{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T18:15:47Z","timestamp":1783448147193,"version":"3.55.0"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017724","name":"Henan Provincial Department of Transportation","doi-asserted-by":"publisher","award":["2023SZDXK318"],"award-info":[{"award-number":["2023SZDXK318"]}],"id":[{"id":"10.13039\/100017724","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Subject and Specialty Construction Funding Project for Private Regular Institutions of Higher Education in Henan Province","award":["2023"],"award-info":[{"award-number":["2023"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To identify the key determinants of traffic injury risk and clarify the relative roles of built environment factors and crash-context factors, this study develops a traffic injury risk identification framework that integrates 5D built environment variables with non-5D factors, using traffic crash data collected in Changsha, Hunan Province, China, from 2017 to 2019. After data cleaning, screening, and spatial matching, a total of 9,743 valid samples were obtained, and injury occurrence in a crash was defined as a binary dependent variable. On this basis, three feature sets were constructed, including a 5D feature set, a non-5D feature set, and a combined 5D\u2009+\u2009non-5D feature set. Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) models were then developed and compared, and the best-performing model was further interpreted using the Shapley Additive Explanations (SHAP) method. The results showed that the combined 5D\u2009+\u2009non-5D feature set consistently outperformed the models using either the 5D or non-5D feature set alone, indicating that traffic injury risk arises from the joint influence of the built environment and immediate crash-context conditions. Among the three models, CatBoost achieved the best performance under the combined feature set and produced the highest receiver operating characteristic-area under the curve (ROC-AUC) value, demonstrating superior overall discriminative ability. The SHAP results further revealed that, within the combined CatBoost model, 5D variables accounted for a larger share of the model-based contribution than non-5D variables. However, given the relatively small improvement in accuracy after adding 5D variables, this finding should be interpreted as evidence of complementary explanatory information rather than as a dominant source of predictive performance. Distance to the nearest metro station, lighting condition, road network density, point of interest (POI) mix, and distance to the nearest bus stop were identified as the most influential factors. Further dependence analysis showed that a greater distance to the nearest metro station generally increased traffic injury risk, whereas higher road network density and greater POI mix were generally associated with lower injury risk. From the perspective of the interaction between 5D built environment characteristics and non-5D factors, this study reveals the multidimensional pathways through which traffic injury risk is shaped. The findings also confirm the effectiveness of the CatBoost\u2013SHAP framework for traffic injury risk identification and interpretation, and provide empirical support for urban traffic safety risk assessment, road environment optimization, and refined governance strategies.<\/jats:p>","DOI":"10.1371\/journal.pone.0353205","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T17:30:39Z","timestamp":1783445439000},"page":"e0353205","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effects of 5D built environment and non-built-environment factors on injury crash risk: An interpretable machine learning analysis"],"prefix":"10.1371","volume":"21","author":[{"given":"Wenfang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2184-2985","authenticated-orcid":true,"given":"Xingchen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"pone.0353205.ref001","doi-asserted-by":"crossref","first-page":"121","DOI":"10.3141\/2451-14","article-title":"Analysis of Traffic Injury Severity in Dhaka, Bangladesh","volume":"2451","author":"M Kamruzzaman","year":"2014","journal-title":"Transp Res Rec"},{"key":"pone.0353205.ref002","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.jth.2017.01.009","article-title":"Investigating injury severity risk factors in automobile crashes with predictive analytics and sensitivity analysis methods","volume":"4","author":"D Delen","year":"2017","journal-title":"J Transp Health"},{"issue":"3","key":"pone.0353205.ref003","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1080\/15389588.2019.1710834","article-title":"Comparative risk factor analyses on bi-level injury severity of taxi and private car crashes in Seoul, South Korea","volume":"21","author":"Y Noh","year":"2020","journal-title":"Traffic Inj Prev"},{"key":"pone.0353205.ref004","doi-asserted-by":"crossref","first-page":"105615","DOI":"10.1016\/j.aap.2020.105615","article-title":"Applying a joint model of crash count and crash severity to identify road segments with high risk of fatal and serious injury crashes","volume":"144","author":"AP Afghari","year":"2020","journal-title":"Accid Anal Prev"},{"issue":"21","key":"pone.0353205.ref005","doi-asserted-by":"crossref","DOI":"10.3390\/su142113858","article-title":"Injury Severity Analysis of Rear-End Crashes at Signalized Intersections","volume":"14","author":"M Sharafeldin","year":"2022","journal-title":"Sustainability"},{"issue":"17","key":"pone.0353205.ref006","doi-asserted-by":"crossref","first-page":"11126","DOI":"10.3390\/ijerph191711126","article-title":"Investigating the Risk Factors Associated with Injury Severity in Pedestrian Crashes in Santiago, Chile","volume":"19","author":"A Rampinelli","year":"2022","journal-title":"Int J Environ Res Public Health"},{"issue":"4","key":"pone.0353205.ref007","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1177\/0885412215595438","article-title":"Pedestrian safety and the built environment: a review of the risk factors","volume":"30","author":"P Stoker","year":"2015","journal-title":"J Plan Lit"},{"key":"pone.0353205.ref008","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.jsr.2020.07.004","article-title":"A conceptual framework to understand the role of built environment on traffic safety","volume":"75","author":"D Saha","year":"2020","journal-title":"J Safety Res"},{"key":"pone.0353205.ref009","doi-asserted-by":"crossref","first-page":"105244","DOI":"10.1016\/j.aap.2019.07.020","article-title":"Crash risk, crash exposure, and the built environment: A conceptual review","volume":"134","author":"LA Merlin","year":"2020","journal-title":"Accid Anal Prev"},{"key":"pone.0353205.ref010","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.apgeog.2016.06.005","article-title":"Influence of built environment on pedestrian crashes: A network-based GIS analysis","volume":"73","author":"D Dai","year":"2016","journal-title":"Appl Geogr"},{"key":"pone.0353205.ref011","doi-asserted-by":"crossref","first-page":"101129","DOI":"10.1016\/j.jth.2021.101129","article-title":"Building walkable and safe neighborhoods: Assessing the built environment characteristics for pedestrian safety in buffalo, NY","volume":"22","author":"L Yin","year":"2021","journal-title":"J Transp Health"},{"key":"pone.0353205.ref012","doi-asserted-by":"crossref","first-page":"106683","DOI":"10.1016\/j.aap.2022.106683","article-title":"A comprehensive analysis of the relationships between the built environment and traffic safety in the Dutch urban areas","volume":"172","author":"M Asadi","year":"2022","journal-title":"Accid Anal Prev"},{"issue":"5","key":"pone.0353205.ref013","doi-asserted-by":"crossref","first-page":"2641","DOI":"10.3390\/ijerph19052641","article-title":"Objective and Perceived Traffic Safety for Children: A Systematic Literature Review of Traffic and Built Environment Characteristics Related to Safe Travel","volume":"19","author":"Y Amiour","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"pone.0353205.ref014","doi-asserted-by":"crossref","first-page":"105621","DOI":"10.1016\/j.aap.2020.105621","article-title":"Does elderly safety matter? Associations between built environments and pedestrian crashes in Seoul, Korea","volume":"144","author":"S Lee","year":"2020","journal-title":"Accid Anal Prev"},{"issue":"4","key":"pone.0353205.ref015","doi-asserted-by":"crossref","first-page":"2280","DOI":"10.3390\/ijerph19042280","article-title":"The Influence of Built Environment Factors on Elderly Pedestrian Road Safety in Cities: The Experience of Madrid","volume":"19","author":"D G\u00e1lvez-P\u00e9rez","year":"2022","journal-title":"Int J Environ Res Public Health"},{"issue":"4","key":"pone.0353205.ref016","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1136\/injuryprev-2021-044459","article-title":"Child pedestrian and cyclist injuries, and the built and social environment across Canadian cities: the Child Active Transportation Safety and the Environment Study (CHASE)","volume":"28","author":"L Rothman","year":"2022","journal-title":"Inj Prev"},{"issue":"2","key":"pone.0353205.ref017","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1177\/03611981221108392","article-title":"Spatial analysis of relationships between intersection safety, the urban built environment, and average income level: a case study of Des Moines","volume":"2677","author":"D Okaidjah","year":"2023","journal-title":"Transp Res Rec"},{"issue":"11","key":"pone.0353205.ref018","doi-asserted-by":"crossref","first-page":"2367","DOI":"10.1080\/13658816.2023.2254362","article-title":"Uncovering the association between traffic crashes and street-level built-environment features using street view images","volume":"37","author":"S Hu","year":"2023","journal-title":"Int J Geograph Inform Sci"},{"issue":"4","key":"pone.0353205.ref019","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1080\/10095020.2023.2261767","article-title":"ST-GWLR: combining geographically weighted logistic regression and spatiotemporal hotspot trend analysis to explore the effect of built environment on traffic crash","volume":"27","author":"X Qu","year":"2023","journal-title":"Geo-spatial Inform Sci"},{"key":"pone.0353205.ref020","doi-asserted-by":"crossref","first-page":"103737","DOI":"10.1016\/j.apgeog.2025.103737","article-title":"Traffic safety in relation to multidimensional street network and land use features: A nonlinear analysis with population heterogeneity","volume":"183","author":"C Ling","year":"2025","journal-title":"Appl Geogr"},{"issue":"5","key":"pone.0353205.ref021","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1080\/15389588.2025.2541915","article-title":"Nonlinear effects of built environment on road traffic safety: A multi-scale perspective","volume":"27","author":"N Wu","year":"2026","journal-title":"Traffic Inj Prev"},{"key":"pone.0353205.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2021\/3771640","article-title":"Analyzing Accident Injury Severity via an Extreme Gradient Boosting (XGBoost) Model","volume":"2021","author":"S Wu","year":"2021","journal-title":"J Adv Transp"},{"issue":"5","key":"pone.0353205.ref023","doi-asserted-by":"crossref","first-page":"4486","DOI":"10.3390\/su15054486","article-title":"Temporal Instability and Transferability Analysis of Daytime and Nighttime Motorcyclist-Injury Severities Considering Unobserved Heterogeneity of Data","volume":"15","author":"C Se","year":"2023","journal-title":"Sustainability"},{"issue":"1","key":"pone.0353205.ref024","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1080\/15389588.2023.2244104","article-title":"An exploratory investigation into the influence of risk factors on driver injury severity in angle crashes: A random parameter bivariate ordered probit model approach","volume":"25","author":"Z Fang","year":"2024","journal-title":"Traffic Inj Prev"},{"issue":"2","key":"pone.0353205.ref025","doi-asserted-by":"crossref","first-page":"646","DOI":"10.3390\/su14020646","article-title":"Pedestrian Safety in Compact and Mixed-Use Urban Environments: Evaluation of 5D Measures on Pedestrian Crashes","volume":"14","author":"H Sung","year":"2022","journal-title":"Sustainability"},{"key":"pone.0353205.ref026","doi-asserted-by":"crossref","first-page":"108305","DOI":"10.1016\/j.aap.2025.108305","article-title":"Application of the dual-model interpretability framework of XGBoost-SHAP and GAT-GNNExplainer to investigate the impact of the built environment on traffic accidents at intersections","volume":"224","author":"Y Chen","year":"2026","journal-title":"Accid Anal Prev"},{"issue":"10","key":"pone.0353205.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0292363","article-title":"Influence of the built environment on taxi travel demand based on the optimal spatial analysis unit","volume":"18","author":"Y Duan","year":"2023","journal-title":"PLoS One"},{"key":"pone.0353205.ref028","doi-asserted-by":"crossref","first-page":"101827","DOI":"10.1016\/j.compenvurbsys.2022.101827","article-title":"Investigating the spatiotemporal pattern between the built environment and urban vibrancy using big data in Shenzhen, China","volume":"95","author":"L Chen","year":"2022","journal-title":"Comput Environ Urban Syst"},{"key":"pone.0353205.ref029","doi-asserted-by":"crossref","first-page":"103127","DOI":"10.1016\/j.jtrangeo.2021.103127","article-title":"Neighbourhood effects on station-level transit use: Evidence from the Taipei metro","volume":"94","author":"DE Andersson","year":"2021","journal-title":"Journal of Transport Geography"},{"issue":"3","key":"pone.0353205.ref030","doi-asserted-by":"crossref","first-page":"105","DOI":"10.3390\/ijgi13030105","article-title":"Exploring the Spatiotemporal Effects of the Built Environment on the Nonlinear Impacts of Metro Ridership: Evidence from Xi\u2019an, China","volume":"13","author":"Y Xi","year":"2024","journal-title":"IJGI"},{"issue":"1","key":"pone.0353205.ref031","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s12942-024-00361-y","article-title":"The built environment, purpose-specific walking behaviour and overweight: evidence from Wuhan metropolis in central China","volume":"23","author":"S He","year":"2024","journal-title":"Int J Health Geogr"},{"key":"pone.0353205.ref032","doi-asserted-by":"crossref","first-page":"106090","DOI":"10.1016\/j.scs.2024.106090","article-title":"Exploring the nuanced correlation between built environment and the integrated travel of dockless bike-sharing and metro at origin-route-destination level","volume":"119","author":"H Shen","year":"2025","journal-title":"Sustain Cities Soc"},{"issue":"1","key":"pone.0353205.ref033","article-title":"The Influence of Density-Diversity and Facility Accessibility in Work-Residence Built Environments on Commuting Mode Choice","volume":"19","author":"J Zhu","year":"2026","journal-title":"Appl Spatial Analysis"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T17:30:45Z","timestamp":1783445445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353205"}},"subtitle":[],"editor":[{"given":"Yajie","family":"Zou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":33,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353205","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]}}}