Premium
Predicting Severity of Foreign Body Injuries in Children in Upper Airways: An Approach Based on Regression Trees
Author(s) -
Berchialla Paola,
Snidero Silvia,
Stancu Alexandru,
Scarinzi Cecilia,
Corradetti Roberto,
Gregori Dario
Publication year - 2007
Publication title -
risk analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.972
H-Index - 130
eISSN - 1539-6924
pISSN - 0272-4332
DOI - 10.1111/j.1539-6924.2007.00971.x
Subject(s) - choking , foreign body , linear discriminant analysis , poison control , medicine , injury prevention , decision tree , medical emergency , statistics , computer science , surgery , mathematics , artificial intelligence , anatomy
The entry of a small item into the upper airways is one of the leading causes of injuries in children up to 14 years old. The aim of this study is to characterize types of objects causing choking along with the features of the children involved in the accident and compare results with current standards. The European Survey on Foreign Bodies Injuries Study (ESFBI) collected data on foreign body injuries from 19 European countries. The data from ESFBI were selected according to the ICD‐9‐CM codes 933 (foreign body in the pharynx and larynx) and 934 (foreign body in the trachea, bronchi, and lungs). Both a classification tree and a linear discriminant analysis (LDA) have been set up to predict the probability that an injured child experiences a hospitalization. The classification tree provides flowchart‐type decision rules and allows for analyzing the impact of the item features, the children characteristics, and the circumstances of the accidents on the severity of the foreign body injuries. Results showed that children younger than 3.5 who are involved in an accident have a high probability to experience a hospitalization.