{"id":"W4379653782","doi":"10.1158/2767-9764.c.6684845","title":"Data from Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Generalizability theory; Radiomics; Artificial intelligence; Machine learning; Computer science; Deep learning; Artificial neural network; Medical imaging; Medicine; Medical physics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01794757,0.001081897,0.0007847687,0.001614569,0.0005078762,0.001433859,0.002380709,0.001859866,0.0009981713],"category_scores_gemma":[0.04161176,0.0003899153,0.001928894,0.001680395,0.00125102,0.00162659,0.003258913,0.001896063,0.0004852599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001629915,"about_ca_system_score_gemma":0.0014768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01444827,"about_ca_topic_score_gemma":0.0122634,"domain_scores_codex":[0.9944405,0.003433452,0.0002957428,0.001008491,0.0005892671,0.0002324693],"domain_scores_gemma":[0.9720656,0.01683191,0.002020728,0.006077437,0.002148954,0.000855427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003322036,0.001498142,0.5398655,0.0007294914,0.002122512,0.0003971308,0.0008020336,0.2944876,0.001616443,0.002118376,0.01216634,0.1408745],"study_design_scores_gemma":[0.0003365468,0.001256123,0.1769668,0.0002934412,0.0005250419,0.0003293016,0.000893886,0.7990176,0.005357231,0.005979937,0.008868875,0.0001752436],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.9648731,0.001180439,0.01815088,0.002393643,0.0002604173,0.000328973,0.009974257,0.0008304009,0.002007824],"genre_scores_gemma":[0.9766981,0.0001990988,0.009597129,0.0003008062,0.0000585106,0.0001416445,0.01261875,0.00005258739,0.0003332947],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01794757,"threshold_uncertainty_score":0.09491694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1442536740209812,"score_gpt":0.4354463554961185,"score_spread":0.2911926814751373,"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."}}