Triage in major incidents: development and external validation of novel machine learning-derived primary and secondary triage tools.

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.

Paediatric major incident triage: UK military tool offers best performance in predicting the need for time-critical major surgical and resuscitative intervention.

BACKGROUND: Children are frequently injured during major incidents (MI), including terrorist attacks, conflict and natural disasters. Triage facilitates healthcare resource allocation in order to maximise overall survival. A critical function of MI triage tools is to identify patients needing time-critical major resuscitative and surgical intervention (Priority 1 (P1) status). This study compares the performance of 11 MI triage tools in predicting P1 status in children from the UK Trauma Audit and Research Network (TARN) registry. METHODS: Patients aged <16 years within TARN (January 2008-December 2017) were included. 11 triage tools were applied to patients' first recorded pre-hospital physiology. Patients were retrospectively assigned triage categories (P1, P2, P3, Expectant or Dead) using predefined intervention-based criteria. Tools' performance in <16s were evaluated within four-yearly age subgroups, comparing tool-predicted and intervention-based priority status. FINDINGS: Amongst 4962 patients, mortality was 1.1% (n = 53); median Injury Severity Score (ISS) was 9 (IQR 9-16). Blunt injuries predominated (94.4%). 1343 (27.1%) met intervention-based criteria for P1, exhibiting greater intensive care requirement (60.2% vs. 8.5%, p < 0.01) and ISS (median 17 vs 9, p < 0.01) compared with P2 patients. The Battlefield Casualty Drills (BCD) Triage Sieve had greatest sensitivity (75.7%) in predicting P1 status in children <16 years, demonstrating a 38.4-49.8% improvement across all subgroups of children <12 years compared with the UK's current Paediatric Triage Tape (PTT). JumpSTART demonstrated low sensitivity in predicting P1 status in 4 to 8 year olds (35.5%) and 0 to 4 year olds (28.5%), and was outperformed by its adult counterpart START (60.6% and 59.6%). INTERPRETATION: The BCD Triage Sieve had greatest sensitivity in predicting P1 status in this paediatric trauma registry population: we recommend it replaces the PTT in UK practice. Users of JumpSTART may consider alternative tools. We recommend Lerner's triage category definitions when conducting MI evaluations.

Comparative analysis of major incident triage tools in children: a UK population-based analysis.

INTRODUCTION: Triage is a key principle in the effective management of major incidents. There is currently a paucity of evidence to guide the triage of children. The aim of this study was to perform a comparative analysis of nine adult and paediatric triage tools, including the novel 'Sheffield Paediatric Triage Tool' (SPTT), assessing their ability in identifying patients needing life-saving interventions (LSIs). METHODS: A 10-year (2008-2017) retrospective database review of the Trauma Audit Research Network (TARN) Database for paediatric patients (<16 years) was performed. Primary outcome was identification of patients receiving one or more LSIs from a previously defined list. Secondary outcomes included mortality and prediction of Injury Severity Score (ISS) >15. Primary analysis was conducted on patients with complete prehospital physiological data with planned secondary analyses using first recorded data. Performance characteristics were evaluated using sensitivity, specificity, undertriage and overtriage. RESULTS: 15 133 patients met TARN inclusion criteria. 4962 (32.8%) had complete prehospital physiological data and 8255 (54.5%) had complete first recorded physiological data. The majority of patients were male (69.5%), with a median age of 11.9 years. The overwhelming majority of patients (95.4%) sustained blunt trauma, yielding a median ISS of 9 and overall, 875 patients (17.6%) received at least one LSI. The SPTT demonstrated the greatest sensitivity of all triage tools at identifying need for LSI (92.2%) but was associated with the highest rate of overtriage (75.0%). Both the Paediatric Triage Tape (sensitivity 34.1%) and JumpSTART (sensitivity 45.0%) performed less well at identifying LSI. By contrast, the adult Modified Physiological Triage Tool-24 (MPTT-24) triage tool had the second highest sensitivity (80.8%) with tolerable rates of overtriage (70.2%). CONCLUSION: The SPTT and MPTT-24 outperform existing paediatric triage tools at identifying those patients requiring LSIs. This may necessitate a change in recommended practice. Further work is needed to determine the optimum method of paediatric major incident triage, but consideration should be given to simplifying major incident triage by the use of one generic tool (the MPTT-24) for adults and children.

The BCD Triage Sieve outperforms all existing major incident triage tools: Comparative analysis using the UK national trauma registry population.

BACKGROUND: Natural disasters, conflict, and terrorism are major global causes of death and disability. Central to the healthcare response is triage, vital to ensure the right care is provided to the right patient at the right time. The ideal triage tool has high sensitivity for the highest priority (P1) patients with acceptably low over-triage. This study compared the performance of major incident triage tools in predicting P1 casualty status in adults in the prospective UK Trauma Audit and Research Network (TARN) registry. METHODS: TARN patients aged 16+ years (January 2008-December 2017) were included. Ten existing triage tools were applied using patients' first recorded pre-hospital physiology. Patients were subsequently assigned triage categories (P1, P2, P3, Expectant or Dead) based on pre-defined, intervention-based criteria. Tool performance was assessed by comparing tool-predicted and intervention-based priority status. FINDINGS: 195,709 patients were included; mortality was 7·0% (n=13,601); median Injury Severity Score (ISS) was 9 (IQR 9-17); 97·1% sustained blunt injuries. 22,144 (11·3%) patients fulfilled intervention-based criteria for P1 status, exhibiting higher mortality (12·8% vs. 5·0%, p<0.001), increased intensive care requirement (52·4% vs 5·0%, p<0.001), and more severe injuries (median ISS 21 vs 9, p<0.001) compared with P2 patients.In 16-64 year olds, the highest performing tool was the Battlefield Casualty Drills (BCD) Triage Sieve (Prediction of P1 status: 70·4% sensitivity, over-triage 70·9%, area under the receiver operating curve (AUC) 0·068 [95%CI 0·676-0·684]). The UK National Ambulance Resilience Unit (NARU) Triage Sieve had sensitivity of 44·9%; over-triage 56·4%; AUC 0·666 (95%CI 0·662-0·670). All tools performed poorly amongst the elderly (65+ years). INTERPRETATION: The BCD Triage Sieve performed best in this nationally representative population; we recommend it supersede the NARU Triage Sieve as the UK primary major incident triage tool. Validated triage category definitions are recommended for appraising future major incidents. FUNDING: This study is funded by the National Institute for Health Research (NIHR) Surgical Reconstruction and Microbiology Research Centre. GVG also acknowledges support from the MRC Heath Data Research UK (HDRUK/CFC/01). The views expressed are those of the authors and not necessarily those of the NIHR, the Department of Health and Social Care, or the Ministry of Defence.

Pre-hospital blood transfusion - an ESA survey of European practice.

BACKGROUND: Blood products are a lifesaving commodity in the treatment of major trauma. Although there is little evidence for use of pre-hospital blood products (PHBP) in seriously injured patients, an increasing number of emergency medical services have started using PHBP for treatment of major haemorrhage. The primary aim of this survey was to establish the degree of prehospital blood product use throughout Europe and discover main indications. The secondary aim was to evaluate opinions about PHBP and also the experience and the personal views of its users. METHODS: The subcommittee for Critical Emergency Medicine of the European Society of Anaesthesiology (ESA) held an online survey of European Helicopter Emergency Services (HEMS) and all French Services d'Aide Médicale Urgente (SAMU) regions. It contained 13 questions both open and multiple-choice about the frequency transfusions are carried out, the PHBP used and the perceived benefit. The survey was distributed to the corresponding HEMS leads in 14 European countries. RESULTS: In total there were 172 valid responses; overall 48% of all respondents have prehospital access to packed red cells, 22% to fresh plasma and 14% use lyophilised plasma. Besides blood product administration, 94% of all services use tranexamic acid. Sixty five percent of all replies came from French and from German services (37 and 28% respectively). PHBP were mainly used for trauma related emergencies. France has the highest uptake of use of blood products at 89%, whereas the rate in Germany was far lower at 6%. Fifty five percent of the service leads felt that PHBP are beneficial, and even lifesaving in individual cases despite being needed infrequently. CONCLUSIONS: We found remarkable dissimilarities in practice between the different European countries. Even if there is not an absolute consensus amongst providers on the benefit of PHBP, the majority feel they are beneficial. The difference in practice is possibly related to the perceived lack of evidence on prehospital blood transfusion. We suggest to include the use of PHBP in trauma registries in order to consolidate the existing evidence.

Primary Blast Lung Injury: The UK Military Experience.

INTRODUCTION: Primary blast lung injury occurs when an explosive shock wave passes through the thorax and transits through tissues of varying densities. It requires close proximity to an explosion and presents quick with respiratory distress in survivors. MATERIALS AND METHODS: The Joint Theatre Trauma Registry and the Defence Statistics (Health) Database were interrogated for casualties injured as a result of an explosion during the conflict in Afghanistan. The case notes and imaging of casualties meeting the criteria for diagnosis were reviewed. Demographic and clinical data on casualties with primary blast lung injury were analyzed. RESULTS: 848 blast-exposed casualties survived to discharge from intensive care, and 238 blast-exposed casualties were killed in action. Following exclusions, 111 case notes and all postmortem reports were reviewed in detail. About, 25 casualties had isolated primary blast lung injury (2.9% of casualties surviving to discharge from intensive care) and 31 nonsurvivors (13% of nonsurvivors) had the disease documented at postmortem. Severe cases of primary blast lung injury required an estimated average of 4.5 days of conventional mechanical ventilation. CONCLUSIONS: 8.1% of blast exposed casualties suffered primary blast lung injury. It was a less severe disease than other nontraumatic forms of acute lung injury and did not cause deaths once a casualty had reached a combat support hospital. It was well managed with a relatively brief period of conventional mechanical ventilation.

Marauding terrorist attack (MTA): prehospital considerations.

Terrorist attacks are increasing each year as are the number of deaths associated with them. Recent incidents have seen a shift in tactics with the use of multiple terrorists across multiple locations with firearms or knives, referred to as the marauding terrorist attack. These methods are becoming more prevalent alongside the use of vehicles deliberately aimed at pedestrians. Management of these incidents can be challenging. Not only it involves a large number of casualties but also the management of a dynamic scene in terms of both location and threat from attack. In order to improve response, and potentially outcomes, a system or response needs to have preplanned and practised procedures in place. This article reviews major incident management for those unfamiliar with current prehospital practice and details some of the findings from recent marauding terrorist firearm attacks, in particular the evolution of newer scene management tools such as 3 Echo and THREAT. It highlights the importance of haemorrhage control and the public initiatives focusing on actions during a terrorist incident.

Died of wounds: a mortality review.

OBJECTIVES: Combat casualty care is a complex system involving multiple clinicians, medical interventions and casualty transfers. Improving the performance of this system requires examination of potential weaknesses. This study reviewed the cause and timing of death of casualties deemed to have died from their injuries after arriving at a medical treatment facility during the recent conflicts in Iraq and Afghanistan, in order to identify potential areas for improving outcomes. METHODS: This was a retrospective review of all casualties who reached medical treatment facilities alive, but subsequently died from injuries sustained during combat operations in Afghanistan and Iraq. It included all deaths from start to completion of combat operations. The UK military joint theatre trauma registry was used to identify cases, and further data were collected from clinical notes, postmortem records and coroner's reports. RESULTS: There were 71 combat-related fatalities who survived to a medical treatment facility; 17 (24%) in Iraq and 54 (76%) in Afghanistan. Thirty eight (54%) died within the first 24 h. Thirty-three (47%) casualties died from isolated head injuries, a further 13 (18%) had unsurvivable head injuries but not in isolation. Haemorrhage following severe lower limb trauma, often in conjunction with abdominal and pelvic injuries, was the cause of a further 15 (21%) deaths. CONCLUSIONS: Severe head injury was the most common cause of death. Irrespective of available medical treatment, none of this group had salvageable injuries. Future emphasis should be placed in preventative strategies to protect the head against battlefield trauma.

Rotational thromboelastometry-guided trauma resuscitation.

PURPOSE OF REVIEW: Haemorrhage from major trauma is a significant cause of death worldwide. The UK Defence Medical Service (UK-DMS) has had significant experience in managing severely injured and shocked trauma casualties over the last decade. This has led to the integration of rotational thromboelastometry (ROTEM) into damage control resuscitation delivered at Camp Bastion Field Hospital in Afghanistan. This review aims to describe the rationale for its use and how its use has evolved by UK-DMS. RECENT FINDINGS: Although there is reasonable evidence showing its benefit in cardiac and liver surgery, evidence for its use in trauma is limited. More recent studies and meta-analyses have demonstrated a reduced rate of transfusion and blood loss, but no benefit on mortality. Despite this, there is a growing body of opinion supporting ROTEM use in trauma with European guidelines supporting its use where available. Recent UK-DMS experience has shown that it is a fast, reliable and robust means of identifying transfusion requirements. SUMMARY: ROTEM provides a means to rapidly assess coagulation in trauma casualties, allowing targeted use of blood products. It provides information on clot initiation strength and breakdown. However, its use in trauma has still to be fully evaluated.

Impact of high ratios of plasma-to-red cell concentrate on the incidence of acute respiratory distress syndrome in UK transfused combat casualties.

Trauma transfusion strategies, which incorporate balanced red-cell concentrate (RCC)-to-fresh frozen plasma (FFP) ratios, may be associated with improved survival in massively transfused patients. However, the use of this approach in nonmassively transfused patients has led to concern regarding an increase in acute respiratory distress syndrome (ARDS). The aim of this study was to assess the incidence of ARDS in transfused UK military casualties. All UK military casualties receiving an RCC transfusion within a 16-month period were identified from the UK Trauma Registry, and chest radiographs retrieved. If bilateral infiltrates were present, case notes were retrieved to calculate the PaO2/FIO2 ratio in accordance with the American-European Consensus Conference criteria. Patients were divided into massively transfused (≥ 10 U/24 h) and nonmassively transfused (<10 U/24 h) receiving a high ratio (≥ 0.75) or low (<0.75) RCC:FFP ratio. The primary outcome was the development of ARDS within 7 days of transfusion. Primary blast lung injury was excluded. Of 145 patients identified, 144 had records available for analysis with a median injury severity score of 21. The majority were injured by explosion (76%), and the remainder by gunshot (24%). There were 60 nonmassively transfused patients with 18 in the low and 42 in the high RCC:FFP ratio groups. Of the remaining 80 massively transfused patients, 11 were in the low and 73 were in the high-ratio groups. There was no difference in the incidence of ARDS between low- and high-ratio groups in either nonmassively transfused (22.2% vs. 9.5%; P = 0.232) or massively transfused (18.2% vs. 23.3%; P = 1.000) casualties. There was no statistically significant increase in the incidence of ARDS in UK casualties treated with high, compared with low, ratios of plasma to RCC.