{"id":"W1775135849","doi":"10.1136/amiajnl-2013-002411","title":"Learning regular expressions for clinical text classification","year":2014,"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":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; U.S. Department of Veterans Affairs","keywords":"Computer science; Natural language processing; Artificial intelligence","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":[0.003759383,0.00007639427,0.0002468863,0.00003305962,0.0001246179,0.00002291852,0.0003691456,0.0001794897,0.00000405942],"category_scores_gemma":[0.01870376,0.00004716096,0.0002366181,0.0001090842,0.0001810266,0.000006619814,0.00007723315,0.0003642939,0.000002896205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004412435,"about_ca_system_score_gemma":0.0001524261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001422524,"about_ca_topic_score_gemma":0.00000103887,"domain_scores_codex":[0.9981297,0.0003012018,0.0007992797,0.000058851,0.000554238,0.0001567552],"domain_scores_gemma":[0.9967979,0.0004539032,0.002191139,0.0001593132,0.0002622097,0.0001355398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002292961,0.000217781,0.08765202,0.00004595814,0.0003669067,3.234962e-7,0.0004736531,0.0001291077,0.006439507,0.0002725718,0.1663657,0.7378072],"study_design_scores_gemma":[0.002093888,0.002558145,0.1023724,0.0001776158,0.0001445723,0.00003098512,0.00262436,0.02140705,0.001860998,0.0006121768,0.8658571,0.0002607097],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9065242,0.00005852095,0.08659031,0.00564906,0.0006629813,0.00009806102,0.000002653724,0.00001027755,0.0004039368],"genre_scores_gemma":[0.9834392,0.0003835893,0.01250346,0.00219827,0.001010048,0.000005662484,0.00001173588,0.00001070601,0.0004373054],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7375464,"threshold_uncertainty_score":0.9895621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02529999204355388,"score_gpt":0.3547212481779366,"score_spread":0.3294212561343827,"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."}}