{"id":"W4415008445","doi":"10.2196/72068","title":"Unsupervised Coverage Sampling to Enhance Clinical Chart Review Coverage for Computable Phenotype Development: Simulation and Empirical Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Sampling (signal processing); Sample size determination; Chart; Sample (material); Empirical research","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01410885,0.0006823403,0.0008270575,0.001174295,0.0004887401,0.0008454758,0.001388408,0.001154106,0.001128418],"category_scores_gemma":[0.07038624,0.0003731192,0.0009688248,0.001044534,0.0009917265,0.001277449,0.001239059,0.001362231,0.0001072575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002389998,"about_ca_system_score_gemma":0.001840484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02248263,"about_ca_topic_score_gemma":0.01174711,"domain_scores_codex":[0.9946855,0.004129659,0.0001169724,0.0004532111,0.0003723541,0.0002423744],"domain_scores_gemma":[0.8841822,0.1032875,0.003920336,0.004021379,0.003525323,0.00106321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004306465,0.0003924322,0.04588078,0.000131087,0.0001405956,0.0001298276,0.0003254714,0.9182515,0.0004584378,0.006207194,0.001211882,0.02644018],"study_design_scores_gemma":[0.00004864077,0.00009204411,0.003242189,0.00001737046,0.00001843566,0.00003132324,0.0000511906,0.994555,0.0002543056,0.001490724,0.0001899192,0.000008886352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8508133,0.0006491564,0.1441912,0.0009166213,0.00004142374,0.0005547321,0.0005165576,0.000275297,0.002041818],"genre_scores_gemma":[0.9635389,0.0001348939,0.03516909,0.0001124486,0.0000204177,0.0002322625,0.0004737225,0.00001890327,0.000299376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02248263,"threshold_uncertainty_score":0.07461566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0755575359375241,"score_gpt":0.4799906859226574,"score_spread":0.4044331499851332,"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."}}