{"id":"W2988743666","doi":"10.1136/bmjhci-2019-100009","title":"Coding and classifying GP data: the POLAR project","year":2019,"lang":"en","type":"article","venue":"BMJ Health & Care Informatics","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Monash University; HCF Research Foundation","keywords":"SNOMED CT; Computer science; Coding (social sciences); Medical diagnosis; Data science; Population; Analytics; Data mining; Big data; Diagnosis code; Information retrieval; Natural language processing; Terminology; Medicine; Pathology","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.005008296,0.0001954943,0.0004176847,0.0001517785,0.001964742,0.00005143008,0.0004897625,0.0002396242,0.00007547673],"category_scores_gemma":[0.0007858229,0.0001287032,0.00003031751,0.0002878575,0.00006586788,0.00082105,0.0004996049,0.001412457,0.000569874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003620872,"about_ca_system_score_gemma":0.002987551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006620535,"about_ca_topic_score_gemma":0.000212616,"domain_scores_codex":[0.9959921,0.0003905711,0.001947698,0.0001523,0.0006329843,0.0008843719],"domain_scores_gemma":[0.9964184,0.000988842,0.001064184,0.001012892,0.0002251909,0.0002904595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001218889,0.00001859812,0.04675629,0.04359523,0.00003986907,0.000001249865,0.3646263,0.00001724197,0.000001077879,0.01293962,0.4233174,0.1085653],"study_design_scores_gemma":[0.0009760085,0.0001525083,0.004935151,0.00138522,0.00001240668,0.00001221795,0.1558869,0.02313901,3.886391e-7,0.00003076233,0.8132775,0.0001918511],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3958188,0.008274739,0.02459275,0.159474,0.02057113,0.05684729,0.002109256,0.002258878,0.3300532],"genre_scores_gemma":[0.7959139,0.003212803,0.01602615,0.1784002,0.0020513,0.0005329144,0.002069895,0.00009520151,0.001697567],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4000952,"threshold_uncertainty_score":0.9993346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3970979486549057,"score_gpt":0.5433169716742404,"score_spread":0.1462190230193347,"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."}}