{"id":"W2170270347","doi":"","title":"Lexically-Triggered Hidden Markov Models for Clinical Document Coding","year":2011,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Hidden Markov model; Discriminative model; Computer science; Coding (social sciences); Artificial intelligence; Natural language processing; Phrase; Set (abstract data type); Speech recognition; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0008002164,0.0001304381,0.0002079821,0.00006672902,0.00009351567,0.000107056,0.001180539,0.0001219544,0.00005657256],"category_scores_gemma":[0.0001230655,0.0001078481,0.0001235154,0.0001392579,0.0000545265,0.0005686015,0.000337868,0.0001818895,0.00001263031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000380928,"about_ca_system_score_gemma":0.00006586769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000737919,"about_ca_topic_score_gemma":0.000001304747,"domain_scores_codex":[0.9986273,0.0000622589,0.0003608389,0.000425348,0.000215953,0.0003082974],"domain_scores_gemma":[0.9989783,0.0001628218,0.0001187886,0.0005077208,0.0001168556,0.0001155626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004614437,0.00007579846,0.00005608767,0.00002929482,0.00001946595,0.00001449494,0.0004299064,9.058786e-8,0.001319822,0.5538419,0.0090609,0.435106],"study_design_scores_gemma":[0.000320277,0.000140471,0.00003364087,0.00004073112,0.000008937705,0.000007989156,0.000005624273,0.01869174,0.0133526,0.966444,0.0007568497,0.0001970979],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008923775,0.0002821988,0.9847987,0.0006168895,0.0002586942,0.0003065982,0.000002115947,0.0006173776,0.012225],"genre_scores_gemma":[0.3035977,0.00003564189,0.6955187,0.0004061027,0.0000709028,0.00004210906,0.000001228972,0.000009195893,0.0003184743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4349089,"threshold_uncertainty_score":0.4397919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08503920427112521,"score_gpt":0.3482915807232321,"score_spread":0.2632523764521069,"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."}}