{"id":"W3160847342","doi":"10.5858/arpa.2020-0723-cp","title":"Validating Whole Slide Imaging Systems for Diagnostic Purposes in Pathology","year":2021,"lang":"en","type":"article","venue":"Archives of Pathology & Laboratory Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"ca_institutions":"York Central Hospital","funders":"","keywords":"Guideline; Medicine; Grading (engineering); Concordance; Medical physics; Telepathology; Context (archaeology); Medical diagnosis; MEDLINE; Pathology; Health care","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":[0.0007668009,0.0001818183,0.0004970708,0.0003052446,0.00008628587,0.00001386985,0.0004886502,0.000066905,0.000004427426],"category_scores_gemma":[0.002827525,0.0001748115,0.00004632028,0.0004921849,0.0005232284,0.0002208123,0.0002221048,0.0002285308,0.000003561835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004586728,"about_ca_system_score_gemma":0.0002676016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002089211,"about_ca_topic_score_gemma":0.00003268121,"domain_scores_codex":[0.9976515,0.0005955874,0.0005959239,0.0006021414,0.000169183,0.000385657],"domain_scores_gemma":[0.9955012,0.003300655,0.0002934753,0.0006460231,0.0001795864,0.00007902204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005535997,0.0002218604,0.06435674,0.0006972696,0.00005180424,0.00640405,0.01741352,0.001467608,0.8197655,0.034323,0.001281159,0.0539621],"study_design_scores_gemma":[0.02390564,0.004971649,0.3027838,0.007720549,0.0004525768,0.006436891,0.02074232,0.1331013,0.3147844,0.1196666,0.06215411,0.003280238],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3318787,0.01783089,0.6409534,0.004400847,0.003363744,0.0006041626,0.00006038187,0.0001567826,0.0007511877],"genre_scores_gemma":[0.9759844,0.0003444012,0.02230591,0.0007104878,0.0003528747,0.0002071478,0.00002331027,0.00002547158,0.00004597784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6441057,"threshold_uncertainty_score":0.7128608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01354589899077042,"score_gpt":0.2739924397818307,"score_spread":0.2604465407910603,"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."}}