{"id":"W3034286360","doi":"10.1007/s00428-020-02858-w","title":"Identification of areas of grading difficulties in prostate cancer and comparison with artificial intelligence assisted grading","year":2020,"lang":"en","type":"article","venue":"Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"Cancerfonden; Barts Charity","keywords":"Grading (engineering); Medicine; Cohen's kappa; Prostate cancer; Kappa; Prostate; Medical physics; Artificial intelligence; Radiology; Statistics; Cancer; Internal medicine; Computer science; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004387753,0.0003576801,0.00111483,0.0002144142,0.00008201131,0.0000171598,0.0001996275,0.0001077114,0.000009615492],"category_scores_gemma":[0.0004615378,0.0002448089,0.0001103864,0.0006018759,0.001018301,0.0001097257,0.0001229411,0.0004675234,0.000002111863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006179022,"about_ca_system_score_gemma":0.0001913209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002529859,"about_ca_topic_score_gemma":0.0000866394,"domain_scores_codex":[0.9972213,0.0001900744,0.001154109,0.000680332,0.0003461601,0.0004080355],"domain_scores_gemma":[0.9981278,0.0004869556,0.0006963555,0.0003412684,0.0001393283,0.0002083052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002288591,0.001127159,0.7297056,0.001043042,0.0005666772,0.0001766801,0.009003526,0.001223401,0.1790486,0.003338566,0.00008864448,0.07238955],"study_design_scores_gemma":[0.002494619,0.003761291,0.6582834,0.001514724,0.0009089616,0.00001534193,0.01013196,0.0104114,0.3091202,0.002775813,0.00007572214,0.0005065564],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899492,0.005461269,0.0008450694,0.002482464,0.00008313928,0.0009462789,0.00008087887,0.00005753321,0.0000941895],"genre_scores_gemma":[0.9945837,0.003518949,0.001325585,0.000211852,0.00007253505,0.0001340494,0.0001159932,0.00002922925,0.000008134217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1300716,"threshold_uncertainty_score":0.9983016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06936937948551243,"score_gpt":0.3778614382692679,"score_spread":0.3084920587837555,"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."}}