{"id":"W4411299917","doi":"10.1016/j.iatssr.2025.06.001","title":"Exploring the factors affecting injury severity in highway and non-highway crashes in Bangladesh applying machine learning and SHAP","year":2025,"lang":"en","type":"article","venue":"IATSS Research","topic":"Traffic and Road Safety","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Bangladesh University of Engineering and Technology","keywords":"Injury prevention; Poison control; Human factors and ergonomics; Occupational safety and health; Suicide prevention; Transport engineering; Engineering; Medical emergency; Forensic engineering; Environmental health; Applied psychology; Psychology; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001423236,0.0005014232,0.0003964896,0.001661206,0.0004144631,0.0007523025,0.0006329212,0.0004007946,0.001437755],"category_scores_gemma":[0.003776482,0.000202051,0.0007419282,0.00155487,0.000437214,0.0007638998,0.0007681224,0.000570435,0.0002093319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002270724,"about_ca_system_score_gemma":0.001397704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07745591,"about_ca_topic_score_gemma":0.06568816,"domain_scores_codex":[0.9994606,0.0002263399,0.00005162194,0.00008885589,0.00007703959,0.00009553613],"domain_scores_gemma":[0.9986577,0.0006137695,0.0002450392,0.00007136566,0.000332166,0.00008000697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008356,0.0000776368,0.9409791,0.00008762552,0.0001549898,0.0002725871,0.0006945059,0.02878196,0.0004873968,0.002102858,0.0004606035,0.02581721],"study_design_scores_gemma":[0.000006367193,0.0002583643,0.7889864,0.00009684328,0.0001362809,0.0002316767,0.005999435,0.1987733,0.0007376382,0.003532177,0.001192167,0.00004943041],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929637,0.0002274581,0.004670511,0.0003650974,0.000006805044,0.00003784481,0.00033142,0.00001670278,0.001380425],"genre_scores_gemma":[0.998151,0.0001620361,0.001031575,0.00001242455,0.000003079128,0.00001402758,0.0002710909,0.000001706562,0.0003530271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07745591,"threshold_uncertainty_score":0.1540101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05625901585260585,"score_gpt":0.3132165215818937,"score_spread":0.2569575057292879,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}