{"id":"W2979992932","doi":"10.1016/j.media.2020.101796","title":"BIAS: Transparent reporting of biomedical image analysis challenges","year":2020,"lang":"en","type":"preprint","venue":"Medical Image Analysis","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; Ministerstvo Školství, Mládeže a Tělovýchovy; Canadian Cancer Society; NIH Clinical Center; European Research Council; National Institutes of Health; National Science Foundation","keywords":"Interpretability; Checklist; Benchmarking; Computer science; Data science; Transparency (behavior); Set (abstract data type); Quality (philosophy); Artificial intelligence; Psychology; Business; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6618311,0.003823109,0.004439496,0.0204293,0.01142199,0.02767489,0.01225316,0.02146427,0.009696756],"category_scores_gemma":[0.894087,0.004688193,0.007815882,0.009495193,0.0154241,0.0192667,0.0374001,0.01699597,0.01087003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0133071,"about_ca_system_score_gemma":0.08470623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003374745,"about_ca_topic_score_gemma":0.003770853,"domain_scores_codex":[0.1503901,0.520516,0.2052843,0.01515115,0.103727,0.004931461],"domain_scores_gemma":[0.03406747,0.4377479,0.1215502,0.1220103,0.2782308,0.006393383],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002018529,0.0003177383,0.009351914,0.04328329,0.001791954,0.001414044,0.0255455,0.00270262,0.007998498,0.07811502,0.4870418,0.3404191],"study_design_scores_gemma":[0.0009259788,0.0006445691,0.006098661,0.03678912,0.0008614913,0.001651338,0.004775526,0.006182697,0.01339833,0.09400788,0.8335652,0.00109923],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0101103,0.01402745,0.6491997,0.1811243,0.04644152,0.05337668,0.006759382,0.009722433,0.02923813],"genre_scores_gemma":[0.08961707,0.007281205,0.7063974,0.05235231,0.01321232,0.1068147,0.006351694,0.004837548,0.01313563],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3381689,"threshold_uncertainty_score":0.4170225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4378958910839068,"score_gpt":0.501754488514744,"score_spread":0.06385859743083722,"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."}}