Predicting the need for massive transfusion: Prospective validation of a smartphone-based clinical decision support tool

American Association for the Surgery of Trauma/American College of Surgeons Committee on Trauma: Clinical protocol for damage-control resuscitation for the adult trauma patient

ABSTRACT

Damage-control resuscitation in the care of critically injured trauma patients aims to limit blood loss and prevent and treat coagulopathy by combining early definitive hemorrhage control, hypotensive resuscitation, and early and balanced use of blood products (hemostatic resuscitation) and the use of other hemostatic agents. This clinical protocol has been developed to provide evidence-based recommendations for optimal damage-control resuscitation in the care of trauma patients with hemorrhage.

Identification of major hemorrhage in trauma patients in the prehospital setting: diagnostic accuracy and impact on outcome

Background

Hemorrhage is the most common cause of potentially preventable death after injury. Early identification of patients with major hemorrhage (MH) is important as treatments are time-critical. However, diagnosis can be difficult, even for expert clinicians. This study aimed to determine how accurate clinicians are at identifying patients with MH in the prehospital setting. A second aim was to analyze factors associated with missed and overdiagnosis of MH, and the impact on mortality.

Methods

Retrospective evaluation of consecutive adult (≥16 years) patients injured in 2019-2020, assessed by expert trauma clinicians in a mature prehospital trauma system, and admitted to a major trauma center (MTC). Clinicians decided to activate the major hemorrhage protocol (MHPA) or not. This decision was compared with whether patients had MH in hospital, defined as the critical admission threshold (CAT+): administration of ≥3 U of red blood cells during any 60-minute period within 24 hours of injury. Multivariate logistical regression analyses were used to analyze factors associated with diagnostic accuracy and mortality.

Results

Of the 947 patients included in this study, 138 (14.6%) had MH. MH was correctly diagnosed in 97 of 138 patients (sensitivity 70%) and correctly excluded in 764 of 809 patients (specificity 94%). Factors associated with missed diagnosis were penetrating mechanism (OR 2.4, 95% CI 1.2 to 4.7) and major abdominal injury (OR 4.0; 95% CI 1.7 to 8.7). Factors associated with overdiagnosis were hypotension (OR 0.99; 95% CI 0.98 to 0.99), polytrauma (OR 1.3, 95% CI 1.1 to 1.6), and diagnostic uncertainty (OR 3.7, 95% CI 1.8 to 7.3). When MH was missed in the prehospital setting, the risk of mortality increased threefold, despite being admitted to an MTC.

Conclusion

Clinical assessment has only a moderate ability to identify MH in the prehospital setting. A missed diagnosis of MH increased the odds of mortality threefold. Understanding the limitations of clinical assessment and developing solutions to aid identification of MH are warranted.

Level of evidence

Level III-Retrospective study with up to two negative criteria.

Study type

Original research; diagnostic accuracy study.

Early Prediction of Massive Transfusion for Patients With Traumatic Hemorrhage: Development of a Multivariable Machine Learning Model

Objective

Develop a novel machine learning (ML) model to rapidly identify trauma patients with severe hemorrhage at risk of early mortality.

Background

The critical administration threshold (CAT, 3 or more units of red blood cells in a 60-minute period) indicates severe hemorrhage and predicts mortality, whereas early identification of such patients improves survival.

Methods

Patients from the PRospective, Observational, Multicenter, Major Trauma Transfusion and Pragmatic, Randomized Optimal Platelet, and Plasma Ratio studies were identified as either CAT+ or CAT-. Candidate variables were separated into 4 tiers based on the anticipated time of availability during the patient's assessment. ML models were created with the stepwise addition of variables and compared with the baseline performance of the assessment of blood consumption (ABC) score for CAT+ prediction using a cross-validated training set and a hold-out validation test set.

Results

Of 1245 PRospective, Observational, Multicenter, Major Trauma Transfusion and 680 Pragmatic, Randomized Optimal Platelet and Plasma Ratio study patients, 1312 were included in this analysis, including 862 CAT+ and 450 CAT-. A CatBoost gradient-boosted decision tree model performed best. Using only variables available prehospital or on initial assessment (Tier 1), the ML model performed superior to the ABC score in predicting CAT+ patients [area under the receiver-operator curve (AUC = 0.71 vs 0.62)]. Model discrimination increased with the addition of Tier 2 (AUC = 0.75), Tier 3 (AUC = 0.77), and Tier 4 (AUC = 0.81) variables.

Conclusions

A dynamic ML model reliably identified CAT+ trauma patients with data available within minutes of trauma center arrival, and the quality of the prediction improved as more patient-level data became available. Such an approach can optimize the accuracy and timeliness of massive transfusion protocol activation.

Development and validation of a Bayesian network predicting neurosurgical intervention after injury in children and adolescents

BACKGROUND

Timely surgical decompression improves functional outcomes and survival among children with traumatic brain injury and increased intracranial pressure. Previous scoring systems for identifying the need for surgical decompression after traumatic brain injury in children and adults have had several barriers to use. These barriers include the inability to generate a score with missing data, a requirement for radiographic imaging that may not be immediately available, and limited accuracy. To address these limitations, we developed a Bayesian network to predict the probability of neurosurgical intervention among injured children and adolescents (aged 1-18 years) using physical examination findings and injury characteristics observable at hospital arrival.

METHODS

We obtained patient, injury, transportation, resuscitation, and procedure characteristics from the 2017 to 2019 Trauma Quality Improvement Project database. We trained and validated a Bayesian network to predict the probability of a neurosurgical intervention, defined as undergoing a craniotomy, craniectomy, or intracranial pressure monitor placement. We evaluated model performance using the area under the receiver operating characteristic and calibration curves. We evaluated the percentage of contribution of each input for predicting neurosurgical intervention using relative mutual information (RMI).

RESULTS

The final model included four predictor variables, including the Glasgow Coma Scale score (RMI, 31.9%), pupillary response (RMI, 11.6%), mechanism of injury (RMI, 5.8%), and presence of prehospital cardiopulmonary resuscitation (RMI, 0.8%). The model achieved an area under the receiver operating characteristic curve of 0.90 (95% confidence interval [CI], 0.89-0.91) and had a calibration slope of 0.77 (95% CI, 0.29-1.26) with a y intercept of 0.05 (95% CI, -0.14 to 0.25).

CONCLUSION

We developed a Bayesian network that predicts neurosurgical intervention for all injured children using four factors immediately available on arrival. Compared with a binary threshold model, this probabilistic model may allow clinicians to stratify management strategies based on risk.

LEVEL OF EVIDENCE

Prognostic and Epidemiological; Level III.

Time is tissue: Barriers to timely transfusion after pediatric injury

ABSTRACT

Strategies to improve outcomes among children and adolescents in hemorrhagic shock have primarily focused on component resuscitation, pharmaceutical coagulation adjuncts, and hemorrhage control techniques. Many of these strategies have been associated with better outcomes in children, but the barriers to their use and the impact of timely use on morbidity and mortality have received little attention. Because transfusion is uncommon in injured children, few studies have identified and described barriers to the processes of using these interventions in bleeding patients, processes that move from the decision to transfuse, to obtaining the necessary blood products and adjuncts, and to delivering them to the patient. In this review, we identify and describe the steps needed to ensure timely blood transfusion and propose practices to minimize barriers in this process. Given the potential impact of time on hemorrhage associated outcomes, ensuring timely intervention may have a similar or greater impact than the interventions themselves.

Massive Transfusion Protocol Predictive Modeling in the Modern Electronic Medical Record

Objectives

Integrate a predictive model for massive transfusion protocol (MTP) activation and delivery in the electronic medical record (EMR) using prospectively gathered data; externally validate the model and assess the accuracy and precision of the model over time.

Background

The Emory model for predicting MTP using only four input variables was chosen to be integrated into our hospital's EMR to provide a real time clinical decision support tool. The continuous variable output allows for periodic re-calibration of the model to optimize sensitivity and specificity.

Methods

Prospectively collected data from level 1 and 2 trauma activations were used to input heart rate, systolic blood pressure, base excess (BE) and mechanism of injury into the EMR-integrated model for predicting MTP activation and delivery. MTP delivery was defined as: 6 units of packed red blood cells/6 hours (MTP1) or 10 units in 24 hours (MTP2). The probability of MTP was reported in the EMR. ROC and PR curves were constructed at 6, 12, and 20 months to assess the adequacy of the model.

Results

Data from 1162 patients were included. Areas under ROC for MTP activation, MTP1 and MTP2 delivery at 6, 12, and 20 months were 0.800, 0.821, and 0.831; 0.796, 0.861, and 0.879; and 0.809, 0.875, and 0.905 (all P < 0.001). The areas under the PR curves also improved, reaching values at 20 months of 0.371, 0.339, and 0.355 for MTP activation, MTP1 delivery, and MTP2 delivery.

Conclusions

A predictive model for MTP activation and delivery was integrated into our EMR using prospectively collected data to externally validate the model. The model's performance improved over time. The ability to choose the cut-points of the ROC and PR curves due to the continuous variable output of probability of MTP allows one to optimize sensitivity or specificity.