{"id":"W4311059376","doi":"10.1101/2022.11.29.22282888","title":"Tools for categorization of diagnostic codes in hospital data: Operationalizing CCSR into a patient data repository","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; St. Michael's Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Canadian Frailty Network; University of Toronto; University Health Network","keywords":"Coding (social sciences); Operationalization; ICD-10; Categorization; Diagnosis code; Androstenediol; Medicine; Medical classification; Data mining; Computer science; Statistics; Artificial intelligence; Mathematics; Psychiatry; Environmental health; Nursing; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00318332,0.0001812243,0.0004501917,0.0001750675,0.0006166989,0.00003143393,0.001133372,0.0002956369,0.00012574],"category_scores_gemma":[0.01897721,0.0001742606,0.00003017951,0.0001589976,0.00004532749,0.0005388032,0.003137433,0.001091915,0.00000777665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003235177,"about_ca_system_score_gemma":0.001929769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001551782,"about_ca_topic_score_gemma":0.0003490841,"domain_scores_codex":[0.9961448,0.0006434673,0.001765022,0.0005743522,0.0005506488,0.0003217095],"domain_scores_gemma":[0.9921011,0.00478317,0.0009784369,0.001754392,0.0002629612,0.0001198935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000456583,0.001613454,0.6482989,0.0497628,0.0002474512,0.00003852172,0.1145071,0.009873812,0.0002034357,0.01791677,0.1248708,0.03221038],"study_design_scores_gemma":[0.004542477,0.001234438,0.142011,0.008739571,0.0003153867,0.000002889098,0.02056069,0.3288179,0.0001516718,0.005458096,0.4865078,0.001658094],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.929192,0.001453505,0.0366184,0.006226801,0.01144257,0.008800731,0.004495377,0.0001552608,0.001615369],"genre_scores_gemma":[0.9508598,0.000426358,0.003454722,0.0004976032,0.0005083286,0.001631249,0.04251136,0.00003023999,0.00008027835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5062879,"threshold_uncertainty_score":0.9892864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3259460652604069,"score_gpt":0.472216701731843,"score_spread":0.1462706364714362,"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."}}