{"id":"W4412440980","doi":"10.1016/j.esmoop.2025.105509","title":"The use of machine learning models to predict progression-free survival and overall survival outcomes from waterfall plots in randomized clinical trials (MAP-OUTCOMES)","year":2025,"lang":"en","type":"article","venue":"ESMO Open","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Waterfall; Clinical endpoint; Confidence interval; Medicine; Randomized controlled trial; Progression-free survival; Logistic regression; Waterfall model; Artificial intelligence; Machine learning; Internal medicine; Statistics; Oncology; Overall survival; Computer science; Mathematics; Software; Cartography","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04353424,0.001127489,0.00175583,0.003638408,0.0002351441,0.002190214,0.001650784,0.001574158,0.001993016],"category_scores_gemma":[0.1312882,0.0006230877,0.003370413,0.001756519,0.0009106316,0.00206237,0.001267838,0.001965434,0.000497885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001207946,"about_ca_system_score_gemma":0.001713613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009005033,"about_ca_topic_score_gemma":0.001044191,"domain_scores_codex":[0.9764272,0.01941709,0.001387934,0.001342725,0.00120389,0.0002211162],"domain_scores_gemma":[0.8262246,0.1594381,0.009019884,0.002927658,0.001965608,0.0004241394],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005082616,0.0003589834,0.03598339,0.003539822,0.002077851,0.0005921698,0.0003056942,0.6723498,0.001597117,0.01073379,0.005833276,0.2615455],"study_design_scores_gemma":[0.0003112126,0.0005741208,0.002765248,0.0002454959,0.0002365272,0.0001397275,0.00002675419,0.9718997,0.0008698149,0.02066166,0.002233203,0.0000366071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07893368,0.004080348,0.9057265,0.002432664,0.0001449522,0.001692601,0.002909643,0.002767966,0.001311738],"genre_scores_gemma":[0.6806697,0.001181816,0.3100312,0.0006972131,0.0001765127,0.00357384,0.002721516,0.0001814134,0.0007667596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9564658,"threshold_uncertainty_score":0.2302338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1472286405677557,"score_gpt":0.4280689458158332,"score_spread":0.2808403052480775,"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."}}