{"id":"W2888696592","doi":"10.1038/s41379-018-0109-4","title":"An international multicenter study to evaluate reproducibility of automated scoring for assessment of Ki67 in breast cancer","year":2018,"lang":"en","type":"article","venue":"Modern Pathology","topic":"AI in cancer detection","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Juravinski Cancer Centre; Sinai Health System; University of Toronto; Ontario Institute for Cancer Research; Queen's University; Alberta Health Services; McMaster University; Juravinski Hospital; University of British Columbia","funders":"Cure Brain Cancer Foundation; National Institute for Health and Care Research; NIHR Biomedical Research Centre, Royal Marsden NHS Foundation Trust/Institute of Cancer Research; Government of Ontario; Ontario Institute for Cancer Research; Cancer Research UK; Breast Cancer Research Foundation","keywords":"Intraclass correlation; Reproducibility; Medicine; Correlation coefficient; Breast cancer; Coefficient of variation; Confidence interval; Nuclear medicine; Medical physics; Radiology; Statistics; Cancer; Mathematics; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00194402,0.00008316845,0.0001930157,0.0001580981,0.00002522809,0.00001134936,0.0005347642,0.00003248142,0.0000097605],"category_scores_gemma":[0.00006793185,0.00008191223,0.00002654139,0.0001711302,0.00005073056,0.000242565,0.0002157916,0.00005727904,7.83468e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002059572,"about_ca_system_score_gemma":0.00009063094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003111205,"about_ca_topic_score_gemma":0.0005413903,"domain_scores_codex":[0.9982016,0.0001849298,0.0003653747,0.000888421,0.0002014502,0.000158211],"domain_scores_gemma":[0.9981583,0.00003202824,0.0001580179,0.001184565,0.0004356798,0.0000313675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001935477,0.00112688,0.8384342,0.00002686381,0.00003069024,0.000004344625,0.007713872,0.0123859,0.09667163,0.00007029682,0.00001227945,0.04332947],"study_design_scores_gemma":[0.000452036,0.0003403642,0.5060908,0.00001201792,0.000003831194,0.000002598369,0.00002555584,0.4877465,0.005106559,0.0001776855,0.000001384028,0.00004064852],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.731652,0.000002622586,0.2667982,0.0002337114,0.0007534396,0.0004646301,0.0000168589,0.00005644995,0.00002210288],"genre_scores_gemma":[0.9708888,9.349099e-7,0.02882209,0.00005840262,0.00007455656,0.0001420227,9.793172e-7,0.000007425514,0.000004820477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4753606,"threshold_uncertainty_score":0.3340284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05968679981892819,"score_gpt":0.4219095261387893,"score_spread":0.3622227263198611,"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."}}