TY - JOUR
T1 - A Gradient Boosting Machine Learning Model for Predicting Early Mortality in the Emergency Department Triage
T2 - Devising a Nine-Point Triage Score
AU - Klug, Maximiliano
AU - Barash, Yiftach
AU - Bechler, Sigalit
AU - Resheff, Yehezkel S.
AU - Tron, Talia
AU - Ironi, Avi
AU - Soffer, Shelly
AU - Zimlichman, Eyal
AU - Klang, Eyal
N1 - Publisher Copyright: © 2019, Society of General Internal Medicine.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Background: Emergency 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. Objective: Evaluate 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. Design: An 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 Results: Overall, 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. Conclusion: The 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.
AB - Background: Emergency 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. Objective: Evaluate 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. Design: An 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 Results: Overall, 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. Conclusion: The 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.
KW - early mortality
KW - emergency department
KW - gradient boosting
KW - machine learning
KW - triage
UR - http://www.scopus.com/inward/record.url?scp=85074832493&partnerID=8YFLogxK
U2 - https://doi.org/10.1007/s11606-019-05512-7
DO - https://doi.org/10.1007/s11606-019-05512-7
M3 - مقالة
C2 - 31677104
SN - 0884-8734
VL - 35
SP - 220
EP - 227
JO - Journal of General Internal Medicine
JF - Journal of General Internal Medicine
IS - 1
ER -