Related Experiment Videos
Young child injury analysis by the classification entropy method
1Croatian National Institute of Public Health, Zagreb, Rockefellerova, Croatia.
Insights
This study analyzed child injuries in Croatia, finding that age, place, and gender are key factors in determining injury causes. This information entropy method optimizes injury cause classification for prevention programs.
Area of Science:
- Public Health
- Injury Prevention
- Biostatistics
Background:
- Childhood injuries pose a significant public health concern, necessitating effective data collection and analysis for preventive strategies.
- Koprivnica County, Croatia, has implemented a project to register accidents and injuries since 1992, providing a valuable dataset for analysis.
- Children aged 1-4 years constitute a notable percentage of the population, making them a critical group for injury prevention efforts.
Purpose of the Study:
- To analyze complex injury attributes in children aged 1-4 years in Koprivnica County.
- To introduce and apply a novel method using information entropy for classifying injury causes.
- To identify and rank the importance of input attributes (age, gender, place of injury) in child injury ascertainment.
Main Methods:
- Data collection on injured individuals seeking medical aid in Koprivnica County since 1992.
- Classification of binary attributes into input (age, gender, place of injury) and output (severity of injury).
- Application of information entropy to classify injury-cause attributes, determining minimum information content and employing a sequential decision procedure.
Main Results:
- Information entropy was calculated for input attributes, revealing their predictive power for injury causes.
- A decision tree was generated, demonstrating increasing entropy and decreasing determinism.
- Age (0.5347 N), place of injury (0.6062 N), and gender (0.6105 N) were identified as measurable attributes in descending order of importance for child injury ascertainment.
Conclusions:
- The information entropy method provides an optimal approach for classifying injury causes.
- Understanding the relative importance of age, place, and gender is crucial for developing targeted child injury prevention programs.
- The study highlights the effectiveness of data-driven methods in enhancing injury surveillance and prevention strategies.
Abstract:
The project 'The Register and Preventive Programs for Accidents and Injuries' enabled data collection on all the injured who sought medical aid in Koprivnica County (population 61,052), Croatia, since 1992. Children aged 1-4 years are 5.03% of the whole population of the district. Complex injury attributes were analysed. Binary attributes were classified as input: age, gender, place of injury; and output: severity of injury. A new application of information entropy was introduced and applied to the classification of injury-causes attributes. The information entropy was calculated for the classification of input attributes according to the minimum information content. The decision procedure is given as a sequential procedure separating important from unimportant causes of injury at each decision level. Thus a decision tree with increasing entropy, i.e. decreasing determinism, was obtained showing that age (0.5347 N), place (0.6062 N) and gender (0.6105 N) are measurable attributes in child injury ascertainment in a descending pattern. It was shown that this method is, at the same time, an optimal way of using an attribute decision process of injury causes classification.