Risk assessment for intraabdominal injury following blunt trauma in children: Derivation and validation of a machine learning model
bit.ly shows its articles on its own site.
Read the article on bit.ly ↗Article · Jun 2020 · 1 min read
In brief
In brief
This study applies machine learning to the PECARN blunt abdominal trauma dataset to create predictive models for intra-abdominal injury requiring intervention in children. The models aim to provide individualized risk assessment beyond existing low-risk criteria, potentially reducing unnecessary CT scans while improving clinical decision-making for pediatric trauma patients.
Written by the GCMD Library team from the article.
Background: Computed tomography (CT) is the gold standard for diagnosing intra-abdominal injury (IAI) but is expensive and risks radiation exposure. The Pediatric Emergency Care Applied Research Network (PECARN) model identifies children at low risk of IAI requiring intervention (IAI-I) in whom CT may be omitted, but does not provide an individualized risk assessment to positively predict IAI-I. We sought to apply machine learning algorithms to the PECARN blunt abdominal trauma (BAT) dataset experimentally to create models for predicting both the presence and absence of IAI-I for pediatric BAT victims.
Methods: Using the PECARN dataset we derived and validated predictive models for IAI-I. The dataset was divided into derivation (n=7940) and validation (n=4089) subsets. Six algorithms were tested to create two models using 19 clinical variables including emesis, dyspnea, GCS