: Unhealthy alcohol use could impair recovery of older patients after medical or surgical hospitalizations. However, no prior research has evaluated whether older patients who screen positive for unhealthy alcohol use are at increased risk of readmissions or emergency department (ED) visits within 30 days after discharge. This study examined the association between AUDIT-C alcohol screening results and 30-day readmissions or ED visits.
Methods: Veterans Affairs (VA) patients age 65 years or older, were eligible if they were hospitalized for a medical or surgical condition (2/1/2009–10/1/2011) and had an AUDIT-C score documented in their VA electronic medical record in the year before they were hospitalized. VA and Medicare data identified VA or non-VA index hospitalizations, readmissions, and ED visits. Primary analyses adjusted for demographics, comorbid conditions, and past-year health care utilization.
Results: Among 579,330 hospitalized patients, 13.7% were readmitted and 12.0% visited an ED within 30 days of discharge. In primary analyses, high-risk drinking (n = 7,167) and nondrinking (n = 357,086) were associated with increased probability of readmission (13.8%, 95% CI 13.0–14.6%; and 14.2%, 95% CI 14.1–14.3%, respectively), relative to low-risk drinking (12.9%; 95% CI 12.7–13.0%). Only nondrinkers had increased risk for ED visits.
Conclusions: Alcohol screening results indicating high-risk drinking that were available in medical records were modestly associated with risk for 30-day readmissions and were not associated with risk for ED visits.
Keywords: Alcohol screening | Quality | Unhealthy alcohol use | Emergency department | Readmissions | Post-discharge care
A Systematic Review on the Effectiveness of Brief Interventions for Alcohol Misuse among Adults in Emergency Departments
بررسی سیستماتیک بر روی اثربخشی مداخلات مختصر برای الکل استفادة نادرست در بزرگسالان در بخش اورژانس-2016
Given the frequency with which individuals seek treatment for alcohol-related consequences in emergency de- partments (EDs), they may be the optimal setting to deliver brief interventions (BIs) for alcohol misuse. Studies examining the effectiveness of BIs for alcohol misuse conducted in EDs have yielded mixed results, and new ar- ticles have been published since the last review in 2008. The aim of this study was to provide an updated system- atic review on the effectiveness of BIs for alcohol misuse delivered to adults in EDs. Articles published in June 2014 and earlier were identiﬁed from online databases (PsycInfo, Healthstar, CINAHL, Medline, Nursing and Al- lied Health). Search terms included (1) alcohol, (2) “alcohol screening”, “brief intervention”, “brief alcohol inter- vention” or feedback and (3) “emergency department” or “emergency room”. Once duplicates were removed, 171 abstracts were identiﬁed for review. Thirty-four studies were included in the systematic review. All studies reported a signiﬁcant reduction in alcohol consumption at 3 months post-BI, with some studies ﬁnding signiﬁ- cant differences between the BI and control groups, and other studies ﬁnding signiﬁcant decreases in both con- ditions but no between-groups differences. The majority of studies did not ﬁnd signiﬁcant between-group differences at 6 and 12 months post-BI with regard to decreases in alcohol consumption. Individuals who re- ceived a BI were signiﬁcantly less likely to have an alcohol-related injury at 6 or 12 months post-BI than individ- uals who did not receive a BI. BIs are unlikely to reduce subsequent hospitalizations however, they may be effective in reducing risky driving and motor vehicle crashes associated with alcohol use, which can result in hos- pitalization. Beyond the effects generated by visiting EDs, BIs delivered in EDs may not be effective in reducing alcohol consumption, or in reducing subsequent hospitalizations. BIs may be effective in reducing some alcohol-related consequences. Future studies ought to investigate for whom BIs are most effective, and the pro- cesses that lead to decreases in alcohol consumption and alcohol-related consequences.© 2015 Elsevier Inc. All rights reserved.
Keywords: Brief intervention | Alcohol | Emergency department | Adults | Systematic review
A ‘time and motion’ evaluation of automated dispensing machines in the emergency department
ارزیابی زمان و حرکت توزیع خودکار ماشین آلات در بخش اورژانس-2016
Background: There has been limited assessment of the impact that automated medication dis-pensing machines have on the medication administration process, particularly in Australianemergency departments. The aim of this study is to examine the change in medication retrievaltimes, number of medications retrieved and staff perceptions before and after the installationof automated dispensing machines in an Australian emergency and trauma centre.
Methods: A time and motion method recorded the time taken and number of medicationsretrieved from the medication room by emergency department staff, before and after theinstallation of two automated dispensing machines. Surveys were administered to staff membersto elicit the perceived impact on clinical practice, utilising 5-point Likert scales.
Results: A total of 954 medication retrievals (1030 medications) were recorded in the pre-implementation period and 842 (991 medications) in the post-implementation period. The meantime taken to retrieve any medication was significantly longer in the post-implementationperiod (+5.7 s; p < 0.01). For schedules 2, 3, 4 or unscheduled medications, the mean timeincreased by 26.9 s (p < 0.01), but decreased by 36.1 s (p < 0.01) for schedule 8 or 11 medications.The mean number of medications per retrieval increased slightly in the post implementation period (+0.10; p < 0.01). Staff perceptions were that automated dispensing machines improveknowledge of medications on imprest (p = 0.03) and reduced medication retrieval time (p < 0.01).
Conclusions: This study found that the medication retrieval process was slower with automateddispensing machines for Schedules 2, 3, 4 and unscheduled medications, but quicker for Sched-ule 8 and 11 medications in an Australian emergency and trauma centre. Although retrievingmedications took slightly longer overall, staff believed automated dispensing machines save time.© 2016 College of Emergency Nursing Australasia Ltd. Published by Elsevier Ltd. All rightsreserved.
KEYWORDS: Pharmaceutical Services | Medication systems | Hospital | Medication errors |Pharmaceutical Preparations | Automated Dispensing machine
A cross-sectional study of the clinical characteristics of cancer patients presenting to one tertiary referral emergency department
یک مطالعه به صورت مقطعی از ویژگی های بالینی بیماران مبتلا به سرطان مراجعه کننده که یک سوم به بخش اورژانس ارجاع داده می شوند-2016
Introduction: There is increasing evidence of cancer patients presenting to emergency departments (ED). The study aim was to analyse the characteristics of adult cancer patients presenting to one ED. Understanding cancer patient presentations could assist in the development of new models of care.
Methods: A 12 month retrospective audit was conducted of a random sample of cancer patients. Demographics and characteristic variables were analysed using descriptive, comparative and correlational statistics.
Results: The presentation rate for adult cancer patients was 1110 (2.4%) with 290 sampled. The common symptoms were fever (n = 54: 18.6%), abdominal pain (n = 34: 11.7%), and shortness of breath (n = 32: 11%). The majority of patients were allocated a Triage Category 2 (n = 94: 32.4%) or Triage Category 3 (n = 131: 45.2%). The majority of patients presented between 2 and 15 times. For patients administered antibiotics the average time was 119.8 minutes (SD ± 85.5). The average ED length of stay was mean 8.08 hours with 271 patients (93.4%) admitted to the hospital. Of the 290 patients, 105 (36.2%) had died within 12 months of ED presentation.
Conclusion: The study has shown that while cancer patients are only a small percentage of ED presentations the vast majority are allocated high triage codes, have high admission rates and high mortality rates.
Keywords: Cancer | Oncology | Haematology | Emergency | Time to antibiotic | Chemotherapy | Radiation