{"id":"W1568047218","doi":"10.1023/a:1015014402846","title":"A Data Mining Approach to Characterizing Medical Code Usage Patterns","year":2002,"lang":"en","type":"article","venue":"Journal of Medical Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Health informatics; Computer science; Code (set theory); Data mining; Data science; Programming language; Medicine; Public health","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.004075668,0.00013019,0.0003719637,0.0001275537,0.0001007732,0.0003230721,0.00563595,0.0001511271,0.00009319274],"category_scores_gemma":[0.0008873841,0.00009598916,0.000052707,0.0003375531,0.0000348559,0.0005678575,0.001017405,0.0004605039,0.00005461906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003771263,"about_ca_system_score_gemma":0.0001180746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003438703,"about_ca_topic_score_gemma":0.000002888075,"domain_scores_codex":[0.9954181,0.0001444604,0.0008715392,0.0003501719,0.002900828,0.000314888],"domain_scores_gemma":[0.9973673,0.000231999,0.0003671372,0.0009211093,0.00008366149,0.001028812],"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":[0.00000552822,0.001136883,0.001857916,0.0002700924,0.0001979704,0.0008931821,0.003457831,0.00001583564,0.0001257275,0.003685815,0.2729937,0.7153595],"study_design_scores_gemma":[0.0004147597,0.00007613844,0.0007055115,0.0007599995,0.0000112198,0.002310034,0.0002064844,0.7957671,0.000003822694,0.000002918445,0.1995932,0.0001488019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01445308,0.0003955732,0.969682,0.01346802,0.00114786,0.0001188735,0.00007613123,0.0000420244,0.000616457],"genre_scores_gemma":[0.8306322,0.0006540286,0.1564756,0.004605508,0.006877043,0.00004939178,0.00007160255,0.00005857254,0.0005760067],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8161792,"threshold_uncertainty_score":0.9997441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1143657616866908,"score_gpt":0.3179121908718094,"score_spread":0.2035464291851186,"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."}}