{"id":"W2034448355","doi":"10.1109/jbhi.2013.2274733","title":"Data Mining in Bone Marrow Transplant Records to Identify Patients With High Odds of Survival","year":2013,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Mitacs; Tehran University of Medical Sciences and Health Services","keywords":"Medicine; Odds; Odds ratio; Prioritization; Confidence interval; Matching (statistics); Probabilistic logic; Bone marrow transplant; Data mining; Computer science; Internal medicine; Bone marrow; Oncology; Bone marrow transplantation; Artificial intelligence; Logistic regression; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003479306,0.0001483045,0.0006924954,0.000420577,0.0002076303,0.0000120241,0.0003943262,0.0001941745,0.0001515925],"category_scores_gemma":[0.0002346066,0.0001010601,0.00002486131,0.000409287,0.000128955,0.0005311715,0.000088361,0.0007962437,0.00002917734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001379603,"about_ca_system_score_gemma":0.0009600854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002824265,"about_ca_topic_score_gemma":0.002015552,"domain_scores_codex":[0.9946324,0.0002375782,0.003639063,0.0001025468,0.0008197734,0.0005686809],"domain_scores_gemma":[0.9963991,0.0004896123,0.001534801,0.0002907511,0.0005098059,0.0007759288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004269167,0.0003262229,0.8095868,0.005122832,0.0000440537,0.0000118705,0.03975208,0.00001262107,0.0000163683,0.00007914974,0.01989767,0.1247234],"study_design_scores_gemma":[0.002585378,0.003900925,0.9424964,0.009146993,0.00003532027,0.00002452098,0.02687002,0.003993751,0.00002211483,0.0004008452,0.01016018,0.0003635442],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868775,0.0001012841,0.002535376,0.007964575,0.001549069,0.000692996,0.0002223845,0.000007741453,0.00004908867],"genre_scores_gemma":[0.9868245,0.0004998785,0.01009423,0.002193363,0.0002893666,0.00001021226,0.00005232992,0.00001479252,0.00002136669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1329096,"threshold_uncertainty_score":0.4269462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1746587700316266,"score_gpt":0.457515108301605,"score_spread":0.2828563382699784,"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."}}