{"id":"W2177078353","doi":"10.4103/2153-3539.170649","title":"Extraction and analysis of discrete synoptic pathology report data using R","year":2015,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Parsing; Computer science; Scripting language; Quality assurance; Information retrieval; Data mining; Data extraction; Simple (philosophy); Natural language processing; Pathology; Medicine; Programming language; MEDLINE","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002382921,0.00008980527,0.0003967998,0.0005991033,0.00004794103,0.00003594769,0.0005452379,0.0001110589,0.000001897705],"category_scores_gemma":[0.0004443387,0.00007542455,0.00006067094,0.0007055975,0.0001096602,0.001842518,0.0003319032,0.0002348338,9.399926e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007743509,"about_ca_system_score_gemma":0.000176122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003411629,"about_ca_topic_score_gemma":0.000003126175,"domain_scores_codex":[0.9982504,0.0001005114,0.001126425,0.00009443262,0.0002936314,0.0001346562],"domain_scores_gemma":[0.9966525,0.00009631299,0.002086842,0.0006994477,0.0003738221,0.00009104716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007151804,0.0008102366,0.2253416,0.0009062795,0.008887754,0.03653389,0.1107454,0.2851684,0.0385721,0.008327485,0.004370072,0.2796216],"study_design_scores_gemma":[0.0005099553,0.0004513442,0.01235903,0.00002925625,0.001049145,0.06018469,0.0009996842,0.922143,0.0004421546,0.001040493,0.0006362951,0.0001549128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4086727,0.00008496625,0.5905569,0.00008954806,0.0004597251,0.00002655376,0.000004524488,0.00000676127,0.0000984006],"genre_scores_gemma":[0.6558669,0.00005573743,0.3439445,0.00006402667,0.00005051539,3.586067e-7,0.00000617321,0.000003908129,0.000007857237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6369746,"threshold_uncertainty_score":0.3075724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08520372962763761,"score_gpt":0.3599386390515053,"score_spread":0.2747349094238677,"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."}}