{"id":"W2898121486","doi":"10.3390/urbansci3010033","title":"Insights from Self-Organizing Maps for Predicting Accessibility Demand for Healthcare Infrastructure","year":2019,"lang":"en","type":"article","venue":"Urban Science","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Pacific Institute for Climate Solutions; Clemson University","keywords":"Health care; Cluster analysis; Population; Computer science; Data science; Geography; Business; Medicine; Economic growth; Artificial intelligence; Economics; Environmental health","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001135429,0.0001779515,0.0002798521,0.0001010661,0.001701231,0.0003650778,0.001171948,0.000158586,0.00005899378],"category_scores_gemma":[0.0005092582,0.0001550811,0.0001033208,0.0008919521,0.0005219111,0.001671976,0.000080383,0.0001695568,0.000007303082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003220707,"about_ca_system_score_gemma":0.001183894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001043665,"about_ca_topic_score_gemma":0.001766383,"domain_scores_codex":[0.9972766,0.0000616496,0.000401604,0.0009572324,0.000663586,0.0006393263],"domain_scores_gemma":[0.9981058,0.0003993755,0.0002307328,0.0004721743,0.0004956287,0.0002962679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002905225,0.00003098196,0.9791744,0.00008120302,0.000006640131,2.34264e-7,0.01382716,0.000004344182,0.002621135,0.003150931,0.0003235004,0.0007504417],"study_design_scores_gemma":[0.0007593742,0.00009005649,0.935205,0.00006444805,0.0000306108,7.751293e-8,0.0038094,0.0008792441,0.002237266,0.04423236,0.01233927,0.0003528977],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993243,0.00030812,0.001391854,0.0004821326,0.001239265,0.001684896,0.000163447,0.0002186651,0.001268656],"genre_scores_gemma":[0.9924926,0.000004166778,0.006419648,0.0002608892,0.0005539764,0.00004437613,0.00003352539,0.00001500615,0.0001758572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04396938,"threshold_uncertainty_score":0.9995984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01726574043095914,"score_gpt":0.3011145019288358,"score_spread":0.2838487614978767,"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."}}