Dataset Information

Defining High-risk Emergency Chief Complaints: Data-driven Triage for Low- and Middle-income Countries.

ABSTRACT:

Objectives

Emergency medicine in low- and middle-income countries (LMICs) is hindered by lack of research into patient outcomes. Chief complaints (CCs) are fundamental to emergency care but have only recently been uniquely codified for an LMIC setting in Uganda. It is not known whether CCs independently predict emergency unit patient outcomes.

Methods

Patient data collected in a Ugandan emergency unit between 2009 and 2018 were randomized into validation and derivation data sets. A recursive partitioning algorithm stratified CCs by 3-day mortality risk in each group. The process was repeated in 10,000 bootstrap samples to create an averaged risk ranking. Based on this ranking, CCs were categorized as "high-risk" (>2× baseline mortality), "medium-risk" (between 2 and 0.5× baseline mortality), and "low-risk" (<0.5× baseline mortality). Risk categories were then included in a logistic regression model to determine if CCs independently predicted 3-day mortality.

Results

Overall, the derivation data set included 21,953 individuals with 7,313 in the validation data set. In total, 43 complaints were categorized, and 12 CCs were identified as high-risk. When controlled for triage data including age, sex, HIV status, vital signs, level of consciousness, and number of complaints, high-risk CCs significantly increased 3-day mortality odds ratio (OR = 2.39, 95% confidence interval [CI] = 1.95 to 2.93, p < 0.001) while low-risk CCs significantly decreased 3-day mortality odds (OR = 0.16, 95% CI = 0.09 to 0.29, p < 0.001).

Conclusions

High-risk CCs were identified and found to predict increased 3-day mortality independent of vital signs and other data available at triage. This list can be used to expand local triage systems and inform emergency training programs. The methodology can be reproduced in other LMIC settings to reflect their local disease patterns.

SUBMITTER: Rice B

PROVIDER: S-EPMC7818254 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Defining High-risk Emergency Chief Complaints: Data-driven Triage for Low- and Middle-income Countries.

Rice Brian B Leanza Joseph J Mowafi Hani H Thadeus Kamara Nicholas N Mugema Mulogo Edgar E Bisanzo Mark M Nikam Kian K Kizza Hilary H Newberry Jennifer A JA Strehlow Matthew M Kohn Michael M

Academic emergency medicine : official journal of the Society for Academic Emergency Medicine 20200618 12

<h4>Objectives</h4>Emergency medicine in low- and middle-income countries (LMICs) is hindered by lack of research into patient outcomes. Chief complaints (CCs) are fundamental to emergency care but have only recently been uniquely codified for an LMIC setting in Uganda. It is not known whether CCs independently predict emergency unit patient outcomes.<h4>Methods</h4>Patient data collected in a Ugandan emergency unit between 2009 and 2018 were randomized into validation and derivation data sets. ...[more]

PMID: 32416022

Similar Datasets

Project description:Introduction: Black and Hispanic patients are frequently assigned lower acuity triage scores than White patients. This can lead to longer wait times, less aggressive care, and worse outcomes. In this study we aimed to determine whether these effects are more pronounced for patients with subjective complaints. Methods: We performed a retrospective analysis for all adult visits between 2016-2019 at an urban academic emergency department (ED) with acuity-based pods. We determined rates of initial high-acuity triage both across all patients and among the subset located in the high-acuity pod at time of disposition (either through initial assignment or subsequent up-triage). Analysis was performed for common chief complaints categorized as subjective (chest pain, dyspnea, any pain); observed (altered mental status); numeric (fever, hypotension); or protocolized (stroke, ST-elevation myocardial infarction). We constructed logistic regression models to control for age, race, gender, method of arrival, and final disposition. Results: We analyzed 297,355 adult ED visits. Black and Hispanic patients were less likely to be triaged to high-acuity beds (adjusted odds ratio [aOR] 0.76, 95% confidence interval [CI] 0.73-0.79 for Black, and aOR 0.87, 95% CI 0.84-0.90 for Hispanic patients). This effect was more pronounced for those with subjective chief complaints, including chest pain (aOR 0.76, 95% CI 0.73-0.79 for Black and 0.88, 95% CI 0.78-0.99 for Hispanic patients), dyspnea (aOR 0.79, 95% CI 0.68-0.92 and 0.8, 95% CI 0.72-0.99), and any pain (aOR 0.83, 95% CI 0.75-0.92 and 0.89, 95% CI 0.82-0.97, respectively). Among patients in the high-acuity pod at time of disposition, Black and Hispanic patients were disproportionately triaged to lower acuity pods on arrival (aOR 1.47, 95% CI 1.33-1.63 for Black and aOR 1.27, 95% CI 1.15-1.40 for Hispanic adults), with significant differences observed only for subjective chief complaints. No differences were observed for observed, objective, or protocolized complaints in either analysis. Conclusion: Black and Hispanic adults, including those who ultimately required high-acuity resources, were disproportionately triaged to lower acuity pods. This effect was more pronounced for patients with subjective chief complaints. Additional work is needed to identify and overcome potential bias in the assessment of patients with subjective chief complaints in ED triage.

Project description:IntroductionEarly and accurate recognition of children at risk of progressing to critical illness could contribute to improved patient outcomes and resource allocation. In resource limited settings digital triage tools can support decision making and improve healthcare delivery. We developed a model for rapid identification of critically ill children at triage.MethodsThis was a prospective cohort study of acutely ill children presenting at Jinja Regional Referral Hospital in Eastern Uganda. Variables collected in the emergency department informed the development of a logistic model based on hospital admission using bootstrap stepwise regression. Low and high-risk thresholds for 90% minimum sensitivity and specificity, respectively generated three risk level categories. Performance was assessed using receiver operating characteristic curve analysis on a held-out test set generated by an 80:20 split with 10-fold cross validation. A risk stratification table informed clinical interpretation.ResultsThe model derivation cohort included 1,612 participants, with an admission rate of approximately 23%. The majority of admitted patients were under five years old and presenting with sepsis, malaria, or pneumonia. A 9-predictor triage model was derived: logit (p) = -32.888 + (0.252, square root of age) + (0.016, heart rate) + (0.819, temperature) + (-0.022, mid-upper arm circumference) + (0.048 transformed oxygen saturation) + (1.793, parent concern) + (1.012, difficulty breathing) + (1.814, oedema) + (1.506, pallor). The model afforded good discrimination, calibration, and risk stratification at the selected thresholds of 8% and 40%.ConclusionIn a low income, pediatric population, we developed a nine variable triage model with high sensitivity and specificity to predict who should be admitted. The triage model can be integrated into any digital platform and used with minimal training to guide rapid identification of critically ill children at first contact. External validation and clinical implementation are in progress.

Project description:Objective:We learn contextual embeddings for emergency department (ED) chief complaints using Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art language model, to derive a compact and computationally useful representation for free-text chief complaints. Materials and methods:Retrospective data on 2.1 million adult and pediatric ED visits was obtained from a large healthcare system covering the period of March 2013 to July 2019. A total of 355 497 (16.4%) visits from 65 737 (8.9%) patients were removed for absence of either a structured or unstructured chief complaint. To ensure adequate training set size, chief complaint labels that comprised less than 0.01%, or 1 in 10 000, of all visits were excluded. The cutoff threshold was incremented on a log scale to create seven datasets of decreasing sparsity. The classification task was to predict the provider-assigned label from the free-text chief complaint using BERT, with Long Short-Term Memory (LSTM) and Embeddings from Language Models (ELMo) as baselines. Performance was measured as the Top-k accuracy from k?=?1:5 on a hold-out test set comprising 5% of the samples. The embedding for each free-text chief complaint was extracted as the final 768-dimensional layer of the BERT model and visualized using t-distributed stochastic neighbor embedding (t-SNE). Results:The models achieved increasing performance with datasets of decreasing sparsity, with BERT outperforming both LSTM and ELMo. The BERT model yielded Top-1 accuracies of 0.65 and 0.69, Top-3 accuracies of 0.87 and 0.90, and Top-5 accuracies of 0.92 and 0.94 on datasets comprised of 434 and 188 labels, respectively. Visualization using t-SNE mapped the learned embeddings in a clinically meaningful way, with related concepts embedded close to each other and broader types of chief complaints clustered together. Discussion:Despite the inherent noise in the chief complaint label space, the model was able to learn a rich representation of chief complaints and generate reasonable predictions of their labels. The learned embeddings accurately predict provider-assigned chief complaint labels and map semantically similar chief complaints to nearby points in vector space. Conclusion:Such a model may be used to automatically map free-text chief complaints to structured fields and to assist the development of a standardized, data-driven ontology of chief complaints for healthcare institutions.

Project description:BackgroundDespite the growing interest in the development of emergency care systems and emergency medicine (EM) as a specialty globally, there still exists a significant gap between the need for and the provision of emergency care by specialty trained providers. Many efforts to date to expand the practice of EM have focused on programs developed through partnerships between higher- and lower-resource settings.ObjectiveTo systematically review the literature to evaluate the composition of EM training programs in low- and middle-income countries (LMICs) developed through partnerships.MethodsAn electronic search was conducted using four databases for manuscripts on EM training programs - defined as structured education and/or training in the methods, procedures, and techniques of acute or emergency care - developed through partnerships. The search produced 7702 results. Using a priori inclusion and exclusion criteria, 94 manuscripts were included. After scoring these manuscripts, a more in-depth examination of 26 of the high-scoring manuscripts was conducted.FindingsFifteen highlight programs with a focus on specific EM content (i.e. ultrasound) and 11 cover EM programs with broader scopes. All outline programs with diverse curricula and varied educational and evaluative methods spanning from short courses to full residency programs, and they target learners from medical students and nurses to mid-level providers and physicians. Challenges of EM program development through partnerships include local adaptation of international materials; addressing the local culture(s) of learning, assessment, and practice; evaluation of impact; sustainability; and funding.ConclusionsOverall, this review describes a diverse group of programs that have been or are currently being implemented through partnerships. Additionally, it highlights several areas for program development, including addressing other topic areas within EM beyond trauma and ultrasound and evaluating outcomes beyond the level of the learner. These steps to develop effective programs will further the advancement of EM as a specialty and enhance the development of effective emergency care systems globally.

Dataset Information

Defining High-risk Emergency Chief Complaints: Data-driven Triage for Low- and Middle-income Countries.

Objectives

Methods

Results

Conclusions

Publications

Defining High-risk Emergency Chief Complaints: Data-driven Triage for Low- and Middle-income Countries.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets