A Hybrid of Structural Equation Modeling and Artificial Neural Networks to Predict Motorcyclists’ Injuries: A Conceptual Model in a Case-Control Study

  • Shila HASANZADEH Road Traffic Injury Research Center, Tabriz University of Medical Sciences, Tabriz, Iran
  • Mohammad ASGHARIJAFARABADI Mail 1. Road Traffic Injury Research Center, Tabriz University of Medical Sciences, Tabriz, Iran 2. Department of Statistics and Epidemiology, Faculty of Health, Tabriz University of Medical Sciences, Tabriz, Iran
  • Homayoun SADEGHI-BAZARGANI 1. Road Traffic Injury Research Center, Tabriz University of Medical Sciences, Tabriz, Iran 2. Department of Statistics and Epidemiology, Faculty of Health, Tabriz University of Medical Sciences, Tabriz, Iran
Keywords:
Motorcyclists, Traffic injury, Structural equation modeling, Neural networks

Abstract

 

Background: To model, the predictors of injuries caused the hospitalization of motorcyclists using a hybrid structural equation modeling-artificial neural network (SEM-ANN) considering a conceptual model.

Methods: In this case-control study, 300 cases and 156 controls were enrolled using a cluster random sampling. The cases were selected among injured motorcyclists in refereed to Imam Reza Hospital and Tabriz Shohada Hospital, Tabriz, Iran since Mar 2013. The predictability of injury by motorcycle-riding behavior questionnaire (MRBQ), Attention-deficit/hyperactivity disorder (ADHD) along with its subscales and motorcycle related variables was modeled using SEM-ANN. By SEM, linear direct and indirect relationships were assessed. To improve the SEM, the ANN was utilized sequentially to account for the nonlinear and interaction effects that is not supported by SEM.

Results: The predictors of injury were: MRBQ, ADHD, and its subscales, marital status, education level, riding for fun, engine volume, hyper active child, dark hour riding, cell phone answering, driving license (All P less than 0.05). In addition, the findings reveal the Mediating role of MRBQ for the relationship between underlying predictors and injury. Furthermore, ANN showed higher specificity (95.45 vs.77.88) and accuracy (90.76 vs.79.94) than usual SEM which lead us to introduce the second and third order effect of MRBQ into the modified SEM.

Conclusion: The hybrid model provided results that are more accurate; considering the results of the modeling, having intervention programs on ADHD motorcyclists, those have the hyperactive child, and those who answer their cell phones while driving, and improving the motorcyclists’ goal is highly recommended.

References

1. Wells S, Mullin B, Norton R, et al (2004). Motorcycle rider conspicuity and crash related injury: case-control study. BMJ, 328(7444):857.
2. Hair JF, Ringle CM, Sarstedt M (2013). Partial least squares structural equation modeling: Rigorous applications, better results and higher acceptance. Long Range Planning, 46(1-2):1-12.
3. Mahdian M, Sehat M, Fazel MR, et al (2015). Epidemiology of urban traffic accident victims hospitalized more than 24 hours in a level III trauma center, Kashan county, Iran, during 2012-2013. Arch Trauma Res, 4 (2): e28465.
4. Ghorbani A (2011). Nabavi fard H, Khoshhal M, Hosseini H.[Costs imposed on the effects of mortality due to traffic accidents (Sabzevar)(Persian)]. Traffic Management Studies, 20:49-58.
5. Mahdieh Rad AL, Ansari-Moghaddam A, Mohammadi M, et al (2016). The pattern of road traffic crashes in South East Iran. Glob J Health Sci, 8(9): 149–158.
6. Alinia S, Khankeh H, Maddah SSB, Negarandeh R (2015). Barriers of pre-hospital services in road traffic injuries in Tehran: the viewpoint of service providers. Int J Community Based Nurs Midwifery, 3(4): 272–282.
7. ZamaniAlaviche F NS ME MA, Ahmadi F,Ghofranipour F,Tvafiyan SS, (2010). Experienced motorcyclists from risky behaviors: a qualitative research. Quarterly Journal, 9:269-78.
8. ARF GBG (2014). Relationship between attitude, personality traits and perceived control source with a variety of driving behaviors. Journal of Health and Development, 3: 48-61.
9. Motevalian SA, Asadi-Lari M, Rahimi H, Eftekhar M (2011). Validation of a persian version of motorcycle rider behavior questionnaire. Ann Adv Automot Med,55:91-98.
10. Barkley RA, Guevremont DC, Anastopoulos AD, et al (1993). Driving-related risks and outcomes of attention deficit hyperactivity disorder in adolescents and young adults: a 3-to 5-year follow-up survey. Pediatrics, 92(2):212-8.
11. Wiegmann DA, Shappell SA (2017). A human error approach to aviation accident analysis: The human factors analysis and classification system. ed. Routledge.
12. Sakashita C, Senserrick T, Lo S, et al (2014). The Motorcycle Rider Behavior Questionnaire: Psychometric properties and application amongst novice riders in Australia. Transportation Research Part F: Traffic Psychology and Behaviour, 22:126-139.
13. Sadeghi-Bazargani H, Abedi L, Mahini M, et al (2015). Adult attention-deficit hyperactivity disorder, risky behaviors, and motorcycle injuries: a case-control study. Neuropsychiatr Dis Treat, 11:2049-54.
14. Babajanpour M, Jafarabadi MA, Bazargani HS (2017). Predictive ability of underlying factors of motorcycle rider behavior: an application of logistic quantile regression for bounded outcomes. Health Promot Perspect, 7(4): 230–237.
15. Buckler F, Hennig-Thurau T (2008). Identifying hidden structures in marketing's structural models through universal structure modeling. Marketing ZFP, 30:47-66.
16. Albashrawi M, Kartal H, Oztekin A, Motiwalla L (2017). The Impact of Subjective and Objective Experience on Mobile Banking Usage: An Analytical Approach. DOI: 10.24251/HICSS.2017.137.
17. Chong AY-L (2013). A two-staged SEM-neural network approach for understanding and predicting the determinants of m-commerce adoption. Expert Systems with Applications, 40:1240-1247.
18. Sharma SK, Gaur A, Saddikuti V, Rastogi A (2017). Structural equation model (SEM)-neural network (NN) model for predicting quality determinants of e-learning management systems. Behav Inf Technol, 36:1053-1066.
19. Weston R, Gore Jr PA (2006). A brief guide to structural equation modeling. The Counseling Psychologist, 34:719-751.
20. Sadeghi-Bazargani H, Amiri S, Hamraz S, et al (2014). Validity and reliability of the Persian version of Conner’s adult ADHD rating scales: observer and self-report screening versions. Journal of Clinical Research & Governance, 3:42-47.
21. Minsky M, Papert SA (2017). Perceptrons: An introduction to computational geometry. ed. MIT press.
22. Tomić J, Bogojević N, Šoškić Z (2018). Application of Artificial Neural Network to Prediction of Traffic Noise Levels in the City of Niš, Serbia. In: Acoustics and Vibration of Mechanical Structures—AVMS-2017. Ed(s): Springer, pp. 91-98.
23. Hamad K, Khalil MA, Shanableh A (2017). Modeling roadway traffic noise in a hot climate using artificial neural networks. Transportation Research Part D: Transport and Environment, 53:161-177.
24. Lee J-Y, Chung J-H, Son B (2008). Analysis of traffic accident size for Korean highway using structural equation models. Accident Analysis & Prevention, 40:1955-1963.
25. Fyhri A, Klæboe R (2009). Road traffic noise, sensitivity, annoyance and self-reported health—A structural equation model exercise. Enviro Int, 35:91-97.
26. Vaa T (2014). ADHD and relative risk of accidents in road traffic: A meta-analysis. Accid Anal Prev, 62:415-25.
27. Hechtman L, Weiss G, Perlman T (1984). Young adult outcome of hyperactive children who received long-term stimulant treatment. J Am Acad Child Psychiatry, 23(3):261-9.
28. Gilasi m g, moazzami goodarzi zabihollah, kakayi hojjatollah, (2013). Using Factor Analysis and Modeling In the study of knowledge, Attitude and Practice of Pedestrians in Kashan City For guidance on driving regulations in 2007. Journal of Ilam University of Medical Sciences, 5:37-42.
29. Moradi Y G (2007). Risk Factors Risks and Driving Accidents Related to Motorcyclists in Kashan. Quarterly Journal of School of Public Health and Institute of Health Research,, 5:57-68.
30. Aghamolaei T, Tavafian SS, Madani A (2011). Prediction of helmet use among Iranian motorcycle drivers: an application of the health belief model and the theory of planned behavior. Traffic Inj Prev, 12(3):239-43.
31. Horswill MS, Helman S (2003). A behavioral comparison between motorcyclists and a matched group of non-motorcycling car drivers: factors influencing accident risk. Accid Anal Prev, 35(4):589-97.
32. Paleti R, Eluru N, Bhat CR (2010). Examining the influence of aggressive driving behavior on driver injury severity in traffic crashes. Accid Anal Prev, 42(6):1839-54.
33. Kim K, Timm N (2006). Univariate and multivariate general linear models: theory and applications with SAS. ed. Chapman and Hall/CRC.
34. Lardelli-Claret P, Jimenez-Moleon JJ, de Dios Luna-del-Castillo J et al (2005). Driver dependent factors and the risk of causing a collision for two wheeled motor vehicles. Inj Prev, 11(4): 225–231.
35. Peden M, Scurfield R, Sleet D, et al (2004) World report on road traffic injury prevention. World Health Organization Geneva.
Published
2020-10-27
How to Cite
1.
HASANZADEH S, ASGHARIJAFARABADI M, SADEGHI-BAZARGANI H. A Hybrid of Structural Equation Modeling and Artificial Neural Networks to Predict Motorcyclists’ Injuries: A Conceptual Model in a Case-Control Study. Iran J Public Health. 49(11):2194-2204.
Section
Original Article(s)