{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002610521,0.000209427,0.0005618043,0.0001178289,0.000267394,0.0001381883,0.0007208195,0.0001616146,0.00002793512],"category_scores_gemma":[0.001914864,0.0001837696,0.00005941639,0.0005858358,0.00003464999,0.0003485611,0.000636141,0.0005198948,0.00004282934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007899364,"about_ca_system_score_gemma":0.0005992038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004418114,"about_ca_topic_score_gemma":0.000005671398,"domain_scores_codex":[0.996837,0.0001876089,0.001560197,0.0003115555,0.0007191018,0.0003845516],"domain_scores_gemma":[0.9969007,0.001762712,0.0002099385,0.0004937387,0.0002413069,0.0003915491],"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":[0.00005345247,0.0004455657,0.03043766,0.005726674,0.00006899975,0.000004332916,0.009223655,0.00415091,2.497347e-7,0.000748893,0.00543145,0.9437082],"study_design_scores_gemma":[0.0009875898,0.0003750845,0.01950076,0.002042569,0.00001571296,0.000002156249,0.00007755408,0.7806104,0.000002279125,0.0002617592,0.1958355,0.0002886086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1079589,0.0004346414,0.8854316,0.002991303,0.0003829564,0.002318637,0.000002739788,0.0001640585,0.0003151647],"genre_scores_gemma":[0.7913396,0.0004777007,0.139444,0.06782127,0.000197965,0.0004224039,0.00004974326,0.00002397979,0.0002234115],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9434196,"threshold_uncertainty_score":0.7493909,"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."}}