Dataset Information

Development and Assessment of an Interpretable Machine Learning Triage Tool for Estimating Mortality After Emergency Admissions.

ABSTRACT:

Importance

Triage in the emergency department (ED) is a complex clinical judgment based on the tacit understanding of the patient's likelihood of survival, availability of medical resources, and local practices. Although a scoring tool could be valuable in risk stratification, currently available scores have demonstrated limitations.

Objectives

To develop an interpretable machine learning tool based on a parsimonious list of variables available at ED triage; provide a simple, early, and accurate estimate of patients' risk of death; and evaluate the tool's predictive accuracy compared with several established clinical scores.

Design, setting, and participants

This single-site, retrospective cohort study assessed all ED patients between January 1, 2009, and December 31, 2016, who were subsequently admitted to a tertiary hospital in Singapore. The Score for Emergency Risk Prediction (SERP) tool was derived using a machine learning framework. To estimate mortality outcomes after emergency admissions, SERP was compared with several triage systems, including Patient Acuity Category Scale, Modified Early Warning Score, National Early Warning Score, Cardiac Arrest Risk Triage, Rapid Acute Physiology Score, and Rapid Emergency Medicine Score. The initial analyses were completed in October 2020, and additional analyses were conducted in May 2021.

Main outcomes and measures

Three SERP scores, namely SERP-2d, SERP-7d, and SERP-30d, were developed using the primary outcomes of interest of 2-, 7-, and 30-day mortality, respectively. Secondary outcomes included 3-day mortality and inpatient mortality. The SERP's predictive power was measured using the area under the curve in the receiver operating characteristic analysis.

Results

The study included 224 666 ED episodes in the model training cohort (mean [SD] patient age, 63.60 [16.90] years; 113 426 [50.5%] female), 56 167 episodes in the validation cohort (mean [SD] patient age, 63.58 [16.87] years; 28 427 [50.6%] female), and 42 676 episodes in the testing cohort (mean [SD] patient age, 64.85 [16.80] years; 21 556 [50.5%] female). The mortality rates in the training cohort were 0.8% at 2 days, 2.2% at 7 days, and 5.9% at 30 days. In the testing cohort, the areas under the curve of SERP-30d were 0.821 (95% CI, 0.796-0.847) for 2-day mortality, 0.826 (95% CI, 0.811-0.841) for 7-day mortality, and 0.823 (95% CI, 0.814-0.832) for 30-day mortality and outperformed several benchmark scores.

Conclusions and relevance

In this retrospective cohort study, SERP had better prediction performance than existing triage scores while maintaining easy implementation and ease of ascertainment in the ED. It has the potential to be widely applied and validated in different circumstances and health care settings.

SUBMITTER: Xie F

PROVIDER: S-EPMC8397930 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundEmergency readmission poses an additional burden on both patients and healthcare systems. Risk stratification is the first step of transitional care interventions targeted at reducing readmission. To accurately predict the short- and intermediate-term risks of readmission and provide information for further temporal risk stratification, we developed and validated an interpretable machine learning risk scoring system.MethodsIn this retrospective study, all emergency admission episodes from January 1st 2009 to December 31st 2016 at a tertiary hospital in Singapore were assessed. The primary outcome was time to emergency readmission within 90 days post discharge. The Score for Emergency ReAdmission Prediction (SERAP) tool was derived via an interpretable machine learning-based system for time-to-event outcomes. SERAP is six-variable survival score, and takes the number of emergency admissions last year, age, history of malignancy, history of renal diseases, serum creatinine level, and serum albumin level during index admission into consideration.FindingsA total of 293,589 ED admission episodes were finally included in the whole cohort. Among them, 203,748 episodes were included in the training cohort, 50,937 episodes in the validation cohort, and 38,904 in the testing cohort. Readmission within 90 days was documented in 80,213 (27.3%) episodes, with a median time to emergency readmission of 22 days (Interquartile range: 8-47). For different time points, the readmission rates observed in the whole cohort were 6.7% at 7 days, 10.6% at 14 days, 13.6% at 21 days, 16.4% at 30 days, and 23.0% at 60 days. In the testing cohort, the SERAP achieved an integrated area under the curve of 0.737 (95% confidence interval: 0.730-0.743). For a specific 30-day readmission prediction, SERAP outperformed the LACE index (Length of stay, Acuity of admission, Charlson comorbidity index, and Emergency department visits in past six months) and the HOSPITAL score (Hemoglobin at discharge, discharge from an Oncology service, Sodium level at discharge, Procedure during the index admission, Index Type of admission, number of Admissions during the last 12 months, and Length of stay). Besides 30-day readmission, SERAP can predict readmission rates at any time point during the 90-day period.InterpretationBetter performance in risk prediction was achieved by the SERAP than other existing scores, and accurate information about time to emergency readmission was generated for further temporal risk stratification and clinical decision-making. In the future, external validation studies are needed to evaluate the SERAP at different settings and assess their real-world performance.FundingThis study was supported by the Singapore National Medical Research Council under the PULSES Center Grant, and Duke-NUS Medical School.

Project description:Background Unlike linear models which are traditionally used to study all-cause mortality, complex machine learning models can capture non-linear interrelations and provide opportunities to identify unexplored risk factors. Explainable artificial intelligence can improve prediction accuracy over linear models and reveal great insights into outcomes like mortality. This paper comprehensively analyzes all-cause mortality by explaining complex machine learning models. Methods We propose the IMPACT framework that uses XAI technique to explain a state-of-the-art tree ensemble mortality prediction model. We apply IMPACT to understand all-cause mortality for 1-, 3-, 5-, and 10-year follow-up times within the NHANES dataset, which contains 47,261 samples and 151 features. Results We show that IMPACT models achieve higher accuracy than linear models and neural networks. Using IMPACT, we identify several overlooked risk factors and interaction effects. Furthermore, we identify relationships between laboratory features and mortality that may suggest adjusting established reference intervals. Finally, we develop highly accurate, efficient and interpretable mortality risk scores that can be used by medical professionals and individuals without medical expertise. We ensure generalizability by performing temporal validation of the mortality risk scores and external validation of important findings with the UK Biobank dataset. Conclusions IMPACT’s unique strength is the explainable prediction, which provides insights into the complex, non-linear relationships between mortality and features, while maintaining high accuracy. Our explainable risk scores could help individuals improve self-awareness of their health status and help clinicians identify patients with high risk. IMPACT takes a consequential step towards bringing contemporary developments in XAI to epidemiology. Qui et al. present a new approach, IMPACT, that uses explainable artificial intelligence to analyze all-cause mortality. IMPACT provides insights into the individualized mortality risk scores, while maintaining high model accuracy and the expressive power to capture complex, non-linear relationships between mortality and individuals’ features.

Project description:BackgroundEmergency departments (ED) are becoming increasingly overwhelmed, increasing poor outcomes. Triage scores aim to optimize the waiting time and prioritize the resource usage. Artificial intelligence (AI) algorithms offer advantages for creating predictive clinical applications.ObjectiveEvaluate a state-of-the-art machine learning model for predicting mortality at the triage level and, by validating this automatic tool, improve the categorization of patients in the ED.DesignAn institutional review board (IRB) approval was granted for this retrospective study. Information of consecutive adult patients (ages 18-100) admitted at the emergency department (ED) of one hospital were retrieved (January 1, 2012-December 31, 2018). Features included the following: demographics, admission date, arrival mode, referral code, chief complaint, previous ED visits, previous hospitalizations, comorbidities, home medications, vital signs, and Emergency Severity Index (ESI). The following outcomes were evaluated: early mortality (up to 2 days post ED registration) and short-term mortality (2-30 days post ED registration). A gradient boosting model was trained on data from years 2012-2017 and examined on data from the final year (2018). The area under the curve (AUC) for mortality prediction was used as an outcome metric. Single-variable analysis was conducted to develop a nine-point triage score for early mortality.Key resultsOverall, 799,522 ED visits were available for analysis. The early and short-term mortality rates were 0.6% and 2.5%, respectively. Models trained on the full set of features yielded an AUC of 0.962 for early mortality and 0.923 for short-term mortality. A model that utilized the nine features with the highest single-variable AUC scores (age, arrival mode, chief complaint, five primary vital signs, and ESI) yielded an AUC of 0.962 for early mortality.ConclusionThe gradient boosting model shows high predictive ability for screening patients at risk of early mortality utilizing data available at the time of triage in the ED.

Project description:ObjectiveTo predict hospital admission at the time of ED triage using patient history in addition to information collected at triage.MethodsThis retrospective study included all adult ED visits between March 2014 and July 2017 from one academic and two community emergency rooms that resulted in either admission or discharge. A total of 972 variables were extracted per patient visit. Samples were randomly partitioned into training (80%), validation (10%), and test (10%) sets. We trained a series of nine binary classifiers using logistic regression (LR), gradient boosting (XGBoost), and deep neural networks (DNN) on three dataset types: one using only triage information, one using only patient history, and one using the full set of variables. Next, we tested the potential benefit of additional training samples by training models on increasing fractions of our data. Lastly, variables of importance were identified using information gain as a metric to create a low-dimensional model.ResultsA total of 560,486 patient visits were included in the study, with an overall admission risk of 29.7%. Models trained on triage information yielded a test AUC of 0.87 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.88) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on patient history yielded an AUC of 0.86 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.87) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on the full set of variables yielded an AUC of 0.91 for LR (95% CI 0.91-0.91), 0.92 for XGBoost (95% CI 0.92-0.93) and 0.92 for DNN (95% CI 0.92-0.92). All algorithms reached maximum performance at 50% of the training set or less. A low-dimensional XGBoost model built on ESI level, outpatient medication counts, demographics, and hospital usage statistics yielded an AUC of 0.91 (95% CI 0.91-0.91).ConclusionMachine learning can robustly predict hospital admission using triage information and patient history. The addition of historical information improves predictive performance significantly compared to using triage information alone, highlighting the need to incorporate these variables into prediction models.

Project description:BackgroundThe number of older adults with a high risk of frailty and severe illness continues to increase. Moreover, physiological change and multiple comorbidities are challenging to triage in geriatrics. Therefore, we aimed to evaluate variables to predict 28-day mortality and develop a screening tool to predict mortality and lifesaving intervention among geriatric patients in the emergency department (ED).MethodsThis study was a retrospective, single-center, observational study at the ED of Ramathibodi Hospital, Bangkok. Patients aged ≥ 65 years who visited the ED between January 2018 and December 2019 were enrolled. In the development cohort, univariable logistic regression was used to identify predictors of 28-day mortality in older patients. A predictive model for mortality and the need for lifesaving intervention was developed by multivariable logistic regression. In addition, the score was validated with internal validation and compared between development and validation set by chi-square.ResultsWe enrolled 1393 patients. In the development cohort, among these 1002 patients, 103 (10.3%) of whom died within 28 days. Malignancy, shock index (SI), systolic blood pressure (SBP) < 100 mmHg, and altered mentation were independent risk factors of 28-day mortality. We developed new screening tools named the S-TRIAGE score, which has the respiratory rate (< 11, > 22 breaths/min), the ratio of pulse oximetric saturation to the fraction of inspired oxygen (< 420, 420-450), SI (> 1, 0.6-0.99), SBP < 100 mmHg, body temperature (< 36, > 37.5 °C), and mental change. The area under a receiver operating characteristic (ROC) curve of the S-TRIAGE score in the validation cohort was 0.826 [95% confidence interval (95%CI) 0.773-0.879] in predicting mortality and lifesaving intervention, and the clinical score classified patients into five groups.ConclusionThis study showed malignancy, hypotension, increased SI, and mental status change were predictive factors for 28-day mortality in older adults in the ED. The screening tool risk score for geriatrics used in this study is potentially a good predictor of mortality and lifesaving intervention in high-risk older patients in the ED.

Project description:BackgroundDevelopment of emergency department (ED) triage systems that accurately differentiate and prioritize critically ill from stable patients remains challenging. We used machine learning models to predict clinical outcomes, and then compared their performance with that of a conventional approach-the Emergency Severity Index (ESI).MethodsUsing National Hospital and Ambulatory Medical Care Survey (NHAMCS) ED data, from 2007 through 2015, we identified all adult patients (aged ≥ 18 years). In the randomly sampled training set (70%), using routinely available triage data as predictors (e.g., demographics, triage vital signs, chief complaints, comorbidities), we developed four machine learning models: Lasso regression, random forest, gradient boosted decision tree, and deep neural network. As the reference model, we constructed a logistic regression model using the five-level ESI data. The clinical outcomes were critical care (admission to intensive care unit or in-hospital death) and hospitalization (direct hospital admission or transfer). In the test set (the remaining 30%), we measured the predictive performance, including area under the receiver-operating-characteristics curve (AUC) and net benefit (decision curves) for each model.ResultsOf 135,470 eligible ED visits, 2.1% had critical care outcome and 16.2% had hospitalization outcome. In the critical care outcome prediction, all four machine learning models outperformed the reference model (e.g., AUC, 0.86 [95%CI 0.85-0.87] in the deep neural network vs 0.74 [95%CI 0.72-0.75] in the reference model), with less under-triaged patients in ESI triage levels 3 to 5 (urgent to non-urgent). Likewise, in the hospitalization outcome prediction, all machine learning models outperformed the reference model (e.g., AUC, 0.82 [95%CI 0.82-0.83] in the deep neural network vs 0.69 [95%CI 0.68-0.69] in the reference model) with less over-triages in ESI triage levels 1 to 3 (immediate to urgent). In the decision curve analysis, all machine learning models consistently achieved a greater net benefit-a larger number of appropriate triages considering a trade-off with over-triages-across the range of clinical thresholds.ConclusionsCompared to the conventional approach, the machine learning models demonstrated a superior performance to predict critical care and hospitalization outcomes. The application of modern machine learning models may enhance clinicians' triage decision making, thereby achieving better clinical care and optimal resource utilization.

Project description:ImportanceWhile machine learning approaches may enhance prediction ability, little is known about their utility in emergency department (ED) triage.ObjectivesTo examine the performance of machine learning approaches to predict clinical outcomes and disposition in children in the ED and to compare their performance with conventional triage approaches.Design, setting, and participantsPrognostic study of ED data from the National Hospital Ambulatory Medical Care Survey from January 1, 2007, through December 31, 2015. A nationally representative sample of 52 037 children aged 18 years or younger who presented to the ED were included. Data analysis was performed in August 2018.Main outcomes and measuresThe outcomes were critical care (admission to an intensive care unit and/or in-hospital death) and hospitalization (direct hospital admission or transfer). In the training set (70% random sample), using routinely available triage data as predictors (eg, demographic characteristics and vital signs), we derived 4 machine learning-based models: lasso regression, random forest, gradient-boosted decision tree, and deep neural network. In the test set (the remaining 30% of the sample), we measured the models' prediction performance by computing C statistics, prospective prediction results, and decision curves. These machine learning models were built for each outcome and compared with the reference model using the conventional triage classification information.ResultsOf 52 037 eligible ED visits by children (median [interquartile range] age, 6 [2-14] years; 24 929 [48.0%] female), 163 (0.3%) had the critical care outcome and 2352 (4.5%) had the hospitalization outcome. For the critical care prediction, all machine learning approaches had higher discriminative ability compared with the reference model, although the difference was not statistically significant (eg, C statistics of 0.85 [95% CI, 0.78-0.92] for the deep neural network vs 0.78 [95% CI, 0.71-0.85] for the reference; P = .16), and lower number of undertriaged critically ill children in the conventional triage levels 3 to 5 (urgent to nonurgent). For the hospitalization prediction, all machine learning approaches had significantly higher discrimination ability (eg, C statistic, 0.80 [95% CI, 0.78-0.81] for the deep neural network vs 0.73 [95% CI, 0.71-0.75] for the reference; P < .001) and fewer overtriaged children who did not require inpatient management in the conventional triage levels 1 to 3 (immediate to urgent). The decision curve analysis demonstrated a greater net benefit of machine learning models over ranges of clinical thresholds.Conclusions and relevanceMachine learning-based triage had better discrimination ability to predict clinical outcomes and disposition, with reduction in undertriaging critically ill children and overtriaging children who are less ill.