Cyclist crash severity modeling: A hybrid approach of XGBoost-SHAP and random parameters logit with heterogeneity in means and variances
Journal of Safety Research · 2025-07 · 93 · 373-398
DOI: 10.1016/j.jsr.2025.04.003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Safety Research, 2025-07. Verfasst von Antonella Scarano und 5 weiteren Autor:innen. Beteiligte Einrichtung: University of Naples Federico II, Department of Civil, Architectural and Environmental Engineering, Via Claudio 21, 80125 Naples, Italy. Electronic a…. Hauptthemen laut MEDLINE: Accidents, Traffic, Bicycling, Models, Statistical. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 118 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
INTRODUCTION: Across the globe, policymakers are focusing on boosting sustainable transport options, notably cycling, to foster eco-friendly urban environments. However, the persistent safety challenges cyclists face continues to hinder these efforts. METHOD: This research explores a novel hybrid methodology to investigate the determinants of cyclist crash severity by combining eXtreme Gradient Boosting (XGBoost) with SHapley Additive exPlanations (SHAP) and a random parameters logit model with heterogeneity in means and variances (RPLHMV). Using crash data from the Department for Transport covering crashes in Great Britain from 2016 to 2019, the research evaluates the methodology's effectiveness. The XGBoost-SHAP model reduced data dimensionality allowing the application of a robust statistical model, while the random parameters logit model with heterogeneity in means and variances captured heterogeneity in both means and variances. RESULTS: The statistical model identified 10 significant variables with fixed parameters for the fatal crashes, 22 significant variables for the serious injuries, and two indicator variables such as cyclist age ≤ 17 and overtaking as a manoeuvre for the second vehicle with statistically significant random parameters associated with serious injury outcomes. The relationships revealed by the logit framework were further examined using the XGBoost-SHAP, which provided deeper insights into the interactions between random and fixed parameters. The use of the hybrid approach allowed to achieve a very good R2 McFadden value of 0.52 for the RPLHMV, demonstrating the model's robustness. CONCLUSIONS: The hybrid approach not only provides a deeper understanding of crash severity dynamics but also helps in creating specific safety measures. PRACTICAL APPLICATIONS: This research can guide policymakers in identifying key factors and interactions that affect crash severity, leading to targeted safety improvements.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Naples Federico II, Department of Civil, Architectural and Environmental Engineering, Via Claudio 21, 80125 Naples, Italy. Electronic address: antonella.scarano@unina.it.
- University of Tehran, School of Civil Engineering, College of Engineering, Iran. Electronic address: matinsadeghi@ut.ac.ir.
- University of Naples Federico II, Department of Civil, Architectural and Environmental Engineering, Via Claudio 21, 80125 Naples, Italy. Electronic address: filomena.mauriello@unina.it.
- University of Naples Federico II, Department of Civil, Architectural and Environmental Engineering, Via Claudio 21, 80125 Naples, Italy. Electronic address: maria.rellariccardi@unina.it.
- University of Tehran, School of Civil Engineering, College of Engineering, Iran. Electronic address: kayvan.aghabayk@ut.ac.ir.
- University of Naples Federico II, Department of Civil, Architectural and Environmental Engineering, Via Claudio 21, 80125 Naples, Italy. Electronic address: alfonso.montella@unina.it.
Zitieren
APA
Scarano, A., Sadeghi, M., Mauriello, F., Riccardi, M. R., Aghabayk, K., & Montella, A. (2025). Cyclist crash severity modeling: A hybrid approach of XGBoost-SHAP and random parameters logit with heterogeneity in means and variances. Journal of Safety Research, 93, 373-398. https://doi.org/10.1016/j.jsr.2025.04.003
Vancouver
Scarano A, Sadeghi M, Mauriello F, Riccardi MR, Aghabayk K, Montella A. Cyclist crash severity modeling: A hybrid approach of XGBoost-SHAP and random parameters logit with heterogeneity in means and variances. Journal of Safety Research. 2025;93:373-398. doi:10.1016/j.jsr.2025.04.003
BibTeX
@article{Scarano2025,
author = {Scarano, Antonella and Sadeghi, Matin and Mauriello, Filomena and Riccardi, Maria Rella and Aghabayk, Kayvan and Montella, Alfonso},
title = {Cyclist crash severity modeling: A hybrid approach of XGBoost-SHAP and random parameters logit with heterogeneity in means and variances},
journal = {Journal of Safety Research},
year = {2025},
volume = {93},
pages = {373--398},
doi = {10.1016/j.jsr.2025.04.003}
}
EUVIMED