Highlights
- •Artificial intelligence (AI) has been used to predict mortality and complications, but not resource use.
- •This AI tool was designed to predict need for mechanical ventilation and intensive care in patients with gunshot injuries.
- •This new tool predicted the need for these resource-intensive health services with high accuracy.
Abstract
Background
Tiered trauma triage systems have resulted in a significant mortality reduction, but
models have remained unchanged. The aim of this study was to develop and test an artificial
intelligence algorithm to predict critical care resource utilization.
Methods
We queried the ACS-TQIP 2017-18 database for truncal gunshot wounds(GSW). An information-aware
deep neural network (DNN-IAD) model was trained to predict ICU admission and need
for mechanical ventilation (MV). Input variables included demographics, comorbidities,
vital signs, and external injuries. The model's performance was assessed using the
area under receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).
Results
For the ICU admission analysis, we included 39,916 patients. For the MV need analysis,
39,591 patients were included. Median (IQR) age was 27 (22,36). AUROC and AUPRC for
predicting ICU need were 84.8 ± 0.5 and 75.4 ± 0.5, and the AUROC and AUPRC for MV
need were 86.8 ± 0.5 and 72.5 ± 0.6.
Conclusions
Our model predicts hospital utilization outcomes in patients with truncal GSW with
high accuracy, allowing early resource mobilization and rapid triage decisions in
hospitals with capacity issues and austere environments.
Graphical abstract
Graphical Abstract
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to The American Journal of SurgeryAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Multiple cause of death data on CDC WONDER.
- A national evaluation of the effect of trauma-center care on mortality.N Engl J Med. 2006; 354: 366-378https://doi.org/10.1056/NEJMsa052049
- Variation in prehospital use and uptake of the national field triage decision scheme.Prehosp Emerg Care. 2013; 17: 135-148https://doi.org/10.3109/10903127.2012.749966
- Planning for the next pandemic: trauma injuries require pre-COVID-19 levels of high-intensity resources.Am Surg. 2022; 88: 1054-1058https://doi.org/10.1177/00031348221087414
- Developing a simple clinical score for predicting mortality and need for ICU in trauma patients.Am Surg. 2019; 85: 733-737https://doi.org/10.1177/000313481908500733
- The Injury Severity Score or the New Injury Severity Score for predicting intensive care unit admission and hospital length of stay?.Injury. 2005; 36: 477-483https://doi.org/10.1016/j.injury.2004.09.039
- What do prehospital trauma scores predict besides mortality?.J Trauma Inj Infect Crit Care. 2011; 71: 754-759https://doi.org/10.1097/TA.0b013e3181fd0dae
- Deep learning and alternative learning strategies for retrospective real-world clinical data.NPJ Digit Med. 2019; 2https://doi.org/10.1038/s41746-019-0122-0
- Development of a field artificial intelligence triage tool: confidence in the prediction of shock, transfusion, and definitive surgical therapy in patients with truncal gunshot wounds.J Trauma Acute Care Surg. 2021; 90: 1054-1060https://doi.org/10.1097/TA.0000000000003155
- Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement.BMC Med. 2015; 13https://doi.org/10.1186/s12916-014-0241-z
- Trauma Quality Improvement Program Participant Use File 2017-2018.2018https://www.facs.org/quality-programs/trauma/quality/national-trauma-data-bank/datasets/Date accessed: April 3, 2022
- Artificial Intelligence for Decision Emulation (Medic-AIDE): FY19 Biomedical Sciences and Technologies Line-Supported Program.2019
- Emergency department triage prediction of clinical outcomes using machine learning models.Crit Care. 2019; 23https://doi.org/10.1186/s13054-019-2351-7
- Building a decision support system for inpatient admission prediction with the manchester triage system and administrative check-in variables.Comput Inf Nurs. 2016; 34: 224-230https://doi.org/10.1097/CIN.0000000000000230
- A simple tool to predict admission at the time of triage.Emerg Med J. 2015; 32: 174-179https://doi.org/10.1136/emermed-2013-203200
- Predicting hospital admissions at emergency department triage using routine administrative data.Acad Emerg Med. 2011; 18: 844-850https://doi.org/10.1111/j.1553-2712.2011.01125.x
- Abnormal vital signs are strong predictors for intensive care unit admission and in-hospital mortality in adults triaged in the emergency department - a prospective cohort study.Scand J Trauma Resuscitation Emerg Med. 2012; 20https://doi.org/10.1186/1757-7241-20-28
- Predicting intensive care unit admission among patients presenting to the emergency department using machine learning and natural language processing.PLoS One. 2020; 15https://doi.org/10.1371/journal.pone.0229331
- Machine learning methods to predict mechanical ventilation and mortality in patients with COVID-19.PLoS One. 2021; 16https://doi.org/10.1371/journal.pone.0249285
- Surgical risk is not linear: derivation and validation of a novel, user-friendly, and machine-learning-based predictive OpTimal trees in emergency surgery risk (POTTER) calculator.Ann Surg. 2018; 268: 574-583https://doi.org/10.1097/SLA.0000000000002956
- Machine learning and prediction in medicine — beyond the peak of inflated expectations.N Engl J Med. 2017; 376: 2507-2509https://doi.org/10.1056/nejmp1702071
- Applications of artificial neural networks in health care organizational decision-making: a scoping review.PLoS One. 2019; 14https://doi.org/10.1371/journal.pone.0212356
Article info
Publication history
Published online: March 17, 2023
Accepted:
March 16,
2023
Received in revised form:
March 10,
2023
Received:
January 25,
2023
Publication stage
In Press Journal Pre-ProofFootnotes
☆Presented at the American College of Surgeons Clinical Congress 2021.
Identification
Copyright
© 2023 Elsevier Inc. All rights reserved.
