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.
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.
Entities:
Keywords:
early mortality; emergency department; gradient boosting; machine learning; triage
Authors: Tadahiro Goto; Carlos A Camargo; Mohammad Kamal Faridi; Brian J Yun; Kohei Hasegawa Journal: Am J Emerg Med Date: 2018-06-28 Impact factor: 2.469
Authors: Michael Christ; Florian Grossmann; Daniela Winter; Roland Bingisser; Elke Platz Journal: Dtsch Arztebl Int Date: 2010-12-17 Impact factor: 5.594
Authors: Rajiv Arya; Grant Wei; Jonathan V McCoy; Jody Crane; Pamela Ohman-Strickland; Robert M Eisenstein Journal: Acad Emerg Med Date: 2013-11 Impact factor: 3.451
Authors: Benjamin C Sun; Renee Y Hsia; Robert E Weiss; David Zingmond; Li-Jung Liang; Weijuan Han; Heather McCreath; Steven M Asch Journal: Ann Emerg Med Date: 2012-12-06 Impact factor: 5.721
Authors: Scott Levin; Matthew Toerper; Eric Hamrock; Jeremiah S Hinson; Sean Barnes; Heather Gardner; Andrea Dugas; Bob Linton; Tom Kirsch; Gabor Kelen Journal: Ann Emerg Med Date: 2017-09-06 Impact factor: 5.721
Authors: Nasim Farrohknia; Maaret Castrén; Anna Ehrenberg; Lars Lind; Sven Oredsson; Håkan Jonsson; Kjell Asplund; Katarina E Göransson Journal: Scand J Trauma Resusc Emerg Med Date: 2011-06-30 Impact factor: 2.953
Authors: William P T M van Doorn; Patricia M Stassen; Hella F Borggreve; Maaike J Schalkwijk; Judith Stoffers; Otto Bekers; Steven J R Meex Journal: PLoS One Date: 2021-01-19 Impact factor: 3.240
Authors: Yu-Hsin Chang; Hong-Mo Shih; Jia-En Wu; Fen-Wei Huang; Wei-Kung Chen; Dar-Min Chen; Yu-Ting Chung; Charles C N Wang Journal: BMC Emerg Med Date: 2022-05-20
Authors: Eyal Klang; Benjamin R Kummer; Neha S Dangayach; Amy Zhong; M Arash Kia; Prem Timsina; Ian Cossentino; Anthony B Costa; Matthew A Levin; Eric K Oermann Journal: Sci Rep Date: 2021-01-14 Impact factor: 4.379
Authors: Amin Naemi; Thomas Schmidt; Marjan Mansourvar; Mohammad Naghavi-Behzad; Ali Ebrahimi; Uffe Kock Wiil Journal: BMJ Open Date: 2021-11-02 Impact factor: 2.692