1
|
Xu Y, Malik N, Chernbumroong S, Vassallo J, Keene D, Foster M, Lord J, Belli A, Hodgetts T, Bowley D, Gkoutos G. Triage in major incidents: development and external validation of novel machine learning-derived primary and secondary triage tools. Emerg Med J 2024; 41:176-183. [PMID: 37751994 PMCID: PMC10894820 DOI: 10.1136/emermed-2022-212440] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2022] [Accepted: 08/12/2023] [Indexed: 10/03/2023]
Abstract
BACKGROUND Major incidents (MIs) are an important cause of death and disability. Triage tools are crucial to identifying priority 1 (P1) patients-those needing time-critical, life-saving interventions. Existing expert opinion-derived tools have limited evidence supporting their use. This study employs machine learning (ML) to develop and validate models for novel primary and secondary triage tools. METHODS Adults (16+ years) from the UK Trauma Audit and Research Network (TARN) registry (January 2008-December 2017) served as surrogates for MI victims, with P1 patients identified using predefined criteria. The TARN database was split chronologically into model training and testing (70:30) datasets. Input variables included physiological parameters, age, mechanism and anatomical location of injury. Random forest, extreme gradient boosted tree, logistic regression and decision tree models were trained to predict P1 status, and compared with existing tools (Battlefield Casualty Drills (BCD) Triage Sieve, CareFlight, Modified Physiological Triage Tool, MPTT-24, MSTART, National Ambulance Resilience Unit Triage Sieve and RAMP). Primary and secondary candidate models were selected; the latter was externally validated on patients from the UK military's Joint Theatre Trauma Registry (JTTR). RESULTS Models were internally tested in 57 979 TARN patients. The best existing tool was the BCD Triage Sieve (sensitivity 68.2%, area under the receiver operating curve (AUC) 0.688). Inability to breathe spontaneously, presence of chest injury and mental status were most predictive of P1 status. A decision tree model including these three variables exhibited the best test characteristics (sensitivity 73.0%, AUC 0.782), forming the candidate primary tool. The proposed secondary tool (sensitivity 77.9%, AUC 0.817), applicable via a portable device, includes a fourth variable (injury mechanism). This performed favourably on external validation (sensitivity of 97.6%, AUC 0.778) in 5956 JTTR patients. CONCLUSION Novel triage tools developed using ML outperform existing tools in a nationally representative trauma population. The proposed primary tool requires external validation prior to consideration for practical use. The secondary tool demonstrates good external validity and may be used to support decision-making by healthcare workers responding to MIs.
Collapse
Affiliation(s)
- Yuanwei Xu
- Centre for Computational Biology, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK
- Health Data Science Centre, University of Birmingham, Birmingham B15 2TT, UK
| | - Nabeela Malik
- NIHR Surgical Reconstruction Microbiology Research Centre, Edgbaston, UK
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK
- Academic Department of Military Surgery & Trauma, Royal Centre for Defence Medicine, Mindelsohn Way, Edgbaston, Birmingham B152WB, UK
| | - Saisakul Chernbumroong
- Centre for Computational Biology, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK
- NIHR Surgical Reconstruction Microbiology Research Centre, Edgbaston, UK
| | - James Vassallo
- Emergency Department, Derriford Hospital, Plymouth, UK
- Academic Department of Military Emergency Medicine, Royal Centre for Defence Medicine, Mindelsohn Way, Edgbaston, Birmingham B15 2WB, UK
| | - Damian Keene
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- Academic Department of Military Surgery & Trauma, Royal Centre for Defence Medicine, Mindelsohn Way, Edgbaston, Birmingham B152WB, UK
| | - Mark Foster
- NIHR Surgical Reconstruction Microbiology Research Centre, Edgbaston, UK
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- Academic Department of Military Surgery & Trauma, Royal Centre for Defence Medicine, Mindelsohn Way, Edgbaston, Birmingham B152WB, UK
| | - Janet Lord
- NIHR Surgical Reconstruction Microbiology Research Centre, Edgbaston, UK
- Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK
| | - Antonio Belli
- NIHR Surgical Reconstruction Microbiology Research Centre, Edgbaston, UK
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | | | - Douglas Bowley
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- Academic Department of Military Surgery & Trauma, Royal Centre for Defence Medicine, Mindelsohn Way, Edgbaston, Birmingham B152WB, UK
| | - George Gkoutos
- Centre for Computational Biology, Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK
- Health Data Science Centre, University of Birmingham, Birmingham B15 2TT, UK
- NIHR Surgical Reconstruction Microbiology Research Centre, Edgbaston, UK
- Institute of Translational Medicine, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- MRC Health Data Research UK (HDR UK), Birmingham, UK
| |
Collapse
|
2
|
El Tawil C, Bergeron A, Khalil E. A Scoping Review of Pediatric Mass-Casualty Incident Triage Algorithms. Disaster Med Public Health Prep 2023; 17:e317. [PMID: 36789661 DOI: 10.1017/dmp.2022.287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/16/2023]
Abstract
OBJECTIVE For the pediatric population, there is no consensus on which triage system to use for mass-casualty incidents (MCI). A scoping review was conducted to identify the most accurate triage system for pediatric patients in MCIs. METHODS MEDLINE (NLM, Bethesda, MA, USA), Embase (Elsevier Inc., Amsterdam, Netherlands), CINAHL (EBSCO Information Services, Ipswitch, MA, USA), and The Cochrane CENTRAL Register of Controlled Trials (John Wiley & Sons, Hoboken, NJ, USA), as well as Scopus (Elsevier Inc., Amsterdam, Netherlands), Global Health (Centre for Agriculture and Bioscience International, Wallingford, UK), Global Health Archive (Centre for Agriculture and Bioscience International, Wallingford, UK), and Global Index Medicus (World Health Organization, Geneva, Switzerland) were searched for relevant studies that were divided into 3 categories: accuracy of a single system, comparison of 2 or more primary triage system and comparison of secondary triage systems. Grey literature was also searched. RESULTS 996 studies were identified from which 18 studies were included. Systems studied were found to have poor inter-rater reliability, had a low level of agreement between providers, had missed critically ill patients or were not externally validated. 11 studies compared pediatric MCI triage algorithms using different strategies and the most accurate algorithm was not identified. A recently developed secondary triage system, specifically for pediatric patients, was found to perform better than the comparison triage system. CONCLUSION Although some algorithms performed better than others, no primary triage algorithm was accurate enough for the pediatric population. However, only 1 secondary triage algorithm was found to be superior to the others.
Collapse
Affiliation(s)
- Chady El Tawil
- Division of Pediatric Emergency Medicine, Montreal Children's Hospital of the McGill University Health Centre, Montreal, Quebec, Canada
| | - Amy Bergeron
- McGill University Health Centre Medical Libraries, Montreal, Quebec, Canada
| | - Elene Khalil
- Division of Pediatric Emergency Medicine, Montreal Children's Hospital of the McGill University Health Centre, Montreal, Quebec, Canada
| |
Collapse
|
3
|
Lu J, Wang X, Chen L, Sun X, Li R, Zhong W, Fu Y, Yang L, Liu W, Han W. Unmanned aerial vehicle based intelligent triage system in mass-casualty incidents using 5G and artificial intelligence. World J Emerg Med 2023; 14:273-279. [PMID: 37425090 PMCID: PMC10323497 DOI: 10.5847/wjem.j.1920-8642.2023.066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2022] [Accepted: 03/02/2023] [Indexed: 07/11/2023] Open
Abstract
BACKGROUND Rapid on-site triage is critical after mass-casualty incidents (MCIs) and other mass injury events. Unmanned aerial vehicles (UAVs) have been used in MCIs to search and rescue wounded individuals, but they mainly depend on the UAV operator's experience. We used UAVs and artificial intelligence (AI) to provide a new technique for the triage of MCIs and more efficient solutions for emergency rescue. METHODS This was a preliminary experimental study. We developed an intelligent triage system based on two AI algorithms, namely OpenPose and YOLO. Volunteers were recruited to simulate the MCI scene and triage, combined with UAV and Fifth Generation (5G) Mobile Communication Technology real-time transmission technique, to achieve triage in the simulated MCI scene. RESULTS Seven postures were designed and recognized to achieve brief but meaningful triage in MCIs. Eight volunteers participated in the MCI simulation scenario. The results of simulation scenarios showed that the proposed method was feasible in tasks of triage for MCIs. CONCLUSION The proposed technique may provide an alternative technique for the triage of MCIs and is an innovative method in emergency rescue.
Collapse
Affiliation(s)
- Jiafa Lu
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
| | - Xin Wang
- Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
| | - Linghao Chen
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China
| | - Xuedong Sun
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
| | - Rui Li
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
| | - Wanjing Zhong
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
| | - Yajing Fu
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
| | - Le Yang
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
| | - Weixiang Liu
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen 518060, China
| | - Wei Han
- Emergency Department of Shenzhen University General Hospital, Shenzhen 518055, China
- Tianjin University, Tianjin 300072, China
| |
Collapse
|
4
|
Vassallo J, Moran CG, Cowburn P, Smith J. New NHS Prehospital Major Incident Triage Tool: from MIMMS to MITT. Emerg Med J 2022; 39:800-802. [PMID: 36244685 PMCID: PMC9613863 DOI: 10.1136/emermed-2022-212569] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2022] [Accepted: 08/15/2022] [Indexed: 11/25/2022]
Abstract
Triage is a key principle in the effective management of major incidents and is the process by which patients are prioritised on the basis of their clinical acuity. However, work published over the last decade has demonstrated that existing methods of triage perform poorly when trying to identify patients in need of life-saving interventions. As a result, a review of major incident triage was initiated by NHS England with the remit to determine the optimum way in which to triage patients of all ages in a major incident for the UK. This article describes the output from this review, the changes being undertaken to UK major incident triage and the introduction of the new NHS Major Incident Triage Tool from the Spring of 2023.
Collapse
Affiliation(s)
- James Vassallo
- Academic Department of Military Emergency Medicine, Royal Centre for Defence Medicine, Birmingham, UK
| | - Chris G Moran
- Department of Orthopaedic Surgery, Nottingham University Hospitals NHS Trust, Nottingham, UK
| | - Philip Cowburn
- Emergency Department, Bristol Royal Infirmary, Bristol, UK
| | - Jason Smith
- Academic Department of Military Emergency Medicine, Royal Centre for Defence Medicine, Birmingham, UK
- Emergency Department, University Hospitals Plymouth NHS Trust, Plymouth, UK
| |
Collapse
|
5
|
METASTART: A Systematic Review and Meta-Analysis of the Diagnostic Accuracy of the Simple Triage and Rapid Treatment (START) Algorithm for Disaster Triage. Prehosp Disaster Med 2021; 37:106-116. [PMID: 34915954 DOI: 10.1017/s1049023x2100131x] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Abstract
INTRODUCTION The goal of disaster triage at both the prehospital and in-hospital level is to maximize resources and optimize patient outcomes. Of the disaster-specific triage methods developed to guide health care providers, the Simple Triage and Rapid Treatment (START) algorithm has become the most popular system world-wide. Despite its appeal and global application, the accuracy and effectiveness of the START protocol is not well-known. OBJECTIVES The purpose of this meta-analysis was two-fold: (1) to estimate overall accuracy, under-triage, and over-triage of the START method when used by providers across a variety of backgrounds; and (2) to obtain specific accuracy for each of the four START categories: red, yellow, green, and black. METHODS A systematic review and meta-analysis was conducted that searched Medline (OVID), Embase (OVID), Global Health (OVID), CINAHL (EBSCO), Compendex (Engineering Village), SCOPUS, ProQuest Dissertations and Theses Global, Cochrane Library, and PROSPERO. The results were expanded by hand searching of journals, reference lists, and the grey literature. The search was executed in March 2020. The review considered the participants, interventions, context, and outcome (PICO) framework and followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Accuracy outcomes are presented as means with 95% confidence intervals (CI) as calculated using the binomial method. Pooled meta-analyses of accuracy outcomes using fixed and random effects models were calculated and the heterogeneity was assessed using the Q statistic. RESULTS Thirty-two studies were included in the review, most of which utilized a non-randomized study design (84%). Proportion of victims correctly triaged using START ranged from 0.27 to 0.99 with an overall triage accuracy of 0.73 (95% CI, 0.67 to 0.78). Proportion of over-triage was 0.14 (95% CI, 0.11 to 0.17) while the proportion of under-triage was 0.10 (95% CI, 0.072 to 0.14). There was significant heterogeneity of the studies for all outcomes (P < .0001). CONCLUSION This meta-analysis suggests that START is not accurate enough to serve as a reliable disaster triage tool. Although the accuracy of START may be similar to other models of disaster triage, development of a more accurate triage method should be urgently pursued.
Collapse
|