Multiple Logistic Regression Model for Assessing the Risk Factors of Traffic Accidents: Khon Kaen Model
Issued Date
2024-08-22
Resource Type
eISSN
18798365
Scopus ID
2-s2.0-85202003524
Pubmed ID
39176512
Journal Title
Studies in health technology and informatics
Volume
316
Start Page
1589
End Page
1593
Rights Holder(s)
SCOPUS
Bibliographic Citation
Studies in health technology and informatics Vol.316 (2024) , 1589-1593
Suggested Citation
Sujayanont P., Muttitanon W., Chemin Y., Som-Ard J., Tippayanate N. Multiple Logistic Regression Model for Assessing the Risk Factors of Traffic Accidents: Khon Kaen Model. Studies in health technology and informatics Vol.316 (2024) , 1589-1593. 1593. doi:10.3233/SHTI240725 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/100678
Title
Multiple Logistic Regression Model for Assessing the Risk Factors of Traffic Accidents: Khon Kaen Model
Corresponding Author(s)
Other Contributor(s)
Abstract
BACKGROUND: Thailand has consistently held the highest global ranking in traffic accidents since 2017, with Khon Kaen displaying the highest mortality rate in the Department of Disease Control Region 7. OBJECTIVES: This study aims to utilize Injury Surveillance (IS) data to identify risk factors associated with emergency room (ER) outcomes at the Emergency Department of Khon Kaen hospital in Khon Kaen Municipality. METHODS: Data from the Injury Surveillance system's (IS system) database were collected, focusing on severity outcomes, time of events, and risk behaviors from January 1, 2008, to December 31, 2021. Data analysis was conducted using the R program, employing the Chi-square or independent T test to compare results and analyze associations between potential risk factors and ER outcomes. Multiple logistic regression (MLR) was used for classification analysis, and a confusion matrix was applied to evaluate the performance of the models. RESULTS: MLR analysis revealed that being male, age, alcohol consumption, and nighttime driving were more likely to increase the probability of severity outcomes. CONCLUSION: Being male, age, alcohol consumption, and nighttime driving are identified as potential risk factors contributing to the development of severity outcomes following traffic accidents.