{"id":"W4414003247","doi":"10.1093/jamia/ocaf134","title":"Transport-based transfer learning on Electronic Health Records: application to detection of treatment disparities","year":2025,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Provincial Health Services Authority; Vancouver Coastal Health; University of British Columbia","funders":"","keywords":"Computer science; Transfer of learning; Population; Machine learning; Generalization; Artificial intelligence; Context (archaeology); Binary classification; Data mining; Feature (linguistics); Support vector machine; Mathematics; Medicine; Geography","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":[0.001753203,0.0000959012,0.0003347318,0.0002154531,0.000138072,0.00002058548,0.0004484905,0.00005051502,0.000001677366],"category_scores_gemma":[0.0005566351,0.00006694868,0.0001446042,0.0007585294,0.00002663885,0.0001164416,0.00001431553,0.0005345389,0.000001492825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001923986,"about_ca_system_score_gemma":0.001064881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005526126,"about_ca_topic_score_gemma":0.0002225548,"domain_scores_codex":[0.9977502,0.0003170723,0.0008801194,0.00006508087,0.0007566909,0.0002309002],"domain_scores_gemma":[0.997909,0.0004144691,0.001185924,0.000187342,0.0001929328,0.0001103243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000124939,0.0001720935,0.055165,0.0001627106,0.0001333974,2.755175e-7,0.003326762,0.06625255,0.00009915266,0.003076402,0.0001725143,0.8713142],"study_design_scores_gemma":[0.001851645,0.009088351,0.1721438,0.0007873704,0.00007847158,0.000008258395,0.0007528785,0.7901849,0.002651592,0.0009665354,0.0212105,0.0002757309],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2997872,0.00002101174,0.6788556,0.02087335,0.0001811167,0.0001942565,0.000001202566,0.00002022929,0.00006607585],"genre_scores_gemma":[0.9947984,0.0001039266,0.001404957,0.003589234,0.00004170765,0.00001125696,0.000001385771,0.000004322198,0.00004476837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8710385,"threshold_uncertainty_score":0.5031157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005414013964400035,"score_gpt":0.2869131495632091,"score_spread":0.2814991355988091,"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."}}