{"id":"W2057663593","doi":"10.1109/bibm.2013.6732511","title":"Patient information extraction in noisy tele-health texts","year":2013,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Noise (video); Natural language processing; Spelling; Noise reduction; Speech recognition; Information retrieval; Sentence; Artificial intelligence; Information extraction; Linguistics","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":[0.00007831817,0.0000591962,0.0000631516,0.00004110547,0.00002648007,0.00001689334,0.0000453501,0.00009988041,0.0000867279],"category_scores_gemma":[0.00006825986,0.00004660778,0.00001970893,0.00005555026,0.00002707924,0.000008504365,0.00002900636,0.00005943773,0.0001215212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001498844,"about_ca_system_score_gemma":0.00003918024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000347446,"about_ca_topic_score_gemma":0.00008419302,"domain_scores_codex":[0.9994769,0.00002345545,0.0001874199,0.00008994884,0.00007267712,0.0001496016],"domain_scores_gemma":[0.9997484,0.00000618629,0.00005595392,0.0001081382,0.00002963683,0.00005170557],"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":[0.000009586324,0.000043101,0.002260395,0.00001211633,0.000004171998,2.114981e-7,0.0001411477,0.000008777438,0.009198299,0.00003646415,0.02706893,0.9612168],"study_design_scores_gemma":[0.0008896597,0.001202543,0.1773573,0.00003302359,0.000002135935,0.00002358422,0.001708044,0.0005949491,0.03116108,0.0002866045,0.7864139,0.0003271366],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875917,0.0002377402,0.003980434,0.00172462,0.0001622124,0.0002138013,0.000002318413,0.00002804341,0.006059072],"genre_scores_gemma":[0.9952804,0.0000704362,0.002975024,0.001333492,0.00003215131,0.0000299595,0.00006201778,0.000002829406,0.0002137219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9608896,"threshold_uncertainty_score":0.190061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00748155273060243,"score_gpt":0.2616006917107492,"score_spread":0.2541191389801468,"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."}}