{"id":"W3080245372","doi":"","title":"BIAS: Transparent reporting of biomedical image analysis challenges","year":2020,"lang":"en","type":"article","venue":"Veřejné služby Informačního systému (Masarykiana Brunensis Universitas)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":129,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; University of Toronto; Sunnybrook Health Science Centre","funders":"NIH Clinical Center; National Science Foundation; European Research Council; Natural Sciences and Engineering Research Council of Canada; Ministerstvo Školství, Mládeže a Tělovýchovy; Canadian Cancer Society","keywords":"Interpretability; Benchmarking; Checklist; Computer science; Data science; Image quality; Set (abstract data type); Quality (philosophy); Process (computing); Image (mathematics); Artificial intelligence; Psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001158723,0.0004522581,0.00177014,0.001041044,0.0001884846,0.00003701276,0.000420072,0.0002644318,0.0005776756],"category_scores_gemma":[0.001777464,0.0004110516,0.0009746054,0.002242316,0.0004304887,0.0004458596,0.0001709231,0.0007550677,0.0000569632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001553879,"about_ca_system_score_gemma":0.0003181176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002348195,"about_ca_topic_score_gemma":0.000008017393,"domain_scores_codex":[0.9951078,0.00011192,0.002338331,0.0006287724,0.001136228,0.0006769485],"domain_scores_gemma":[0.9959379,0.0001571104,0.001846685,0.0006528108,0.0003857354,0.001019692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006094315,0.003505331,0.2223303,0.0210223,0.05298614,0.02201334,0.128511,0.01287568,0.06554795,0.01188243,0.1097315,0.3434998],"study_design_scores_gemma":[0.01879811,0.004249806,0.1925674,0.002495769,0.02773296,0.001166268,0.08834955,0.3511327,0.006304612,0.00009551566,0.3033639,0.003743493],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8005747,0.006110651,0.05482971,0.07043261,0.0007417999,0.001704842,0.0002106357,0.001143564,0.06425155],"genre_scores_gemma":[0.9913898,0.001160695,0.00532126,0.001477603,0.0002205812,0.000003210843,0.0002786549,0.0000477779,0.0001004427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3397563,"threshold_uncertainty_score":0.9998341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.069861126523536,"score_gpt":0.2925615362881141,"score_spread":0.2227004097645781,"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."}}