{"id":"W4293053502","doi":"10.1158/1538-7445.am2022-4087","title":"Abstract 4087: Developing a standardized framework for curating oncology datasets generated by manual abstraction and artificial intelligence","year":2022,"lang":"en","type":"article","venue":"Cancer Research","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Consistency (knowledge bases); Computer science; Population; Test (biology); Lung cancer; Medicine; Artificial intelligence; Data mining; Machine learning; Oncology; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0502281,0.002698193,0.002163049,0.0133309,0.002281311,0.009666564,0.006321962,0.00205808,0.004044496],"category_scores_gemma":[0.07635817,0.00243944,0.006236225,0.007806587,0.00233225,0.007531335,0.01425658,0.004268851,0.004601237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00332708,"about_ca_system_score_gemma":0.0140459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01769287,"about_ca_topic_score_gemma":0.01760737,"domain_scores_codex":[0.9669922,0.01015275,0.008103391,0.004597435,0.009250566,0.0009036108],"domain_scores_gemma":[0.9512444,0.01708716,0.003977341,0.01423393,0.01188125,0.001575909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007167956,0.001140956,0.02253247,0.004154508,0.001718735,0.002058599,0.006287498,0.05817753,0.02936913,0.1072579,0.1197405,0.6468454],"study_design_scores_gemma":[0.0003865531,0.0004596003,0.01412983,0.001658568,0.0004504633,0.001003601,0.001859061,0.5691966,0.03555324,0.1239722,0.2507985,0.0005318314],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002046887,0.0001054571,0.9647052,0.0005009411,0.00006246056,0.001973061,0.002942071,0.02672919,0.0009346359],"genre_scores_gemma":[0.01048826,0.0001191275,0.9724008,0.0002418255,0.00003580484,0.001635651,0.0129758,0.001468406,0.000634314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0502281,"threshold_uncertainty_score":0.2656348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.130425068939352,"score_gpt":0.5168611613552492,"score_spread":0.3864360924158972,"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."}}