{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:25:35Z","timestamp":1787012735649,"version":"build-2736575974"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-55751-y","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:05:08Z","timestamp":1780729508000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparative evaluation of XGBoost, TabNet, and FT transformer models for fatal crash prediction under extreme class imbalance"],"prefix":"10.1038","volume":"16","author":[{"given":"Veysel","family":"Gider","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serdar","family":"Ekinci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davut","family":"Izci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Islam","family":"Gokalp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mostafa","family":"Rashdan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Salman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"key":"55751_CR1","unstructured":"World Health Organization. Number of road traffic deaths. (2026) https:\/\/www.who.int\/data\/gho\/data\/themes\/road-safety. Accessed 4 Jan 2026"},{"key":"55751_CR2","unstructured":"World Health Organization. Road Traffic Injuries [Fact Sheet]; World Health Organization: Geneva, Switzerland. (2023). https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/road-traffic-injuries. Accessed 4 Jan 2026."},{"key":"55751_CR3","doi-asserted-by":"publisher","first-page":"106157","DOI":"10.1016\/j.aap.2021.106157","volume":"157","author":"C Wang","year":"2021","unstructured":"Wang, C., Xie, Y., Huang, H. & Liu, P. A review of surrogate safety measures and their applications in connected and automated vehicles safety modeling. Accid. Anal. Prev. 157, 106157. https:\/\/doi.org\/10.1016\/j.aap.2021.106157 (2021).","journal-title":"Accid. Anal. Prev."},{"key":"55751_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.amar.2024.100333","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Wang, C. & Xie, Y. Modeling the risk of single-vehicle run-off-road crashes on horizontal curves using connected vehicle data. Analytic Methods Accid. Res. 43 : 100333. https:\/\/doi.org\/10.1016\/j.amar.2024.100333 (2024)."},{"key":"55751_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., Xie, Y., Xu, S., Zhao, L. & Wang, C. Trade-offs between safety and volatility in driving interactions: Evidence from a connected vehicle pilot study. In 2025 IEEE Intelligent Vehicles Symposium (IV) (pp. 2089\u20132095). IEEE. . https:\/\/doi.org\/10.1109\/IV64158.2025.11097600 (2025)","DOI":"10.1109\/IV64158.2025.11097600"},{"key":"55751_CR6","doi-asserted-by":"publisher","first-page":"100370","DOI":"10.1016\/j.amar.2025.100370","volume":"45","author":"Y Chen","year":"2025","unstructured":"Chen, Y. et al. Time-dependent effect of advanced driver assistance systems on driver behavior based on connected vehicle data. Analytic Methods Accid. Res. 45, 100370. https:\/\/doi.org\/10.1016\/j.amar.2025.100370 (2025).","journal-title":"Analytic Methods Accid. Res."},{"issue":"2","key":"55751_CR7","doi-asserted-by":"publisher","first-page":"828","DOI":"10.3390\/app12020828","volume":"12","author":"T Bokaba","year":"2022","unstructured":"Bokaba, T., Doorsamy, W. & Paul, B. S. Comparative study of machine learning classifiers for modelling road traffic crashes. Appl. Sci. 12 (2), 828 (2022).","journal-title":"Appl. Sci."},{"issue":"1","key":"55751_CR8","doi-asserted-by":"publisher","first-page":"27468","DOI":"10.1038\/s41598-025-10970-7","volume":"15","author":"AM Mostafa","year":"2025","unstructured":"Mostafa, A. M. et al. AI-based prediction of traffic crash severity for improving road safety and transportation efficiency. Sci. Rep. 15 (1), 27468. https:\/\/doi.org\/10.1038\/s41598-025-10970-7 (2025).","journal-title":"Sci. Rep."},{"key":"55751_CR9","doi-asserted-by":"publisher","first-page":"108017","DOI":"10.1016\/j.aap.2025.108017","volume":"215","author":"J Xiang","year":"2025","unstructured":"Xiang, J., Wang, Z., Chen, Y., Meng, Z. & Wang, J. Joint analysis of crash injury severities for autonomous and conventional vehicles in mixed traffic environments: Application of random parameter bivariate probit model. Crash Anal. Prev. 215, 108017. https:\/\/doi.org\/10.1016\/j.aap.2025.108017 (2025).","journal-title":"Crash Anal. Prev."},{"issue":"19","key":"55751_CR10","doi-asserted-by":"publisher","first-page":"10417","DOI":"10.3390\/app151910417","volume":"15","author":"C Wang","year":"2025","unstructured":"Wang, C. & Serre, T. A hybrid approach to investigating factors associated with crash injury severity: Integrating interpretable machine learning with logit model. Appl. Sci. 15 (19), 10417. https:\/\/doi.org\/10.3390\/app151910417 (2025).","journal-title":"Appl. Sci."},{"issue":"2","key":"55751_CR11","doi-asserted-by":"publisher","first-page":"838","DOI":"10.3390\/app15020838","volume":"15","author":"R Alsaleh","year":"2025","unstructured":"Alsaleh, R., Walia, K., Moshiri, G. & Alsaleh, Y. T. Traffic Collision Severity Modeling Using Multi-Level Multinomial Logistic Regression Model. Appl. Sci. 15 (2), 838. https:\/\/doi.org\/10.3390\/app15020838 (2025).","journal-title":"Appl. Sci."},{"issue":"1","key":"55751_CR12","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s41062-025-02409-9","volume":"11","author":"M Awad","year":"2026","unstructured":"Awad, M., Moussa, G. S., Wahaballa, A. M. & Younes, H. A state-of-the-art review of injury severity analysis in traffic crashes: toward a generalized modeling framework. Innovative Infrastructure Solutions. 11 (1), 19. https:\/\/doi.org\/10.1007\/s41062-025-02409-9 (2026).","journal-title":"Innovative Infrastructure Solutions"},{"issue":"3","key":"55751_CR13","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1108\/JICV-04-2022-0012","volume":"5","author":"Q Yuan","year":"2022","unstructured":"Yuan, Q., Xu, X., Wang, T. & Chen, Y. Investigating safety and liability of autonomous vehicles: Bayesian random parameter ordered probit model analysis. J. Intell. connected Veh. 5 (3), 199\u2013205. https:\/\/doi.org\/10.1108\/JICV-04-2022-0012 (2022).","journal-title":"J. Intell. connected Veh."},{"issue":"8","key":"55751_CR14","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1177\/03611981231157716","volume":"2677","author":"T Wang","year":"2023","unstructured":"Wang, T. et al. Factors associated with the severity of motor vehicle crashes involving electric motorcycles and electric bicycles: A random parameters logit approach with heterogeneity in means. Transp. Res. Rec. 2677 (8), 691\u2013704. https:\/\/doi.org\/10.1177\/03611981231157716 (2023).","journal-title":"Transp. Res. Rec."},{"issue":"1","key":"55751_CR15","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1007\/s10791-025-09759-z","volume":"28","author":"AO Tibetan","year":"2025","unstructured":"Tibetan, A. O. & Ojekemi, O. S. An enhanced sine cosine algorithm based light gradient boosting machine for occupation injury outcome prediction. Discover Comput. 28 (1), 236. https:\/\/doi.org\/10.1007\/s10791-025-09759-z (2025).","journal-title":"Discover Comput."},{"issue":"1","key":"55751_CR16","doi-asserted-by":"publisher","first-page":"29420","DOI":"10.1038\/s41598-025-15388-9","volume":"15","author":"FE Ar\u00e9valo-Cordovilla","year":"2025","unstructured":"Ar\u00e9valo-Cordovilla, F. E. & Pe\u00f1a, M. Evaluating ensemble models for fair and interpretable prediction in higher education using multimodal data. Sci. Rep. 15 (1), 29420. https:\/\/doi.org\/10.1038\/s41598-025-15388-9 (2025).","journal-title":"Sci. Rep."},{"issue":"2","key":"55751_CR17","doi-asserted-by":"publisher","first-page":"531","DOI":"10.3390\/s25020531","volume":"25","author":"M Trigka","year":"2025","unstructured":"Trigka, M. & Dritsas, E. A comprehensive survey of deep learning approaches in image processing. Sensors 25 (2), 531. https:\/\/doi.org\/10.3390\/s25020531 (2025).","journal-title":"Sensors"},{"issue":"7","key":"55751_CR18","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1111\/mice.13357","volume":"40","author":"PF Zhang","year":"2025","unstructured":"Zhang, P. F. et al. Natural language processing-based deep transfer learning model across diverse tabular datasets for bond strength prediction of composite bars in concrete. Computer Aided Civil Infrastructure Eng. 40 (7), 917\u2013939. https:\/\/doi.org\/10.1111\/mice.13357 (2025).","journal-title":"Computer Aided Civil Infrastructure Eng."},{"key":"55751_CR19","doi-asserted-by":"publisher","unstructured":"Arik, S. \u00d6. & Pfister, T. Tabnet: Attentive interpretable tabular learning. In Proceedings of the AAAI conference on artificial intelligence. 35(8), pp. 6679\u20136687. https:\/\/doi.org\/10.1609\/aaai.v35i8.16826 (2021)","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"55751_CR20","doi-asserted-by":"publisher","first-page":"107115","DOI":"10.1016\/j.rineng.2025.107115","volume":"28","author":"X Wang","year":"2025","unstructured":"Wang, X. et al. Research on FT-transformer-based intelligent discrimination model for roof stability classification of retreating coal roadways. Results Eng. 28, 107115. https:\/\/doi.org\/10.1016\/j.rineng.2025.107115 (2025).","journal-title":"Results Eng."},{"key":"55751_CR21","doi-asserted-by":"publisher","unstructured":"Rezashoar, S., Kashi, E. & Saeidi, S. Comparison of machine learning algorithms for predicting traffic crash severity (case study: United Kingdom from 2010 to 2014). Int. J. Crashworthiness. 1\u201310. https:\/\/doi.org\/10.1080\/13588265.2025.2507474 (2025).","DOI":"10.1080\/13588265.2025.2507474"},{"issue":"1","key":"55751_CR22","doi-asserted-by":"publisher","first-page":"21913","DOI":"10.1038\/s41598-025-08005-2","volume":"15","author":"AK Mengistu","year":"2025","unstructured":"Mengistu, A. K. et al. Predicting car crash severity in Northwest Ethiopia: a machine learning approach leveraging driver, environmental, and road conditions. Sci. Rep. 15 (1), 21913. https:\/\/doi.org\/10.1038\/s41598-025-08005-2 (2025).","journal-title":"Sci. Rep."},{"issue":"1","key":"55751_CR23","doi-asserted-by":"publisher","first-page":"e363","DOI":"10.1002\/sta4.363","volume":"10","author":"J Altosaar","year":"2021","unstructured":"Altosaar, J., Ranganath, R. & Tansey, W. RankFromSets: Scalable set recommendation with optimal recall. Stat 10 (1), e363. https:\/\/doi.org\/10.1002\/sta4.363 (2021).","journal-title":"Stat"},{"key":"55751_CR24","doi-asserted-by":"publisher","unstructured":"Alicioglu, G., Sun, B. & Ho, S. S. Assessing crash risk using ordinal regression and multinomial logistic regression data generation. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1\u20138). IEEE. https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9207105 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207105"},{"issue":"3","key":"55751_CR25","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/S0001-4575(01)00028-8","volume":"34","author":"KM Kockelman","year":"2002","unstructured":"Kockelman, K. M. & Kweon, Y. J. Driver injury severity: an application of ordered probit models. Crash Anal. Prev. 34 (3), 313\u2013321. https:\/\/doi.org\/10.1016\/S0001-4575(01)00028-8 (2002).","journal-title":"Crash Anal. Prev."},{"issue":"4","key":"55751_CR26","doi-asserted-by":"publisher","first-page":"353","DOI":"10.3846\/16484142.2011.635465","volume":"26","author":"MM Kunt","year":"2011","unstructured":"Kunt, M. M., Aghayan, I. & Noii, N. Prediction for traffic crash severity: comparing the artificial neural network, genetic algorithm, combined genetic algorithm and pattern search methods. Transport 26 (4), 353\u2013366. https:\/\/doi.org\/10.3846\/16484142.2011.635465 (2011).","journal-title":"Transport"},{"issue":"6","key":"55751_CR27","doi-asserted-by":"publisher","first-page":"7331","DOI":"10.1007\/s12652-022-04441-4","volume":"14","author":"S AlKheder","year":"2023","unstructured":"AlKheder, S., AlRukaibi, F. & Aiash, A. Support vector machine (SVM), random forest (RF), artificial neural network (ANN) and Bayesian network for prediction and analysis of GCC traffic crashes. J. Ambient Intell. Humaniz. Comput. 14 (6), 7331\u20137339. https:\/\/doi.org\/10.1007\/s12652-022-04441-4 (2023).","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"issue":"3","key":"55751_CR28","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.3390\/su14031729","volume":"14","author":"M Yan","year":"2022","unstructured":"Yan, M. & Shen, Y. Traffic crash severity prediction based on random forest. Sustainability 14 (3), 1729. https:\/\/doi.org\/10.3390\/su14031729 (2022).","journal-title":"Sustainability"},{"key":"55751_CR29","doi-asserted-by":"publisher","unstructured":"Obasi, I. C. & Benson, C. Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic crashes. Heliyon 9 (8). https:\/\/doi.org\/10.1016\/j.heliyon.2023.e18812 (2023).","DOI":"10.1016\/j.heliyon.2023.e18812"},{"issue":"4","key":"55751_CR30","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3390\/safety11040121","volume":"11","author":"N Goubraim","year":"2025","unstructured":"Goubraim, N., Elassad, Z. E. A., Mousannif, H. & Ameksa, M. Boosting Traffic Crash Prediction Performance with Ensemble Techniques and Hyperparameter Tuning. Safety 11 (4), 121. https:\/\/doi.org\/10.3390\/safety11040121 (2025).","journal-title":"Safety"},{"issue":"1","key":"55751_CR31","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s40030-022-00696-4","volume":"104","author":"S Koramati","year":"2023","unstructured":"Koramati, S., Mukherjee, A., Majumdar, B. B. & Kar, A. Development of crash prediction model using artificial neural network (ANN): a case study of Hyderabad, India. J. Institution Eng. (India): Ser. A. 104 (1), 63\u201380. https:\/\/doi.org\/10.1007\/s40030-022-00696-4 (2023).","journal-title":"J. Institution Eng. (India): Ser. A"},{"issue":"1","key":"55751_CR32","doi-asserted-by":"publisher","first-page":"20024","DOI":"10.1038\/s41598-022-24476-z","volume":"12","author":"M Iranmanesh","year":"2022","unstructured":"Iranmanesh, M., Seyedabrishami, S. & Moridpour, S. Identifying high crash risk segments in rural roads using ensemble decision tree-based models. Sci. Rep. 12 (1), 20024. https:\/\/doi.org\/10.1038\/s41598-022-24476-z (2022).","journal-title":"Sci. Rep."},{"issue":"7","key":"55751_CR33","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1007\/s40999-025-01108-x","volume":"23","author":"K Aziz","year":"2025","unstructured":"Aziz, K., Chen, F. & Khattak, A. A Novel Bayesian Optimized-Combined Kernel & Tree Boost Approach for Road Traffic Crash Severity Analysis. Int. J. Civil Eng. 23 (7), 1483\u20131501. https:\/\/doi.org\/10.1007\/s40999-025-01108-x (2025).","journal-title":"Int. J. Civil Eng."},{"key":"55751_CR34","doi-asserted-by":"publisher","first-page":"193113","DOI":"10.1109\/ACCESS.2025.3630827","volume":"13","author":"N Hamdan","year":"2025","unstructured":"Hamdan, N. & Sipos, T. Predicting Crash Severity on the Hungarian Road Network: An Ensemble Machine Learning Approach With Resampling and Hyperparameter Tuning. IEEE Access. 13, 193113\u2013193124. https:\/\/doi.org\/10.1109\/ACCESS.2025.3630827 (2025).","journal-title":"IEEE Access."},{"issue":"6","key":"55751_CR35","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.28991\/CEJ-2024-010-06-011","volume":"10","author":"W Laphrom","year":"2024","unstructured":"Laphrom, W. et al. XGBoost-SHAP and unobserved heterogeneity modelling of temporal multivehicle truck-involved crash severity patterns. Civil Eng. J. 10 (6), 1890\u20131908. https:\/\/doi.org\/10.28991\/CEJ-2024-010-06-011 (2024).","journal-title":"Civil Eng. J."},{"issue":"13","key":"55751_CR36","doi-asserted-by":"publisher","first-page":"9878","DOI":"10.3390\/su15139878","volume":"15","author":"M Alrumaidhi","year":"2023","unstructured":"Alrumaidhi, M., Farag, M. M. & Rakha, H. A. Comparative analysis of parametric and non-parametric data-driven models to predict road crash severity among elderly drivers using synthetic resampling techniques. Sustainability 15 (13), 9878. https:\/\/doi.org\/10.3390\/su15139878 (2023).","journal-title":"Sustainability"},{"key":"55751_CR37","doi-asserted-by":"publisher","first-page":"100040","DOI":"10.1016\/j.eastsj.2021.100040","volume":"7","author":"ME Shaik","year":"2021","unstructured":"Shaik, M. E., Islam, M. M. & Hossain, Q. S. A review on neural network techniques for the prediction of road traffic crash severity. Asian Transp. Stud. 7, 100040. https:\/\/doi.org\/10.1016\/j.eastsj.2021.100040 (2021).","journal-title":"Asian Transp. Stud."},{"issue":"2","key":"55751_CR38","doi-asserted-by":"publisher","first-page":"29","DOI":"10.3390\/safety5020029","volume":"5","author":"M Vila\u00e7a","year":"2019","unstructured":"Vila\u00e7a, M., Macedo, E. & Coelho, M. C. A rare event modelling approach to assess injury severity risk of vulnerable road users. Safety 5 (2), 29. https:\/\/doi.org\/10.3390\/safety5020029 (2019).","journal-title":"Safety"},{"issue":"20","key":"55751_CR39","doi-asserted-by":"publisher","first-page":"9534","DOI":"10.3390\/app11209534","volume":"11","author":"D Kim","year":"2021","unstructured":"Kim, D., Jung, S. & Yoon, S. Risk prediction for winter road crashes on expressways. Appl. Sci. 11 (20), 9534. https:\/\/doi.org\/10.3390\/app11209534 (2021).","journal-title":"Appl. Sci."},{"key":"55751_CR40","doi-asserted-by":"publisher","first-page":"106090","DOI":"10.1016\/j.aap.2021.106090","volume":"154","author":"MA Rahim","year":"2021","unstructured":"Rahim, M. A. & Hassan, H. M. A deep learning based traffic crash severity prediction framework. Crash Anal. Prev. 154, 106090. https:\/\/doi.org\/10.1016\/j.aap.2021.106090 (2021).","journal-title":"Accident Anal. Prev."},{"issue":"1","key":"55751_CR41","doi-asserted-by":"publisher","first-page":"32568","DOI":"10.1038\/s41598-025-13484-4","volume":"15","author":"F Alanazi","year":"2025","unstructured":"Alanazi, F., Umar, I. K., Yosri, A. M. & Okail, M. A. Comparative evaluation of deep learning and traditional models for predicting traffic crash severity in Saudi Arabia. Sci. Rep. 15 (1), 32568. https:\/\/doi.org\/10.1038\/s41598-025-13484-4 (2025).","journal-title":"Sci. Rep."},{"issue":"6","key":"55751_CR42","doi-asserted-by":"publisher","first-page":"2872","DOI":"10.1109\/TAI.2023.3328578","volume":"5","author":"N Bhardwaj","year":"2023","unstructured":"Bhardwaj, N., Pal, A. & Das, D. Adaptive context based road crash risk prediction using spatio-temporal deep learning. IEEE Trans. Artif. Intell. 5 (6), 2872\u20132883. https:\/\/doi.org\/10.1109\/TAI.2023.3328578 (2023).","journal-title":"IEEE Trans. Artif. Intell."},{"key":"55751_CR43","doi-asserted-by":"publisher","first-page":"860805","DOI":"10.3389\/fbuil.2022.860805","volume":"8","author":"BW Al-Mistarehi","year":"2022","unstructured":"Al-Mistarehi, B. W., Alomari, A. H., Imam, R. & Mashaqba, M. Using machine learning models to forecast severity level of traffic crashes by R Studio and ArcGIS. Front. built Environ. 8, 860805. https:\/\/doi.org\/10.3389\/fbuil.2022.860805 (2022).","journal-title":"Front. built Environ."},{"key":"55751_CR44","doi-asserted-by":"publisher","first-page":"105405","DOI":"10.1016\/j.aap.2019.105405","volume":"136","author":"AB Parsa","year":"2020","unstructured":"Parsa, A. B., Movahedi, A., Taghipour, H., Derrible, S. & Mohammadian, A. K. Toward safer highways, application of XGBoost and SHAP for real-time crash detection and feature analysis. Crash Anal. Prev. 136, 105405. https:\/\/doi.org\/10.1016\/j.aap.2019.105405 (2020).","journal-title":"Accident Anal. Prev."},{"key":"55751_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-025-0032-7","author":"M Tu","year":"2025","unstructured":"Tu, M. et al. Traffic Crash Prediction Considering Imbalanced Data: An Interpretable Machine Learning Model. Int. J. Control Autom. Syst. 23 (10), 3182\u20133196. https:\/\/doi.org\/10.1007\/s12555-025-0032-7 (2025)"},{"issue":"1","key":"55751_CR46","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/TNSRE.2019.2948798","volume":"28","author":"W Rasheed","year":"2019","unstructured":"Rasheed, W. & Tang, T. B. Anomaly detection of moderate traumatic brain injury using auto-regularized multi-instance one-class SVM. IEEE Trans. Neural Syst. Rehabil. Eng. 28 (1), 83\u201393. https:\/\/doi.org\/10.1109\/TNSRE.2019.2948798 (2019).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"issue":"3","key":"55751_CR47","doi-asserted-by":"publisher","first-page":"347","DOI":"10.3311\/PPtr.40369","volume":"53","author":"N Hamdan","year":"2025","unstructured":"Hamdan, N. & Sipos, T. Advancements in Machine Learning for Traffic Crash Severity Prediction: A Comprehensive Review. Periodica Polytech. Transp. Eng. 53 (3), 347\u2013355. https:\/\/doi.org\/10.3311\/PPtr.40369 (2025).","journal-title":"Periodica Polytech. Transp. Eng."},{"issue":"10","key":"55751_CR48","doi-asserted-by":"publisher","first-page":"5388","DOI":"10.1109\/TKDE.2023.3333824","volume":"36","author":"G Jin","year":"2023","unstructured":"Jin, G. et al. Spatio-temporal graph neural networks for predictive learning in urban computing: A survey. IEEE Trans. Knowl. Data Eng. 36 (10), 5388\u20135408. https:\/\/doi.org\/10.1109\/TKDE.2023.3333824 (2023).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"10","key":"55751_CR49","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1080\/08839514.2021.1935588","volume":"35","author":"R De Medrano","year":"2021","unstructured":"De Medrano, R. & Aznarte, J. L. A new spatio-temporal neural network approach for traffic crash forecasting. Appl. Artif. Intell. 35 (10), 782\u2013801. https:\/\/doi.org\/10.1080\/08839514.2021.1935588 (2021).","journal-title":"Appl. Artif. Intell."},{"key":"55751_CR50","doi-asserted-by":"publisher","unstructured":"Han, W., Zhou, X., Zhang, A., Zhao, L. & Pan, G. AE-TabNet: A Two-stage Framework for Traffic Crash Severity Prediction with Imbalanced Data. In Proceedings of the 2024 2nd International Conference on Frontiers of Intelligent Manufacturing and Automation (pp. 301\u2013306). https:\/\/doi.org\/10.1145\/3704558.3704581 (2024)","DOI":"10.1145\/3704558.3704581"},{"issue":"5","key":"55751_CR51","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1080\/19427867.2024.2398336","volume":"17","author":"Y Pei","year":"2025","unstructured":"Pei, Y., Wen, Y. & Pan, S. Traffic crash severity prediction based on interpretable deep learning model. Transp. Lett. 17 (5), 895\u2013909. https:\/\/doi.org\/10.1080\/19427867.2024.2398336 (2025).","journal-title":"Transp. Lett."},{"issue":"12","key":"55751_CR52","doi-asserted-by":"publisher","first-page":"157","DOI":"10.3390\/computers10120157","volume":"10","author":"D Santos","year":"2021","unstructured":"Santos, D., Saias, J., Quaresma, P. & Nogueira, V. B. Machine Learning Approaches to Traffic Crash Analysis and Hotspot Prediction. Computers 10 (12), 157. https:\/\/doi.org\/10.3390\/computers10120157 (2021).","journal-title":"Computers"},{"key":"55751_CR53","doi-asserted-by":"publisher","first-page":"106505","DOI":"10.1016\/j.aap.2021.106505","volume":"165","author":"OS Liang","year":"2022","unstructured":"Liang, O. S. & Yang, C. C. How are different sources of distraction associated with at-fault crashes among drivers of different age gender groups? Crash Anal. Prev. 165, 106505. https:\/\/doi.org\/10.1016\/j.aap.2021.106505 (2022).","journal-title":"Accident Anal. Prev."},{"issue":"1","key":"55751_CR54","doi-asserted-by":"publisher","first-page":"26566","DOI":"10.1038\/s41598-025-11835-9","volume":"15","author":"E Baki\u015f","year":"2025","unstructured":"Baki\u015f, E., Er\u00e7etin, M. A., Acar, E., G\u00f6kalp, \u0130. & Y\u0131lmaz, M. Prediction of traffic crashes trend with learning methods: a case study for Batman, Turkey. Sci. Rep. 15 (1), 26566. https:\/\/doi.org\/10.1038\/s41598-025-11835-9 (2025).","journal-title":"Sci. Rep."},{"issue":"3","key":"55751_CR55","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s00500-021-06532-4","volume":"26","author":"J Liu","year":"2022","unstructured":"Liu, J. Importance-SMOTE: a synthetic minority oversampling method for noisy imbalanced data. Soft. Comput. 26 (3), 1141\u20131163. https:\/\/doi.org\/10.1007\/s00500-021-06532-4 (2022).","journal-title":"Soft. Comput."},{"key":"55751_CR56","doi-asserted-by":"publisher","unstructured":"Chen, T. XGBoost: A Scalable Tree Boosting System. Cornell University. https:\/\/doi.org\/10.1145\/2939672.2939785 (2016)","DOI":"10.1145\/2939672.2939785"},{"key":"55751_CR57","doi-asserted-by":"publisher","first-page":"e832","DOI":"10.7717\/peerj-cs.832","volume":"7","author":"B Pes","year":"2021","unstructured":"Pes, B. & Lai, G. Cost-sensitive learning strategies for high-dimensional and imbalanced data: a comparative study. PeerJ Comput. Sci. 7, e832. https:\/\/doi.org\/10.7717\/peerj-cs.832 (2021).","journal-title":"PeerJ Comput. Sci."},{"issue":"1","key":"55751_CR58","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1186\/s40537-025-01313-4","volume":"12","author":"KM Sujon","year":"2025","unstructured":"Sujon, K. M., Hassan, R., Choi, K. & Samad, M. A. Accuracy, precision, recall, f1-score, or MCC? empirical evidence from advanced statistics, ML, and XAI for evaluating business predictive models. J. Big Data. 12 (1), 268. https:\/\/doi.org\/10.1186\/s40537-025-01313-4 (2025).","journal-title":"J. Big Data"},{"issue":"6","key":"55751_CR59","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1213\/ane.0000000000005362","volume":"132","author":"V Subramanian","year":"2021","unstructured":"Subramanian, V., Mascha, E. J. & Kattan, M. W. Developing a clinical prediction score: comparing prediction accuracy of integer scores to statistical regression models. Anesth. Analgesia. 132 (6), 1603\u20131613. https:\/\/doi.org\/10.1213\/ane.0000000000005362 (2021).","journal-title":"Anesth. Analgesia"},{"issue":"6","key":"55751_CR60","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1007\/s11222-021-10057-z","volume":"31","author":"G Hooker","year":"2021","unstructured":"Hooker, G., Mentch, L. & Zhou, S. Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance. Stat. Comput. 31 (6), 82. https:\/\/doi.org\/10.1007\/s11222-021-10057-z (2021).","journal-title":"Stat. Comput."},{"key":"55751_CR61","doi-asserted-by":"publisher","unstructured":"Bedane, T. T Road Traffic Accident Dataset of Addis Ababa City. Mendeley Data. V1 https:\/\/doi.org\/10.17632\/xytv86278f.1 (2020).","DOI":"10.17632\/xytv86278f.1"},{"key":"55751_CR62","unstructured":"Nguyen, S. Accident-Severity-Prediction (curated CSV release of the Road Traffic Accidents dataset). GitHub repository. https:\/\/github.com\/sonnguyen129\/Accident-Severity-Prediction (2022)"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55751-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55751-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55751-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:41:48Z","timestamp":1787010108000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55751-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":62,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["55751"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-55751-y","relation":{"references":[{"id-type":"doi","id":"10.1016\/j.amar.2024.100333","asserted-by":"subject"},{"id-type":"doi","id":"10.1007\/s12555-025-0032-7","asserted-by":"subject"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"7 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted using secondary administrative traffic crash records obtained from the Turkish Ministry of Interior, General Directorate of Security, upon an official written request submitted by Assoc. Prof. Dr. \u0130slam G\u00f6kalp (Batman University, Faculty of Engineering\u2013Architecture, Department of Civil Engineering) dated 25.09.2023. The requested dataset covered fatal and injury-related traffic crashes that occurred between 2013 and 2022 within the police jurisdiction area of the central district of Batman province and was officially provided to the university in Excel format for scientific and academic research purposes. The dataset consisted exclusively of retrospective and fully anonymized records and did not contain any personally identifiable information (such as names, national identification numbers, addresses, or contact details). No direct interaction with human participants was involved, and no interventions, experiments, or behavioral measurements were conducted. In accordance with national regulations and institutional guidelines governing the secondary use of anonymized administrative data, and because the study involved neither identifiable personal data nor prospective data collection from human subjects, the need to obtain formal ethical committee approval was waived by Batman University and the data-providing authority. For the same reasons, and due to the retrospective and anonymized nature of the dataset, the need to obtain informed consent from individual participants was also waived by the data-providing authority and the affiliated institution. All procedures performed in this study complied with applicable institutional and national ethical standards for research involving secondary administrative data.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25809"}}