Deep-Learning Approaches to Identify Critically Ill Patients at Emergency Department Triage Using Limited Information
Joshua W Joseph,
Evan L Leventhal,
Anne V Grossestreuer,
Matthew L Wong,
Loren J Joseph,
Larry A Nathanson,
Michael W Donnino,
Leon D Sanchez
Posted 06 May 2020
medRxiv DOI: 10.1101/2020.05.02.20089052
Posted 06 May 2020
Importance Triage quickly identifies critically ill patients, helping to facilitate timely interventions. Many emergency departments use the emergency severity index (ESI) or abnormal vital sign thresholds to identify critically ill patients. However, both rely on fixed thresholds, and false activations detract from efficient care. Prior research suggests that machine-learning approaches may improve triage accuracy, but have relied on information that is often unavailable during the triage process. Objective We examined whether deep-learning approaches could identify critically ill patients using data immediately available at triage with greater discriminative power than ESI or abnormal vital sign thresholds. Design Retrospective, cross-sectional study. Setting An urban tertiary care hospital in the Northeastern United States. Participants Adult patients presenting to the emergency department from 1/1/2012 - 1/1/2020 were included. Deidentified triage information included structured data (age, sex, initial vital signs, ESI score, and clinical trigger activation due to abnormal vital signs), and textual data (chief complaint) with critical illness (defined as mortality or ICU admission within 24 hours) as the outcome. Interventions Three progressively complex deep-learning models were trained (logistic regression on structured data, neural network on structured data, and neural network on structured and textual data), and applied to triage information from all patients. Main Outcomes and Measures The primary outcome was the accuracy of the model for predicting whether patients were critically ill using area under the receiver-operator curve (AUC), as compared to ESI, utilizing a 10-fold cross-validation. Results 445,925 patients were included, with 60,901 (13.7%) critically ill. Vital sign thresholds identified critically ill patients with AUC 0.521 (95% CI 0.519 -- 0.522), and ESI less than 3 demonstrated AUC 0.672 (95% CI 0.671 -- 0.674), logistic regression classified patients with AUC 0.803 (95% CI 0.802 -- 0.804), neural network with structured data with 0.811 (95% CI 0.807 - 0.815), and the neural network model with textual data with AUC 0.851 (95% CI 0.849 -- 0.852). Conclusions and Relevance Deep-learning techniques represent a promising method of enhancing the triage process, even when working from limited information. Further research is needed to determine if improved predictions can be translated into meaningful clinical and operational benefits.
- Downloaded 289 times
- Download rankings, all-time:
- Site-wide: 100,371
- In emergency medicine: 99
- Year to date:
- Site-wide: 90,852
- Since beginning of last month:
- Site-wide: None
Downloads over time
Distribution of downloads per paper, site-wide
- 27 Nov 2020: The website and API now include results pulled from medRxiv as well as bioRxiv.
- 18 Dec 2019: We're pleased to announce PanLingua, a new tool that enables you to search for machine-translated bioRxiv preprints using more than 100 different languages.
- 21 May 2019: PLOS Biology has published a community page about Rxivist.org and its design.
- 10 May 2019: The paper analyzing the Rxivist dataset has been published at eLife.
- 1 Mar 2019: We now have summary statistics about bioRxiv downloads and submissions.
- 8 Feb 2019: Data from Altmetric is now available on the Rxivist details page for every preprint. Look for the "donut" under the download metrics.
- 30 Jan 2019: preLights has featured the Rxivist preprint and written about our findings.
- 22 Jan 2019: Nature just published an article about Rxivist and our data.
- 13 Jan 2019: The Rxivist preprint is live!