Back to Search Start Over

A Pilot Machine Learning Study Using Trauma Admission Data to Identify Risk for High Length of Stay.

Authors :
Stonko DP
Weller JH
Gonzalez Salazar AJ
Abdou H
Edwards J
Hinson J
Levin S
Byrne JP
Sakran JV
Hicks CW
Haut ER
Morrison JJ
Kent AJ
Source :
Surgical innovation [Surg Innov] 2023 Jun; Vol. 30 (3), pp. 356-365. Date of Electronic Publication: 2022 Nov 17.
Publication Year :
2023

Abstract

Introduction: Trauma patients have diverse resource needs due to variable mechanisms and injury patterns. The aim of this study was to build a tool that uses only data available at time of admission to predict prolonged hospital length of stay (LOS).<br />Methods: Data was collected from the trauma registry at an urban level one adult trauma center and included patients from 1/1/2014 to 3/31/2019. Trauma patients with one or fewer days LOS were excluded. Single layer and deep artificial neural networks were trained to identify patients in the top quartile of LOS and optimized on area under the receiver operator characteristic curve (AUROC). The predictive performance of the model was assessed on a separate test set using binary classification measures of accuracy, precision, and error.<br />Results: 2953 admitted trauma patients with more than one-day LOS were included in this study. They were 70% male, 60% white, and averaged 47 years-old (SD: 21). 28% were penetrating trauma. Median length of stay was 5 days (IQR 3-9). For prediction of prolonged LOS, the deep neural network achieved an AUROC of 0.80 (95% CI: 0.786-0.814) specificity was 0.95, sensitivity was 0.32, with an overall accuracy of 0.79.<br />Conclusion: Machine learning can predict, with excellent specificity, trauma patients who will have prolonged length of stay with only physiologic and demographic data available at the time of admission. These patients may benefit from additional resources with respect to disposition planning at the time of admission.

Details

Language :
English
ISSN :
1553-3514
Volume :
30
Issue :
3
Database :
MEDLINE
Journal :
Surgical innovation
Publication Type :
Academic Journal
Accession number :
36397721
Full Text :
https://doi.org/10.1177/15533506221139965