{"id":"W4412115660","doi":"10.1177/09622802251338409","title":"Health utility adjusted survival: A composite endpoint for clinical trial designs","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"Princess Margaret Cancer Foundation","keywords":"Sample size determination; Clinical endpoint; Clinical trial; Survival analysis; Quality of life (healthcare); Medicine; Randomized controlled trial; Statistical power; Statistics; Econometrics; Mathematics; Surgery; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4407431,0.0002345653,0.002549142,0.0007772596,0.0003596891,0.00009854938,0.0008459619,0.0005403138,0.002134742],"category_scores_gemma":[0.4413754,0.0002624519,0.0002151943,0.0009189703,0.0009685327,0.0001102427,0.0003014413,0.001865446,0.0002278078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009332932,"about_ca_system_score_gemma":0.002898579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001656069,"about_ca_topic_score_gemma":0.000524093,"domain_scores_codex":[0.9471559,0.03601436,0.01234715,0.001755113,0.0008726196,0.001854831],"domain_scores_gemma":[0.7836606,0.2124336,0.00101752,0.001101121,0.0003626543,0.001424524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004990905,0.0008331564,0.006812382,0.001033356,0.00008221648,0.000006111264,0.0002303161,0.000001318995,2.530666e-7,0.79022,0.06321903,0.132571],"study_design_scores_gemma":[0.0282167,0.001103558,0.06280681,0.0003580584,0.000007268797,0.00000116867,0.0006280864,0.05472798,0.000002260119,0.6561571,0.1956544,0.000336604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001359822,0.00158743,0.886362,0.1007194,0.002004624,0.003277745,0.0005920063,0.00004653179,0.004050406],"genre_scores_gemma":[0.01935688,0.0009356937,0.9625494,0.01394056,0.0008289756,0.001372367,0.0001481798,0.0000558277,0.0008120568],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1764193,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9207298509088987,"score_gpt":0.7660337274815276,"score_spread":0.154696123427371,"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."}}