{"id":"W3000127051","doi":"10.1038/s41591-019-0649-2","title":"Treating health disparities with artificial intelligence","year":2020,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":218,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Health equity; Health care; Imperfect; Artificial intelligence; Medicine; Computer science; Gerontology; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002933854,0.0001820935,0.0004324982,0.00009191718,0.0001716968,0.00001246958,0.00009485857,0.0001793891,0.0003121886],"category_scores_gemma":[0.0008601417,0.0001197648,0.00003843756,0.0005993997,0.0002138898,0.00007483953,0.00001508845,0.0009434997,0.00005225371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009875347,"about_ca_system_score_gemma":0.0003560606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006879168,"about_ca_topic_score_gemma":0.000124676,"domain_scores_codex":[0.9982824,0.00004879295,0.0005160076,0.0003513415,0.000451985,0.0003494577],"domain_scores_gemma":[0.9987463,0.0001854829,0.0001432955,0.0002083039,0.0002261321,0.0004905222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001453771,0.000221686,0.03326206,0.00108109,0.00008832914,0.00009873105,0.02090337,0.00004327935,0.001096964,0.02730033,0.01593386,0.8985165],"study_design_scores_gemma":[0.001571347,0.08618526,0.0565512,0.01671952,0.001527611,0.001981408,0.2836915,0.03477664,0.2594137,0.05870736,0.1946778,0.004196618],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2057186,0.005849253,0.01422063,0.7688995,0.0006874574,0.0008531314,0.00000568429,0.0002641884,0.003501584],"genre_scores_gemma":[0.9583226,0.000213626,0.001711408,0.03693589,0.002602551,0.000018046,0.00006111335,0.00002468561,0.0001100474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8943199,"threshold_uncertainty_score":0.4883865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1777787438495623,"score_gpt":0.4476006608842074,"score_spread":0.269821917034645,"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."}}