{"id":"W4415711326","doi":"10.1016/j.jth.2025.102197","title":"Using machine learning to predict child active transportation prevalence","year":2025,"lang":"en","type":"article","venue":"Journal of Transport & Health","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; Institut National de la Recherche Scientifique; University of Calgary","funders":"Alberta Children's Hospital Research Institute; Canadian Institutes of Health Research; Alberta Innovates","keywords":"Catchment area; Population; Unit (ring theory); Predictive modelling; Decision tree; Random forest","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003463921,0.0008143061,0.0006806902,0.00228949,0.0003484866,0.001121091,0.0008322718,0.001002313,0.001678906],"category_scores_gemma":[0.008573042,0.0003111381,0.001035362,0.001119894,0.0002308604,0.0007246445,0.0005417335,0.001173493,0.000689673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111956,"about_ca_system_score_gemma":0.001263219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02474181,"about_ca_topic_score_gemma":0.01904932,"domain_scores_codex":[0.9990554,0.0003354396,0.0001034494,0.0002071892,0.0001619003,0.0001365466],"domain_scores_gemma":[0.9947535,0.003602986,0.0004023531,0.000191522,0.0008752522,0.0001744051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002956289,0.0008185453,0.5095187,0.0001428272,0.0003654374,0.0001430968,0.0001171258,0.3538155,0.0008258382,0.0004834846,0.004330408,0.1291434],"study_design_scores_gemma":[0.00001820022,0.000135101,0.03345091,0.0000428575,0.00004756623,0.00003783237,0.00006250419,0.9643199,0.0005344729,0.0007372519,0.0005983294,0.00001510948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9236894,0.0008451835,0.06663416,0.0007829517,0.000145283,0.0002841058,0.003990248,0.0009483144,0.002680409],"genre_scores_gemma":[0.9616076,0.0002548226,0.03258794,0.0000993776,0.0000492755,0.0001729499,0.00424723,0.00002353886,0.0009571692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02474181,"threshold_uncertainty_score":0.04919559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02921796483360158,"score_gpt":0.3611152674552272,"score_spread":0.3318973026216256,"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."}}