{"id":"W2337688125","doi":"10.1093/jamia/ocw011","title":"Electronic medical record phenotyping using the anchor and learn framework","year":2016,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; Natural Sciences and Engineering Research Council of Canada; U.S. Army Medical Research Acquisition Activity; National Institutes of Health; Consortia for Improving Medicine with Innovation and Technology","keywords":"Computer science; Electronic medical record; Electronic health record; Data science; Medical record; Artificial intelligence; Medicine; Internet privacy; Health care; Political science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005106391,0.00009782477,0.0002657296,0.00006659993,0.0002393152,0.00009210047,0.001228046,0.0001129523,0.0000283767],"category_scores_gemma":[0.01531696,0.00004331087,0.00009555549,0.0004477604,0.0001423919,0.0003678835,0.0003066767,0.001280106,0.000004442569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005429913,"about_ca_system_score_gemma":0.0007857669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005698105,"about_ca_topic_score_gemma":0.00001495591,"domain_scores_codex":[0.9963142,0.0005090216,0.0007742559,0.00006474926,0.0019808,0.0003569193],"domain_scores_gemma":[0.9946814,0.002125967,0.002480029,0.000270476,0.0002217164,0.0002204058],"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":[0.0000159943,0.00002308438,0.07713327,0.00002411808,0.0001067029,0.000002818171,0.002699711,0.00005762331,0.00001467123,0.0068253,0.001510757,0.9115859],"study_design_scores_gemma":[0.001213072,0.0006381558,0.05398783,0.001936655,0.00008671945,0.0005607041,0.001066723,0.8777017,0.00004279139,0.03023567,0.03209539,0.00043457],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3372039,0.00008732964,0.5861309,0.07585517,0.0005717174,0.00007024087,3.504263e-7,0.00001823877,0.00006207143],"genre_scores_gemma":[0.9686363,0.0006724327,0.01984272,0.01014185,0.0006508609,0.000001405687,8.207967e-8,0.000010209,0.00004411871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9111514,"threshold_uncertainty_score":0.9929774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009773237003428725,"score_gpt":0.3026507515659937,"score_spread":0.2928775145625649,"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."}}