{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003915212,0.0004958931,0.003646511,0.002001563,0.00009735737,0.00004913085,0.0005339105,0.0009323441,0.004827206],"category_scores_gemma":[0.01634045,0.0004148467,0.003073417,0.004450732,0.0006698518,0.00008039374,0.0003066613,0.001725415,0.00006376109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001807089,"about_ca_system_score_gemma":0.001374555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003925253,"about_ca_topic_score_gemma":0.0008866859,"domain_scores_codex":[0.9892111,0.000386195,0.005742522,0.00136377,0.002709651,0.000586755],"domain_scores_gemma":[0.9923801,0.0005744451,0.003237912,0.001376229,0.0009994345,0.001431899],"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":[0.0006527992,0.005751997,0.1437646,0.01457168,0.1415742,0.005764551,0.03342771,0.0003919967,0.004246058,0.0001261369,0.00671745,0.6430109],"study_design_scores_gemma":[0.0005987045,0.001278774,0.1399884,0.003224361,0.3813086,0.00009977859,0.02455675,0.408443,0.0288476,0.004123847,0.004816917,0.002713336],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4569474,0.009381246,0.34529,0.1826451,0.001052591,0.001191681,0.0001967002,0.0004259374,0.002869393],"genre_scores_gemma":[0.9826076,0.006505433,0.006988435,0.0007047011,0.001039662,0.00008618801,0.001926242,0.00004528652,0.00009641959],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6402975,"threshold_uncertainty_score":0.9998304,"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."}}