This study investigates a new machine-learning approach to predicting fall parameters leading to skull fractures in infants.
In this study, researchers introduced a novel, data-driven approach to predict fall parameters leading to skull fractures in infants in order to aid in determinations of abusive head trauma. The results from the best-performing models demonstrated that while predicting the exact fall height remains challenging, researchers can effectively identify potential impact sites. This work not only provides a tool to enhance the ability to assess abuse in cases of pediatric head trauma, but also advocates for advancements in computational models to simulate complex skull fractures. The researchers utilized a state-of-the-art finite element fracture simulation framework to generate a unique dataset of skull fracture patterns from simulated falls and then extracted features from the resulting fracture patterns in this dataset to be used as input into machine learning models. The authors compared seven machine learning models on their abilities to predict two fall parameters: impact site and fall height. When infants are admitted to the hospital with skull fractures, providers must distinguish between cases of accidental and abusive head trauma. Limited information about the incident is available in such cases, and witness statements are not always reliable. (Published Abstract Provided)