{"id":"W2356882517","doi":"10.1093/jamia/ocw028","title":"Learning statistical models of phenotypes using noisy labeled training data","year":2016,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":165,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Computer science; Scalability; Machine learning; Artificial intelligence; Logistic regression; Feature (linguistics); Phenotype; Feature engineering; Implementation; Predictive modelling; Data mining; Deep learning; Database","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":[0.001791887,0.0000777216,0.0002780033,0.00003675938,0.0000539902,0.00001093087,0.0005470338,0.00008675327,0.000009511594],"category_scores_gemma":[0.00766157,0.00004106326,0.00006488386,0.0001169885,0.000241196,0.00001789235,0.0002250221,0.0002111413,8.364459e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005598985,"about_ca_system_score_gemma":0.0003458037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001296953,"about_ca_topic_score_gemma":0.000004430011,"domain_scores_codex":[0.998229,0.0001636287,0.000650657,0.0000579965,0.000720888,0.0001778686],"domain_scores_gemma":[0.997503,0.0003027714,0.001712582,0.0001960784,0.0001847432,0.0001008203],"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":[0.0003531915,0.000193542,0.02530753,0.00008374677,0.00106176,0.000006216517,0.002687851,0.001223687,0.06015851,0.0003479517,0.01089926,0.8976768],"study_design_scores_gemma":[0.01863375,0.01026807,0.03738775,0.003835388,0.001970065,0.0008504952,0.03515674,0.7517862,0.03580338,0.01015232,0.09165436,0.002501466],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8523424,0.00005520518,0.1464066,0.0008694736,0.0001672856,0.00003065959,0.00002674875,0.000003961166,0.00009762765],"genre_scores_gemma":[0.9790401,0.0001896,0.02022426,0.0003003438,0.0001839167,2.817653e-7,0.000007593072,0.000007058508,0.00004679202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8951753,"threshold_uncertainty_score":0.9172169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04244371233329072,"score_gpt":0.3199957147633697,"score_spread":0.277552002430079,"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."}}