scholarly journals Development and validation of a practical machine-learning triage algorithm for the detection of patients in need of critical care in the emergency department

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yecheng Liu ◽  
Jiandong Gao ◽  
Jihai Liu ◽  
Joseph Harold Walline ◽  
Xiaoying Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Reference Model ◽  
Characteristic Curve ◽  
Learning System ◽  
Development And Validation ◽  
Triage Algorithm ◽  
Mls Method

AbstractIdentifying critically ill patients is a key challenge in emergency department (ED) triage. Mis-triage errors are still widespread in triage systems around the world. Here, we present a machine learning system (MLS) to assist ED triage officers better recognize critically ill patients and provide a text-based explanation of the MLS recommendation. To derive the MLS, an existing dataset of 22,272 patient encounters from 2012 to 2019 from our institution’s electronic emergency triage system (EETS) was used for algorithm training and validation. The area under the receiver operating characteristic curve (AUC) was 0.875 ± 0.006 (CI:95%) in retrospective dataset using fivefold cross validation, higher than that of reference model (0.843 ± 0.005 (CI:95%)). In the prospective cohort study, compared to the traditional triage system’s 1.2% mis-triage rate, the mis-triage rate in the MLS-assisted group was 0.9%. This MLS method with a real-time explanation for triage officers was able to lower the mis-triage rate of critically ill ED patients.

scholarly journals Development and Validation of a Practical Machine-learning Triage Algorithm for the Detection of Patients in Need of Critical Care in the Emergency Department

2021 ◽  
Author(s):  
Yecheng Liu ◽  
Jiandong Gao ◽  
Jihai Liu ◽  
Joseph Harold Walline ◽  
Xiaoying Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Cohort Study ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Characteristic Curve ◽  
Learning System ◽  
Validation Dataset ◽  
Development And Validation ◽  
Triage Algorithm

Abstract Identifying critically ill patients is a key challenge in emergency department (ED) triage. Mis-triage errors are still widespread in triage systems around the world. Here, we present a machine learning system (MLS) to assist ED triage officers better recognize critically ill patients and provide a text-based explanation of the MLS recommendation. To derive the MLS, an existing dataset of 20,272 patient encounters from 2012 to 2019 from our institution’s electronic emergency triage system (EETS) was used for algorithm training. We then conducted a prospective randomized cohort study of ED patients between March and April 2020. The area under the receiver operating characteristic curve (AUC) was 0.86 in a retrospective validation dataset of 2,000 randomized database cases. In the prospective cohort study, compared to the traditional triage system’s 1.2% mis-triage rate, the mis-triage rate in the MLS-assisted group was 0.9%. This MLS method with a real-time explanation for triage officers was able to lower the mis-triage rate of critically ill ED patients.

scholarly journals Using machine learning tools to predict outcomes for emergency department intensive care unit patients

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Qiangrong Zhai ◽  
Zi Lin ◽  
Hongxia Ge ◽  
Yang Liang ◽  
Nan Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Emergency Department ◽  
Intensive Care ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Predictive Accuracy ◽  
Medical Center ◽  
Learning Tools ◽  
Critical Patients

AbstractThe number of critically ill patients has increased globally along with the rise in emergency visits. Mortality prediction for critical patients is vital for emergency care, which affects the distribution of emergency resources. Traditional scoring systems are designed for all emergency patients using a classic mathematical method, but risk factors in critically ill patients have complex interactions, so traditional scoring cannot as readily apply to them. As an accurate model for predicting the mortality of emergency department critically ill patients is lacking, this study’s objective was to develop a scoring system using machine learning optimized for the unique case of critical patients in emergency departments. We conducted a retrospective cohort study in a tertiary medical center in Beijing, China. Patients over 16 years old were included if they were alive when they entered the emergency department intensive care unit system from February 2015 and December 2015. Mortality up to 7 days after admission into the emergency department was considered as the primary outcome, and 1624 cases were included to derive the models. Prospective factors included previous diseases, physiologic parameters, and laboratory results. Several machine learning tools were built for 7-day mortality using these factors, for which their predictive accuracy (sensitivity and specificity) was evaluated by area under the curve (AUC). The AUCs were 0.794, 0.840, 0.849 and 0.822 respectively, for the SVM, GBDT, XGBoost and logistic regression model. In comparison with the SAPS 3 model (AUC = 0.826), the discriminatory capability of the newer machine learning methods, XGBoost in particular, is demonstrated to be more reliable for predicting outcomes for emergency department intensive care unit patients.

scholarly journals Diagnostic Accuracy of Biomarkers for Early Multiple Organ Dysfunction in Critically Ill Patients: A Multicenter Prospective Observational Study

2020 ◽  
Author(s):  
Shigeto Ishikawa ◽  
Yuto Teshima ◽  
Hiroki Otsubo ◽  
Takashi Shimazui ◽  
Taka-aki Nakada ◽  
...  
Keyword(s):  
Emergency Department ◽  
Observational Study ◽  
Critically Ill ◽  
Organ Dysfunction ◽  
Critically Ill Patients ◽  
Characteristic Curve ◽  
Treatment Strategies ◽  
Multiple Organ ◽  
Multiple Organ Dysfunction ◽  
Qsofa Score

Abstract BackgroundShock and organ damage occur in critically ill patients in the emergency department because of biological responses to invasion, and cytokines play an important role in their development. It is important to predict early multiple organ dysfunction (MOD) because it is useful in predicting patient outcomes and selecting treatment strategies. This study examined the accuracy of biomarkers, including interleukin (IL)-6, in predicting early MOD in critically ill patients compared with that of quick sequential organ failure assessment (qSOFA).MethodsThis observational study was conducted at five universities from 2016 to 2018. Data of adult patients with systemic inflammatory response syndrome who presented to the emergency department or were admitted to the intensive care unit were prospectively evaluated. qSOFA score and each biomarker (IL-6, IL-8, IL-10, tumor necrosis factor-α, C-reactive protein, and procalcitonin [PCT]) level were assessed on Days 0, 1, and 2. The primary outcome was set as MOD on Day 2, and the area under the receiver operating characteristic curve (AUROC) was analyzed to evaluate qSOFA scores and biomarker levels.ResultsOf 199 patients, 38 were excluded and 161 were included. Patients with MOD on Day 2 had significantly higher qSOFA, SOFA, and Acute Physiology and Chronic Health Evaluation II scores and a trend toward worse prognosis, including mortality. The AUROC for qSOFA score (Day 0) that predicted MOD (Day 2) was 0.728 (95% confidence interval [CI]: 0.651–0.794). IL-6 (Day 1) showed the highest AUC among all biomarkers (0.790 [95% CI: 0.711–852]). The combination of qSOFA (Day 0) and IL-6 (Day 1) showed improved prediction accuracy (0.859 [95% CI: 0.792–0.907]). The combination model using qSOFA (Day 0) and IL-6 (Day 1) also showed a higher AUROC (0.889 [95% CI: 0.828–0.929]).ConclusionsThe addition of serum IL-6 level to qSOFA scores improved the accuracy of early MOD prediction.

scholarly journals Machine Learning Model to Identify Sepsis Patients in the Emergency Department: Algorithm Development and Validation

2021 ◽  
Vol 11 (11) ◽  
pp. 1055
Author(s):  
Pei-Chen Lin ◽  
Kuo-Tai Chen ◽  
Huan-Chieh Chen ◽  
Md. Mohaimenul Islam ◽  
Ming-Chin Lin
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Characteristic Curve ◽  
External Validation ◽  
Model Performance ◽  
Learning Model ◽  
Gradient Boosting ◽  
Machine Learning Model ◽  
Extreme Gradient Boosting ◽  
Development And Validation

Accurate stratification of sepsis can effectively guide the triage of patient care and shared decision making in the emergency department (ED). However, previous research on sepsis identification models focused mainly on ICU patients, and discrepancies in model performance between the development and external validation datasets are rarely evaluated. The aim of our study was to develop and externally validate a machine learning model to stratify sepsis patients in the ED. We retrospectively collected clinical data from two geographically separate institutes that provided a different level of care at different time periods. The Sepsis-3 criteria were used as the reference standard in both datasets for identifying true sepsis cases. An eXtreme Gradient Boosting (XGBoost) algorithm was developed to stratify sepsis patients and the performance of the model was compared with traditional clinical sepsis tools; quick Sequential Organ Failure Assessment (qSOFA) and Systemic Inflammatory Response Syndrome (SIRS). There were 8296 patients (1752 (21%) being septic) in the development and 1744 patients (506 (29%) being septic) in the external validation datasets. The mortality of septic patients in the development and validation datasets was 13.5% and 17%, respectively. In the internal validation, XGBoost achieved an area under the receiver operating characteristic curve (AUROC) of 0.86, exceeding SIRS (0.68) and qSOFA (0.56). The performance of XGBoost deteriorated in the external validation (the AUROC of XGBoost, SIRS and qSOFA was 0.75, 0.57 and 0.66, respectively). Heterogeneity in patient characteristics, such as sepsis prevalence, severity, age, comorbidity and infection focus, could reduce model performance. Our model showed good discriminative capabilities for the identification of sepsis patients and outperformed the existing sepsis identification tools. Implementation of the ML model in the ED can facilitate timely sepsis identification and treatment. However, dataset discrepancies should be carefully evaluated before implementing the ML approach in clinical practice. This finding reinforces the necessity for future studies to perform external validation to ensure the generalisability of any developed ML approaches.

Pediatric Diabetic Ketoacidosis and Hypoglycemia

2020 ◽  
Author(s):  
Rachel J Williams ◽  
Samantha L. Wood
Keyword(s):  
Emergency Department ◽  
Key Words ◽  
Diabetic Ketoacidosis ◽  
Critically Ill ◽  
Cerebral Edema ◽  
Critically Ill Patients ◽  
Pediatric Patients ◽  
Serum Glucose ◽  
Neurologic Function ◽  
Threat To Life

Abnormalities of serum glucose in pediatric patients are commonly encountered in the emergency department and represent an acute threat to life and neurologic function. Rapidly identifying and aggressively treating hyperglycemia with diabetic ketoacidosis and hypoglycemia are critical to ensure the best possible outcome. This review will guide the emergency provider in the identification, resuscitation, workup, and disposition of these critically ill patients. This review contains 6 figures, 13 tables, and 50 reviews. Key Words: Cerebral edema, diabetic ketoacidosis, hyperglycemia, hypoglycemia

Sign in / Sign up

Export Citation Format

Share Document