{"id":"W2890986727","doi":"10.23889/ijpds.v3i4.963","title":"Using Artificial Intelligence Technology for Social Determinants and Risk Factors Surveillance","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Healthcare Systems and Public Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Social determinants of health; Population; Health equity; Population health; Disease; Risk factor; Disease surveillance; Environmental health; Business; Psychology; Medicine; Public health; Pathology","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002341969,0.00008448368,0.0001688064,0.0004051902,0.000872925,0.0001549672,0.0004818925,0.00007768495,0.000009563336],"category_scores_gemma":[0.002548651,0.00006966165,0.00002850003,0.0002981091,0.0002853553,0.0006757777,0.0001190938,0.0001333233,0.000001141841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713522,"about_ca_system_score_gemma":0.0005997706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008554865,"about_ca_topic_score_gemma":0.0004959457,"domain_scores_codex":[0.9984368,0.00002948755,0.0004975222,0.0003188014,0.0004383842,0.0002790245],"domain_scores_gemma":[0.9980073,0.0000952352,0.0003655788,0.0001833014,0.00119587,0.0001527434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001598283,0.00004275197,0.6800209,0.00003206764,0.00002730372,0.00000240273,0.0002791595,0.000004932744,0.0005439679,0.01387063,0.0001278425,0.3048882],"study_design_scores_gemma":[0.0006738519,0.0007867051,0.6110163,0.000188302,0.00003742087,0.0008324583,0.001055528,0.3367833,0.000915697,0.02910096,0.01825973,0.0003497018],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8695322,0.00001869421,0.125578,0.001811414,0.002242142,0.000326547,0.000463634,0.00001741261,0.000009992586],"genre_scores_gemma":[0.9852096,0.00002544514,0.01312421,0.00007287606,0.0014842,0.000003444272,0.0000620037,0.000008483027,0.000009739824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3367784,"threshold_uncertainty_score":0.6713921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3233185548000539,"score_gpt":0.531245212581993,"score_spread":0.207926657781939,"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."}}