{"id":"W3202987421","doi":"10.1155/2021/3771640","title":"Analyzing Accident Injury Severity via an Extreme Gradient Boosting (XGBoost) Model","year":2021,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Crash; China; Poison control; Injury prevention; Transport engineering; Boosting (machine learning); Occupational safety and health; Descriptive statistics; Human factors and ergonomics; Geography; Statistical analysis; Suicide prevention; Environmental health; Computer science; Statistics; Medicine; Engineering; Mathematics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002607187,0.001147191,0.002315849,0.001062181,0.0005424171,0.0008518184,0.002105887,0.00128643,0.001743697],"category_scores_gemma":[0.002615467,0.0005229287,0.001303264,0.0008116853,0.0006556585,0.0005586513,0.0007780552,0.001288168,0.0003627614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007948288,"about_ca_system_score_gemma":0.001562558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0110888,"about_ca_topic_score_gemma":0.007387315,"domain_scores_codex":[0.9992606,0.0002569042,0.00004354585,0.0001641436,0.0001080153,0.0001667038],"domain_scores_gemma":[0.9991161,0.0004188969,0.00009959385,0.00003852269,0.0002310376,0.00009578258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003163581,0.0003249189,0.0236673,0.0001714009,0.0002463792,0.0001858431,0.00009225265,0.8977913,0.0008407197,0.002565164,0.005027742,0.06877073],"study_design_scores_gemma":[0.00001207159,0.00004310381,0.001160403,0.000009059381,0.0000306226,0.00001534464,0.000009434336,0.997631,0.00008849036,0.0007248169,0.0002699587,0.000005675475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4215884,0.002700103,0.5683906,0.001732292,0.0004708161,0.0002987577,0.0008152102,0.001041092,0.002962592],"genre_scores_gemma":[0.9555216,0.0005328642,0.0385576,0.0004201547,0.0001997101,0.0002276808,0.001077303,0.0000567943,0.00340637],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0110888,"threshold_uncertainty_score":0.02204847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01335909501163988,"score_gpt":0.2376676784364346,"score_spread":0.2243085834247947,"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."}}