Development and validation of a Bayesian belief network predicting the probability of blood transfusion after pediatric injury

Abstract

BACKGROUND:Early recognition and intervention of hemorrhage are associated with decreased morbidity in children. Triage models have been developed to aid in the recognition of hemorrhagic shock after injury but require complete data and have limited accuracy. To address these limitations, we developed a Bayesian belief network, a machine learning model that represents the joint probability distribution for a set of observed or unobserved independent variables, to predict blood transfusion after injury in children and adolescents. METHODS:We abstracted patient, injury, and resuscitation characteristics of injured children and adolescents (age 1 to 18 years) from the 2017 to 2019 Trauma Quality Improvement Project database. We trained a Bayesian belief network to predict blood transfusion within 4 hours after arrival to the hospital following injury using data from 2017 and recalibrated the model using data from 2018. We validated our model on a subset of patients from the 2019 Trauma Quality Improvement Project. We evaluated model performance using the area under the receiver operating characteristic curve and calibration curves and compared performance with pediatric age-adjusted shock index (SIPA) and reverse shock index with Glasgow Coma Scale (rSIG) using sensitivity, specificity, accuracy, and Matthew's correlation coefficient (MCC). RESULTS:The final model included 14 predictor variables and had excellent discrimination and calibration. The model achieved an area under the receiver operating characteristic curve of 0.92 using emergency department data. When used as a binary predictor at an optimal threshold probability, the model had similar sensitivity, specificity, accuracy, and MCC compared with SIPA when only age, systolic blood pressure, and heart rate were observed. With the addition of the Glasgow Coma Scale score, the model has a higher accuracy and MCC than SIPA and rSIG. CONCLUSION:A Bayesian belief network predicted blood transfusion after injury in children and adolescents better than SIPA and rSIG. This probabilistic model may allow clinicians to stratify hemorrhagic control interventions based upon risk.

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

“…34 Because uncertainty has been cited by trauma surgeons as a common reason for delayed diagnosis, decision support aids have been developed to identify life-threatening injuries, including hemorrhagic shock and severe TBI. 8,[35][36][37][38][39][40][41] When later provided an estimate of risk from a decision support aid, the diagnostic accuracy of clinical judgment alone can be improved and can reduce the time to management strategies. 35,42 Decision support aids like NINJA may provide additional contextual information to improve the timeliness of diagnosis and management of brain injuries.…”

“…When applied to unfamiliar scenarios, decisions based on heuristic reasoning are prone to unintended outcomes compared with those based on a conscious and deliberate approach 34 . Because uncertainty has been cited by trauma surgeons as a common reason for delayed diagnosis, decision support aids have been developed to identify life-threatening injuries, including hemorrhagic shock and severe TBI 8,35–41 . When later provided an estimate of risk from a decision support aid, the diagnostic accuracy of clinical judgment alone can be improved and can reduce the time to management strategies 35,42 .…”

Strategies to Obtain and Deliver Blood Products Into Critically Injured Children

“…8 Early recognition of uncontrolled hemorrhage is also difficult because children display robust physiological compensatory mechanisms that can mimic the body's normal adrenergic responses to injury. 8,[10][11][12][13][14][15] As a result, transfusion may be delayed to later stages of shock when transfusion is less effective at reversing the shock state. Without prompt access to blood products and proficiency in rapid infusion methods, early hemorrhage recognition and component resuscitation may be less effective in improving hemorrhage-associated outcomes.…”

“…Only about 3% of injured children receive a blood transfusion within 4 hours of arrival to a trauma center 8 . Early recognition of uncontrolled hemorrhage is also difficult because children display robust physiological compensatory mechanisms that can mimic the body's normal adrenergic responses to injury 8,10–15 . As a result, transfusion may be delayed to later stages of shock when transfusion is less effective at reversing the shock state.…”

Survival bias in pediatric hemorrhagic shock: Are we misrepresenting the data?

“…9,[17][18][19][20] To address challenges with early hemorrhagic shock recognition, several triage tools have been developed in adults and modified for use in children and adolescents. [21][22][23][24][25][26][27][28] While these tools predict the occurrence of a blood transfusion, they may not accurately predict a clinical need for transfusion or the presence of hemorrhagic shock. 9,21 Bias can occur when patients are classified by an intervention (e.g., transfusion) received rather than the underlying condition (e.g., hemorrhagic shock) that might require that intervention.…”