Development of prehospital assessment findings associated with massive transfusion

Wheeler, Abigail R.; Cuenca, Camaren M.; Fisher, Andrew D; April, Michael D.; Shackelford, S; Schauer, Steven G

doi:10.1111/trf.15595

Cited by 9 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dispatch features include the patient’s geographical location and level of response e.g., Advanced Life Support or Basic Life Support, and procedures include CPR and intubation. This result agrees with recent data suggesting that prehospital procedures have high predictive value for predicting the need for hospital interventions such as massive transfusion [ 38 ]. However, when time budgets increase other features, such as vital signs, gain more significance and the importance of the earlier demographic features tends to decline.…”

Section: Resultssupporting

confidence: 92%

“…A recent study developed a linear model to predict whether military trauma patients would receive massive transfusion of blood products, with the goal of discovering “concrete and rapidly and easily assessable” predictors. This study did not explicitly account for model cost, but noted that some data, including vital signs, may be difficult to acquire or unavailable in the prehospital setting and developed multiple models with different numbers of features, implying the potential value in this area of models that automatically account for cost [ 38 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A cost-aware framework for the development of AI models for healthcare applications

et al. 2022

View full text Add to dashboard Cite

The recent emergence of accurate artificial intelligence (AI) models for disease diagnosis raises the possibility that AI-based clinical decision support could substantially lower the workload of healthcare providers. However, for this to occur, the input data to an AI predictive model, i.e., the patient’s features, must themselves be low-cost, that is, efficient, inexpensive, or low-effort to acquire. When time or financial resources for gathering data are limited, as in emergency or critical care medicine, modern high-accuracy AI models that use thousands of patient features are likely impractical. To address this problem, we developed the CoAI ( Cos t-aware AI ) framework to enable any kind of AI predictive model (e.g., deep neural networks, tree ensemble models, etc.) to make accurate predictions given a small number of low-cost features. We show that CoAI dramatically reduces the cost of predicting prehospital acute traumatic coagulopathy, intensive care mortality, and outpatient mortality relative to existing risk scores, while improving prediction accuracy. It also outperforms existing state-of-the-art cost-sensitive prediction approaches in terms of predictive performance, model cost, and training time. Extrapolating these results to all trauma patients in the United States shows that, at a fixed false positive rate, CoAI could alert providers of tens of thousands more dangerous events than other risk scores while reducing providers’ data-gathering time by about 90 percent, leading to a savings of 200,000 cumulative hours per year across all providers. We extrapolate similar increases in clinical utility for CoAI in intensive care. These benefits stem from several unique strengths: First, CoAI uses axiomatic feature attribution methods that enable precise estimation of feature importance. Second, CoAI is model-agnostic, allowing users to choose the predictive model that performs the best for the prediction task and data at hand. Finally, unlike many existing methods, CoAI finds high-performance models within a given budget without any tuning of the cost-vs-performance tradeoff. We believe CoAI will dramatically improve patient care in the domains of medicine in which predictions need to be made with limited time and resources.

show abstract

Section: Resultssupporting

confidence: 92%

Section: Methodsmentioning

confidence: 99%

A cost-aware framework for the development of AI models for healthcare applications

et al. 2022

View full text Add to dashboard Cite

show abstract

“…пульс на лучевой артерии был удовлетворительных ка честв [29]. Проникающие ранения груди и жи вота, высокие отрывы конечностей, необхо димость наложения жгута, пульс > 120 уд/мин, индекс шока ≥ 0,8 определены предикторами боевой травмы с массивной кровопотерей, требующей трансфузии > 10 доз эритроцитсо держащих сред в течение 1 сут [16,26,49]. На основе технологий машинного обучения для военных медиков разработано программное обеспечение для телефона и планшета, кото рое помогает диагностировать шок по введен ным в нее клиническим данным, принять обос нованные решения по сортировке и лечению раненых в полевых условиях [30].…”

Section: результаты и их анализunclassified

Prehospital care according to the principles of Damage Control Resuscitation in the conditions of modern warfare (literature review)

Shapkin

Seliverstov

Stekolnikov

et al. 2023

Med.-biol. soc.-psihol. probl. bezop. črezvyčajnyh situac.

View full text Add to dashboard Cite

Relevance. Bleeding and hemorrhagic shock are the leading cause of potentially preventable deaths in combat casualties. The concept of pre-hospital injury control Remote Damage Control Resuscitation is becoming an integral part of care in the wounded with shock in the field. The significance of prehospital care provision according to the principles of Damage Control Resuscitation is increasing in future “multidomain battlefield”.The objective is to consider the effectiveness and features of prehospital care provision according to the principles of DCR in armed conflicts of the last two decades (in Afghanistan, Iraq, Africa, the Middle East).Methodology. A search was made for scientific articles in the PubMed database and the Scientific Electronic Library (eLIBRARY.ru), published from 2017 to 2022.Results and Discussion. Prehospital care according to the principles of Damage Control Resuscitation includes temporary arrest of bleeding, infusion therapy as part of hemostatic resuscitation and permissive hypotension, adequate respiratory support, prevention and elimination of hypothermia, and prompt evacuation to the stage of surgical care. Effective means to stop bleeding in combat casualties are modern hemostatic tourniquets, pelvic bandage, hemostatic dressings with koalin and chitosan. Resuscitation endovascular balloon occlusion of the aorta is recognized as a promising method for stopping internal bleeding. The basis of hemostatic resuscitation on the battlefield is the earlier transfusion of blood or its components in combination with the introduction of tranexamic acid and calcium preparations. Group O (I) whole blood with low titer anti-A and anti-B antibodies, lyophilized plasma and fibrinogen concentrate offer logistical advantages for combat use.Conclusion. Pre-hospital care according to the principles of Damage Control Resuscitation is effective and can significantly reduce mortality among those injured in combat operations.

show abstract

“…13 Blood transfusions are frequently administered during the resuscitation of severely wounded combat casualties, especially within the rst 6 to 12 hours, when death from hemorrhage is most likely to occur. [14][15][16][17] The classic de nition of massive transfusion (MT) was de ned during the Vietnam War as the transfusion of 10 units of blood in a 24-hour period. Timely activation of massive transfusion protocols is imperative during resuscitation.…”

Section: Introductionmentioning

confidence: 99%

Pulse Pressure: A Predictor of Intervention in Blunt Abdominal Trauma

Salman

Laeeque

Jawaid

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Patients with life-threatening hemorrhage due to blunt torso trauma are at a particularly high risk of being under-diagnosed. The pulse pressure starts narrowing down before the traditional parameters start changing, making it a useful tool for assessing and planning early intervention. Objective: Toassess the utility of low pulse pressure in predicting massive transfusion or operative intervention in patients with isolated blunt torso trauma. Material and Methods: total of 186 patients were included. The pulse pressure and mean arterial pressure were calculated. Vitals, pulse pressure, and mean arterial pressure were monitored every 15 min during the first 6 h, then every 30 min during the next 6 h and afterwards, every 4 h until discharge. Chi-square test and an independent t-test (as appropriate) were applied to compare variables with pulse pressure at the time of presentation. A Differences were considered as statistically significant at p-value ≤ 0.05. Results: total of 55.9% of these patients had injuries due to road traffic accidents. Emergency operative intervention was provided to 26.3% of the patients. Death was 4.3%. Massive transfusion was required by 26.3% of the patients. There was a statistically significant association between low pulse pressure and sex, length of stay, repeat eFAST, emergency operational intervention, outcome, massive transfusion, number of crystalloids consumed within the first four hours after presentation, injury severity score, systolic blood pressure, and pulse rate. Conclusion: The pulse pressure <30 mmHg was observed as an independent predictor for increased blood loss requiring blood transfusion or operative intervention.

show abstract

Development of prehospital assessment findings associated with massive transfusion

Cited by 9 publications

References 32 publications

A cost-aware framework for the development of AI models for healthcare applications

A cost-aware framework for the development of AI models for healthcare applications

Prehospital care according to the principles of Damage Control Resuscitation in the conditions of modern warfare (literature review)

Pulse Pressure: A Predictor of Intervention in Blunt Abdominal Trauma

Contact Info

Product

Resources

About