Predicting blood transfusion following traumatic injury using machine learning models: A systematic review and narrative synthesis.

BACKGROUND: Haemorrhage is a leading cause of preventable death in trauma. Accurately predicting a patient's blood transfusion requirement is essential but can be difficult. Machine learning (ML) is a field of artificial intelligence that is emerging within medicine for accurate prediction modelling. This systematic review aimed to identify and evaluate all ML models that predict blood transfusion in trauma. METHODS: This systematic review was registered on The International Prospective register of Systematic Reviews (CRD4202237110). MEDLINE, Embase and the Cochrane Central Register of Controlled Trials were systematically searched. Publications reporting a ML model that predicted blood transfusion in injured adult patients were included. Data extraction and risk of bias assessment was performed using validated frameworks. Data was synthesised narratively due to significant heterogeneity. RESULTS: Twenty-five ML models for blood transfusion prediction in trauma were identified. Models incorporated diverse predictors and varied ML methodologies. Predictive performance was variable but eight models achieved excellent discrimination (AUROC >0.9) and nine models achieved good discrimination (AUROC >0.8) in internal validation. Only two models reported measures of calibration. Four models have been externally validated in prospective cohorts: the Bleeding Risk Index, Compensatory Reserve Index, the Marsden model and the Mina model. All studies were considered at high risk of bias often due to retrospective datasets, small sample size and lack of external validation. DISCUSSION: This review identified twenty-five ML models developed to predict blood transfusion requirement after injury. Seventeen ML models demonstrated good to excellent performance in-silico but only four models were externally validated. To date ML models demonstrate the potential for early and individualised blood transfusion prediction but further research is critically required to narrow the gap between ML model development and clinical application. LEVEL OF EVIDENCE: Systematic Review Without Meta-Analysis, Level IV.

Evaluating patient factors, operative management and postoperative outcomes in trauma laparotomy patients worldwide: a protocol for a global observational multicentre trauma study.

INTRODUCTION: Trauma contributes to the greatest loss of disability-adjusted life-years for adolescents and young adults worldwide. In the context of global abdominal trauma, the trauma laparotomy is the most commonly performed operation. Variation likely exists in how these patients are managed and their subsequent outcomes, yet very little global data on the topic currently exists. The objective of the GOAL-Trauma study is to evaluate both patient and injury factors for those undergoing trauma laparotomy, their clinical management and postoperative outcomes. METHODS: We describe a planned prospective multicentre observational cohort study of patients undergoing trauma laparotomy. We will include patients of all ages who present to hospital with a blunt or penetrating injury and undergo a trauma laparotomy within 5 days of presentation to the treating centre. The study will collect system, patient, process and outcome data, following patients up until 30 days postoperatively (or until discharge or death, whichever is first). Our sample size calculation suggests we will need to recruit 552 patients from approximately 150 recruiting centres. DISCUSSION: The GOAL-Trauma study will provide a global snapshot of the current management and outcomes for patients undergoing a trauma laparotomy. It will also provide insight into the variation seen in the time delays for receiving care, the disease and patient factors present, and patient outcomes. For current standards of trauma care to be improved worldwide, a greater understanding of the current state of trauma laparotomy care is paramount if appropriate interventions and targets are to be identified and implemented.

ASGBI trauma committee position statement: a national audit of trauma laparotomy in the UK - an unmet need.

Patients who undergo laparotomy for major trauma are amongst the most critically unwell patients, and they have high morbidity and mortality rates. Despite 20 yr of improvements in resuscitation practices, those who present with hypotension continue to have mortality rates of up to 50%. Currently there is no mechanism for capturing national audit data on these patients, leading to their exclusion from potential quality improvement initiatives. We argue that there is an unmet need for quality assurance in this patient cohort and outline possible mechanisms to address this.

Selective aortic arch perfusion: a first-in-human observational cadaveric study.

BACKGROUND: Selective aortic arch perfusion (SAAP) is a novel endovascular technique that combines thoracic aortic occlusion with extracorporeal perfusion of the brain and heart. SAAP may have a role in both haemorrhagic shock and in cardiac arrest due to coronary ischaemia. Despite promising animal studies, no data is available that describes SAAP in humans. The primary aim of this study was to assess the feasibility of selective aortic arch perfusion in humans. The secondary aim of the study was to assess the feasibility of achieving direct coronary artery access via the SAAP catheter as a potential conduit for salvage percutaneous coronary intervention. METHODS: Using perfused human cadavers, a prototype SAAP catheter was inserted into the descending aorta under fluoroscopic guidance via a standard femoral percutaneous access device. The catheter balloon was inflated and the aortic arch perfused with radio-opaque contrast. The coronary arteries were cannulated through the SAAP catheter. RESULTS: The procedure was conducted four times. During the first two trials the SAAP catheter was passed rapidly and without incident to the intended descending aortic landing zone and aortic arch perfusion was successfully delivered via the device. The SAAP catheter balloon failed on the third trial. On the fourth trial the left coronary system was cannulated using a 5Fr coronary guiding catheter through the central SAAP catheter lumen. CONCLUSIONS: For the first time using a perfused cadaveric model we have demonstrated that a SAAP catheter can be easily and safely inserted and SAAP can be achieved using conventional endovascular techniques. The SAAP catheter allowed successful access to the proximal aorta and permitted retrograde perfusion of the coronary and cerebral circulation.

Revisiting the promise, practice and progress of resuscitative endovascular balloon occlusion of the aorta.

PURPOSE OF REVIEW: The use of Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) to temporarily control bleeding and improve central perfusion in critically injured trauma patients remains a controversial topic. In the last decade, select trauma services around the world have gained experience with REBOA. We discuss the recent observational data together with the initial results of the first randomized control trial and provide a view on the next steps for REBOA in trauma resuscitation. RECENT FINDINGS: While the observational data continue to be conflicting, the first randomized control trial signals that in the UK, in-hospital REBOA is associated with harm. Likely a result of delays to haemorrhage control, views are again split on whether to abandon complex interventions in bleeding trauma patients and to only prioritize transfer to the operating room or to push REBOA earlier into the post injury phase, recognizing that some patients will not survive without intervention. SUMMARY: Better understanding of cardiac shock physiology provides a new lens in which to evaluate REBOA through. Patient selection remains a huge challenge. Invasive blood pressure monitoring, combined with machine learning aided decision support may assist clinicians and their patients in the future. The use of REBOA should not delay definitive haemorrhage control in those patients without impending cardiac arrest.

Understanding pre-hospital blood transfusion decision-making for injured patients: an interview study.

BACKGROUND: Blood transfusion for bleeding trauma patients is a promising pre-hospital intervention with potential to improve outcomes. However, it is not yet clear which patients may benefit from pre-hospital transfusions. The aim of this study was to enhance our understanding of how experienced pre-hospital clinicians make decisions regarding patient blood loss and the need for transfusion, and explore the factors that influence clinical decision-making. METHODS: Pre-hospital physicians, from two air ambulance sites in the south of England, were interviewed between December 2018 and January 2019. Participants were involved in teaching or publishing on the management of bleeding trauma patients and had at least 5 years of continuous and contemporary practice at consultant level. Interviews were semi-structured and explored how decisions were made and what made decisions difficult. A qualitative description approach was used with inductive thematic analysis to identify themes and subthemes related to blood transfusion decision-making in trauma. RESULTS: Ten pre-hospital physicians were interviewed and three themes were identified: recognition-primed analysis, uncertainty and imperfect decision analysis. The first theme describes how participants make decisions using selected cues, incorporating their experience and are influenced by external rules and group expectations. What made decisions difficult for the participants was encapsulated in the uncertainty theme. Uncertainty emerged regarding the patient's true underlying physiological state and the treatment effect of blood transfusion. The last theme focuses on the issues with decision-making itself. Participants demonstrated lapses in decision awareness, often incomplete decision evaluation and described challenges to effective learning due to incomplete patient outcome information. CONCLUSION: Pre-hospital clinicians make decisions about bleeding and transfusion which are recognition-primed and incorporate significant uncertainty. Decisions are influenced by experience and are subject to bias. Improved understanding of the decision-making processes provides a theoretical perspective of how decisions might be supported in the future.

Diagnostic accuracy of clinical examination to identify life- and limb-threatening injuries in trauma patients.

BACKGROUND: Timely and accurate identification of life- and limb-threatening injuries (LLTIs) is a fundamental objective of trauma care that directly informs triage and treatment decisions. However, the diagnostic accuracy of clinical examination to detect LLTIs is largely unknown, due to the risk of contamination from in-hospital diagnostics in existing studies. Our aim was to assess the diagnostic accuracy of initial clinical examination for detecting life- and limb-threatening injuries (LLTIs). Secondary aims were to identify factors associated with missed injury and overdiagnosis, and determine the impact of clinician uncertainty on diagnostic accuracy. METHODS: Retrospective diagnostic accuracy study of consecutive adult (≥ 16 years) patients examined at the scene of injury by experienced trauma clinicians, and admitted to a Major Trauma Center between 01/01/2019 and 31/12/2020. Diagnoses of LLTIs made on contemporaneous clinical records were compared to hospital coded diagnoses. Diagnostic performance measures were calculated overall, and based on clinician uncertainty. Multivariate logistic regression analyses identified factors affecting missed injury and overdiagnosis. RESULTS: Among 947 trauma patients, 821 were male (86.7%), median age was 31 years (range 16-89), 569 suffered blunt mechanisms (60.1%), and 522 (55.1%) sustained LLTIs. Overall, clinical examination had a moderate ability to detect LLTIs, which varied by body region: head (sensitivity 69.7%, positive predictive value (PPV) 59.1%), chest (sensitivity 58.7%, PPV 53.3%), abdomen (sensitivity 51.9%, PPV 30.7%), pelvis (sensitivity 23.5%, PPV 50.0%), and long bone fracture (sensitivity 69.9%, PPV 74.3%). Clinical examination poorly detected life-threatening thoracic (sensitivity 48.1%, PPV 13.0%) and abdominal (sensitivity 43.6%, PPV 20.0%) bleeding. Missed injury was more common in patients with polytrauma (OR 1.83, 95% CI 1.62-2.07) or shock (systolic blood pressure OR 0.993, 95% CI 0.988-0.998). Overdiagnosis was more common in shock (OR 0.991, 95% CI 0.986-0.995) or when clinicians were uncertain (OR 6.42, 95% CI 4.63-8.99). Uncertainty improved sensitivity but reduced PPV, impeding diagnostic precision. CONCLUSIONS: Clinical examination performed by experienced trauma clinicians has only a moderate ability to detect LLTIs. Clinicians must appreciate the limitations of clinical examination, and the impact of uncertainty, when making clinical decisions in trauma. This study provides impetus for diagnostic adjuncts and decision support systems in trauma.

Defence Medical Services' REBOA training course.

Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) enables temporary haemorrhage control and physiological stabilisation. This article describes the bespoke Defence Medical Services (DMS) training package for effectively using REBOA. The article covers how the course was designed, how the key learning objectives are taught, participant feedback and the authors' perceptions of future training challenges and opportunities. Since the inaugural training course in April 2019, the authors have delivered six courses, training over 100 clinicians. For the first time in the UK DMS, we designed and delivered a robust specialist endovascular training programme, with demonstrable, significant increases in confidence and competence. As a result of this course, the first DMS REBOA-equipped forward surgical teams deployed in June 2019. Looking to the future, there is a requirement to develop an assessment of skill retention and the potential need for revalidation.

Balloons on the battlefield: REBOA implementation in the UK Defence Medical Services.

Established in 2018, the Defence Endovascular Resuscitation (DefER) group recognised that resuscitative endovascular balloon occlusion of the aorta (REBOA) offered an option to improve survival in battle casualties dying from haemorrhage, particularly in remote and austere surgical settings. Following a successful jHub opportunity assessment, DefER purchased training and operational kit at pace. By 1 April 2019, the first forward surgical group undertook a bespoke endovascular training and assessment package. Results of the pilot were presented back to a jHub 4* Innovation Board, which initially awarded £500 000 to fund the project to full implementation. Med Op Cap provided a solution to establish REBOA as a core capability on to the 370 modules. REBOA catheters and arterial access kit are now available to deployed Role 2 facilities across defence as an adjunct to damage control resuscitation in specific circumstances. REBOA has, from a standing start, gained pan-Defence Medical Services (DMS) endorsement and has been integrated into deployed damage control resuscitation. To establish a new resuscitation capability across all Role 2 platforms within 15 months of inception represents implementation at pace. This agility was unlocked by empowering clinicians to develop the platform in conjunction with commercial procurement. This article describes how this innovative pathway facilitated the rapid introduction of a lifesaving haemorrhage control technique to equip DMS clinicians.

Use of a modified Delphi process to develop research priorities in major trauma.

PURPOSE: The burden of major trauma within the UK is ever increasing. There is a need to establish research priorities within the field. Delphi methodology can be used to develop consensus opinion amongst a group of stakeholders. This can be used to prioritise clinically relevant, patient-centred research questions to guide future funding allocations. The aim of our study was to identify key future research priorities pertaining to the management of major trauma in the UK. METHODS: A three-phased modified Delphi process was undertaken. Phase 1 involved the submission of research questions by members of the trauma community using an online survey (Phase 1). Phases 2 and 3 involved two consecutive rounds of prioritisation after questions were subdivided into 6 subcategories: Brain Injury, Rehabilitation, Trauma in Older People, Pre-hospital, Interventional, and Miscellaneous (Phases 2 and 3). Cut-off points were agreed by consensus amongst the steering subcommittees. This established a final prioritised list of research questions. RESULTS: In phase 1, 201 questions were submitted by 65 stakeholders. After analysis and with consensus achieved, 186 questions were taken forward for prioritisation in phase 2 with 114 included in phase 3. 56 prioritised major trauma research questions across the 6 categories were identified with a clear focus on long-term patient outcomes. Research priorities across the patient pathway from roadside to rehabilitation were deemed of importance. CONCLUSIONS: Consensus within the major trauma community has identified 56 key research questions across 6 categories. Dissemination of these questions to funding bodies to allow for the development of high-quality research is now required. There is a clear indication for targeted multi-centre multi-disciplinary research in major trauma.

Trauma Laparotomy in the UK: A Prospective National Service Evaluation.

BACKGROUND: Trauma patients requiring abdominal operation have considerable morbidity and mortality, yet no specific quality indicators are measured in the trauma systems of the UK. The aims of this study were to describe the characteristics and outcomes of patients undergoing emergency abdominal operation and key processes of care. STUDY DESIGN: A prospective multicenter service evaluation was conducted within all of the major trauma centers in the UK. The study was conducted during 6 months beginning in January 2019. Patients of any age undergoing laparotomy or laparoscopy within 24 hours of injury were included. Existing standards for related emergent conditions were used. RESULTS: The study included 363 patients from 34 hospitals. The majority were young men with no comorbidities who required operation to control bleeding (51%). More than 90% received attending-delivered care in the emergency department (318 of 363) and operating room (321 of 363). The overall mortality rate was 9%. Patients with blunt trauma had a greater risk of death compared with patients with penetrating injuries (16.6% vs 3.8%; risk ratio 4.3; 95% CI, 2.0 to 9.4). Patients in which the Major Hemorrhage Protocol (MHP) was activated and who received a blood transfusion (n = 154) constituted a high-risk subgroup, accounting for 45% of the study cohort but 97% of deaths and 96% of blood components transfused. The MHP subgroup had expedited timelines from emergency department arrival to knife to skin (MHP: median 119 minutes [interquartile range 64 to 218 minutes] vs no MHP: median 211 minutes [interquartile range 135 to 425 minutes]; p < 0.001). CONCLUSIONS: The majority of trauma patients requiring emergency abdominal operation received a high standard of expedited care in a maturing national trauma system. Despite this, mortality and resource use among high-risk patients remains considerable.

Early Identification of Trauma-induced Coagulopathy: Development and Validation of a Multivariable Risk Prediction Model.

OBJECTIVE: The aim of this study was to develop and validate a risk prediction tool for trauma-induced coagulopathy (TIC), to support early therapeutic decision-making. BACKGROUND: TIC exacerbates hemorrhage and is associated with higher morbidity and mortality. Early and aggressive treatment of TIC improves outcome. However, injured patients that develop TIC can be difficult to identify, which may compromise effective treatment. METHODS: A Bayesian Network (BN) prediction model was developed using domain knowledge of the causal mechanisms of TIC, and trained using data from 600 patients recruited into the Activation of Coagulation and Inflammation in Trauma (ACIT) study. Performance (discrimination, calibration, and accuracy) was tested using 10-fold cross-validation and externally validated on data from new patients recruited at 3 trauma centers. RESULTS: Rates of TIC in the derivation and validation cohorts were 11.8% and 11.0%, respectively. Patients who developed TIC were significantly more likely to die (54.0% vs 5.5%, P < 0.0001), require a massive blood transfusion (43.5% vs 1.1%, P < 0.0001), or require damage control surgery (55.8% vs 3.4%, P < 0.0001), than those with normal coagulation. In the development dataset, the 14-predictor BN accurately predicted this high-risk patient group: area under the receiver operating characteristic curve (AUROC) 0.93, calibration slope (CS) 0.96, brier score (BS) 0.06, and brier skill score (BSS) 0.40. The model maintained excellent performance in the validation population: AUROC 0.95, CS 1.22, BS 0.05, and BSS 0.46. CONCLUSIONS: A BN (http://www.traumamodels.com) can accurately predict the risk of TIC in an individual patient from standard admission clinical variables. This information may support early, accurate, and efficient activation of hemostatic resuscitation protocols.

Prehospital tranexamic acid shortens the interval to administration by half in Major Trauma Networks: a service evaluation.

INTRODUCTION: Tranexamic acid (TXA) reduces bleeding and mortality. Recent trials have demonstrated improved survival with shorter intervals to TXA administration. The aims of this service evaluation were to assess the interval from injury to TXA administration and describe the characteristics of patients who received TXA pre-hospital and in-hospital. METHODS: We reviewed Trauma and Audit Research Network records and local trauma registries to identify patients of any age that received TXA at all London Major Trauma Centres and Queen's Medical Centre, Nottingham, during 2017. We used the 2016 NICE Guidelines (NG39) which state that TXA should be given within 3 hours of injury. RESULTS: We identified 1018 patients who received TXA, of whom 661 (65%) had sufficient data to assess the time from injury to TXA administration. The median interval was 74 min (IQR: 47-116). 92% of patients received TXA within 3 hours from injury, and 59% within 1 hour. Half of the patients (54%) received prehospital TXA. The median time to TXA administration when given prehospital was 51 min (IQR: 39-72), and 112 min (IQR: 84-160) if given in-hospital (p<0.001). In-hospital TXA patients had less haemodynamic derangement and lower base deficit on admission compared with patients given prehospital TXA. CONCLUSION: Prehospital administration of TXA is associated with a shorter interval from injury to drug delivery. Identifying a proportion of patients at risk of haemorrhage remains a challenge. However, further reinforcement is needed to empower pre-hospital clinicians to administer TXA to trauma patients without overt signs of shock.

Pre-hospital Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) for exsanguinating pelvic haemorrhage.

AIM: To report the initial experience and outcomes of Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA) as an adjunct to pre-hospital resuscitation of patients with exsanguinating pelvic haemorrhage. METHODS: Descriptive case series of consecutive adult patients, treated with pre-hospital Zone III REBOA by a physician-led pre-hospital trauma service, between January 2014 and July 2018. RESULTS: REBOA was attempted in 19 trauma patients (13 successful, six failed attempts) and two non-trauma patients (both successful) with exsanguinating pelvic haemorrhage. Trauma patients were severely injured (median ISS 34, IQR: 27-43) and profoundly hypotensive (median systolic blood pressure [SBP] 57, IQR: 40-68 mmHg). REBOA significantly improved blood pressure (Pre-REBOA median SBP 57, IQR: 35-67 mmHg versus Post- REBOA SBP 114, IQR: 86-132 mmHg; Median of differences 66, 95% CI: 25-74 mmHg; P < 0.001). REBOA was associated with significantly lower risk of pre-hospital cardiac arrest (REBOA 0/13 [0%] versus no REBOA 3/6 [50%], P = 0.021) and death from exsanguination (REBOA 0/13 [0%] versus no REBOA 4/6 [67%], P = 0.004), when compared to patients with a failed attempt. Successful REBOA was associated with improved survival (REBOA 8/13 [62%] versus no REBOA 2/6 [33%]; P = 0.350). Distal arterial thrombus requiring thrombectomy was common in the REBOA group (10/13, 77%). CONCLUSION: REBOA is a feasible pre-hospital resuscitation strategy for patients with exsanguinating pelvic haemorrhage. REBOA significantly improves blood pressure and may reduce the risk of pre-hospital hypovolaemic cardiac arrest and early death due to exsanguination. Distal arterial thrombus formation is common, and should be actively managed.

Outcomes following trauma laparotomy for hypotensive trauma patients: A UK military and civilian perspective.

BACKGROUND: The management of trauma patients has changed radically in the last decade, and studies have shown overall improvements in survival. However, reduction in mortality for the many may obscure a lack of progress in some high-risk patients. We sought to examine the outcomes for hypotensive patients requiring laparotomy in UK military and civilian cohorts. METHODS: We undertook a review of two prospectively maintained trauma databases: the UK Joint Theatre Trauma Registry for the military cohort (February 4, 2003, to September 21, 2014) and the trauma registry of the Royal London Hospital major trauma center (January 1, 2012, to January 1, 2017) for civilian patients. Adults undergoing trauma laparotomy within 90 minutes of arrival at the emergency department (ED) were included. RESULTS: Hypotension was present on arrival at the ED in 155 (20.4%) of 761 military patients. Mortality was higher in hypotensive casualties (25.8% vs. 9.7% in normotensive casualties; p < 0.001). Hypotension was present on arrival at the ED in 63 (35.7%) of 176 civilian patients. Mortality was higher in hypotensive patients (47.6% vs. 12.4% in normotensive patients; p < 0.001). In both cohorts of hypotensive patients, neither the average injury severity, the prehospital time, the ED arrival systolic blood pressure, nor mortality rate changed significantly during the study period. CONCLUSIONS: Despite improvements in survival after trauma for patients overall, the mortality for patients undergoing laparotomy who arrive at the ED with hypotension has not changed and appears stubbornly resistant to all efforts. Specific enquiry and research should continue to be directed at this high-risk group of patients. LEVEL OF EVIDENCE: Prognostic/Epidemiologic, level IV.