{"id":"W4385547547","doi":"10.1200/go.2023.9.supplement_1.107","title":"The use of machine learning models to predict PFS and OS outcomes from waterfall plots in randomized clinical trials (MAP-OUTCOMES).","year":2023,"lang":"en","type":"article","venue":"JCO Global Oncology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Waterfall; Medicine; Clinical endpoint; Randomized controlled trial; Sample size determination; Clinical trial; Statistics; Artificial intelligence; Internal medicine; Computer science; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01421514,0.0002532515,0.003065542,0.0001389011,0.00009479166,0.00004033994,0.000218034,0.000285044,0.00003355762],"category_scores_gemma":[0.03490876,0.0001397023,0.0004300191,0.0002812523,0.00037429,0.0000844223,0.000308747,0.000810663,0.00003289172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388961,"about_ca_system_score_gemma":0.0001880152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002650185,"about_ca_topic_score_gemma":0.000322156,"domain_scores_codex":[0.9926421,0.003972956,0.00204931,0.0004566811,0.0003974197,0.0004815091],"domain_scores_gemma":[0.9779588,0.02082285,0.0004563582,0.0003321107,0.00008023727,0.0003496258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.03790479,0.0003036747,0.801627,0.00003693374,0.0009800348,0.000286665,0.0006758593,0.006564423,0.0001123859,0.0009609722,0.006304842,0.1442424],"study_design_scores_gemma":[0.2147784,0.0009097122,0.1929858,0.0002029046,0.0007146828,0.0000249711,0.0001655451,0.520554,0.000007147197,0.003661278,0.06569641,0.0002990528],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9563086,0.0003850796,0.002228466,0.03778104,0.00120662,0.001494789,0.00005516575,0.0001477754,0.0003924351],"genre_scores_gemma":[0.9898782,0.001193186,0.003635948,0.004057151,0.0002181562,0.0000963636,0.00008432663,0.00003687381,0.0007997495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6086412,"threshold_uncertainty_score":0.9732206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1800737593164457,"score_gpt":0.4453138155587777,"score_spread":0.2652400562423319,"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."}}