{"id":"W4414096736","doi":"10.2147/ceor.s533069","title":"Determinants of Economic Costs Following Road Traffic Injuries in Canada: A Quantile Regression Forests Machine Learning Approach","year":2025,"lang":"en","type":"article","venue":"ClinicoEconomics and Outcomes Research","topic":"Traffic and Road Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Quantile regression; Economic cost; Resource allocation; Road traffic; Quantile; Poison control; Resource (disambiguation); Economic model; Decision tree","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001033145,0.0001780885,0.0006145532,0.0003258041,0.0001184907,0.00003420473,0.0002559331,0.0001222006,0.000008629699],"category_scores_gemma":[0.00009632143,0.0001598623,0.0001017011,0.0001198541,0.00007711868,0.0001034516,0.0001521228,0.0005458316,0.000003504614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005940415,"about_ca_system_score_gemma":0.0006361824,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.08518684,"about_ca_topic_score_gemma":0.7343817,"domain_scores_codex":[0.9983635,0.00009487032,0.0007096491,0.0003020578,0.00009472849,0.0004351827],"domain_scores_gemma":[0.9990403,0.0005513065,0.00006011927,0.0002397035,0.00001687958,0.00009168145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000377155,0.00001775919,0.8644672,0.0001136007,0.00003789302,0.000004530918,0.0001248284,0.03376968,0.000002537908,0.0001532594,0.0000871298,0.1011839],"study_design_scores_gemma":[0.0007070765,0.00002241589,0.5950511,0.00007961263,0.000005512574,6.435288e-7,0.0004019543,0.4031822,0.00003795526,0.00002558503,0.0003657431,0.0001202952],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967943,0.001176805,0.00001103934,0.00004755558,0.00040126,0.0002502493,0.00001994379,0.00002877049,0.001270072],"genre_scores_gemma":[0.9987979,0.0007495941,0.0001178323,0.00001212995,0.00001512234,0.00002112333,0.00001183441,0.00002540056,0.0002490768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6491948,"threshold_uncertainty_score":0.920905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0284970310377287,"score_gpt":0.3532528931435239,"score_spread":0.3247558621057952,"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."}}