{"id":"W4396781237","doi":"10.1038/s43856-024-00502-1","title":"A comprehensive AI model development framework for consistent Gleason grading","year":2024,"lang":"en","type":"article","venue":"Communications Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Agency for Science, Technology and Research","keywords":"Computer science; Workflow; Artificial intelligence; Scanner; Grading (engineering); Digital pathology; Scalability; Image quality; Pattern recognition (psychology); Machine learning; Computer vision; Image (mathematics); Database","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":[0.0002724955,0.0001298343,0.0001772942,0.0001710482,0.000372324,0.00007635089,0.001393084,0.00006780772,0.000005682527],"category_scores_gemma":[0.000120849,0.0001154113,0.00004777619,0.0005094596,0.0001852721,0.0002079199,0.0004415287,0.0003120445,0.00002356901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002717037,"about_ca_system_score_gemma":0.0002360451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001202015,"about_ca_topic_score_gemma":0.000009432068,"domain_scores_codex":[0.9989509,0.00005287556,0.000309877,0.0002913736,0.0002066735,0.0001883046],"domain_scores_gemma":[0.9970244,0.0008926557,0.00005951856,0.001727168,0.0002138644,0.00008244442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005415247,0.00003724015,0.00001567468,0.000149218,0.00007920762,0.00000122744,0.006102298,0.0006657081,0.0005077455,0.7948643,0.01293409,0.1846379],"study_design_scores_gemma":[0.000143779,0.00004800784,0.00003954226,0.0005803749,0.00001821415,0.00001328307,0.0001270854,0.703261,0.0002389903,0.07155804,0.2238608,0.000110846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001346156,0.01274925,0.9426036,0.04233587,0.000627832,0.0003722681,0.000001972089,0.0003823235,0.0007923005],"genre_scores_gemma":[0.3841467,0.0004801224,0.6131803,0.001629445,0.00008100927,0.0003075907,0.00001382223,0.0000151446,0.0001457574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7233062,"threshold_uncertainty_score":0.4706338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.146219847374851,"score_gpt":0.3956946391391918,"score_spread":0.2494747917643409,"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."}}