{"id":"W2994498882","doi":"10.6004/jnccn.2019.7333","title":"Are Surrogate Endpoints Unbiased Metrics in Clinical Benefit Scores of the ASCO Value Framework?","year":2019,"lang":"en","type":"article","venue":"Journal of the National Comprehensive Cancer Network","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; Canadian Agency for Drugs and Technologies in Health; University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Surrogate endpoint; Hazard ratio; Internal medicine; Clinical endpoint; Randomized controlled trial; Clinical trial; Progression-free survival; Overall survival; Oncology; Confidence interval","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1710078,0.001178221,0.002191951,0.004079643,0.0005630709,0.004868482,0.00144704,0.001228956,0.002219535],"category_scores_gemma":[0.4276328,0.0005490925,0.002150284,0.003648933,0.003510584,0.004327255,0.003107407,0.003138427,0.0005358439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003478145,"about_ca_system_score_gemma":0.00366989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001832457,"about_ca_topic_score_gemma":0.001662718,"domain_scores_codex":[0.851492,0.1151649,0.008299989,0.005765049,0.01794612,0.001331829],"domain_scores_gemma":[0.6193419,0.2849632,0.05055134,0.0174775,0.02537691,0.00228924],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003876758,0.0002718207,0.2945099,0.00232606,0.005212461,0.0001779338,0.001999258,0.03691619,0.0008000851,0.1325286,0.0182734,0.5031075],"study_design_scores_gemma":[0.001488115,0.004018759,0.1725773,0.005165058,0.00248935,0.0008974719,0.00126197,0.1782757,0.00316543,0.572966,0.05714294,0.0005519871],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2452268,0.05336229,0.6496274,0.02164339,0.00134647,0.001520316,0.003888756,0.0003644574,0.02302014],"genre_scores_gemma":[0.8896707,0.002279491,0.1019554,0.002769169,0.0006275037,0.00116494,0.001078531,0.0001291659,0.0003251639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8289921,"threshold_uncertainty_score":0.9043867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3911725397162,"score_gpt":0.4721492326583674,"score_spread":0.08097669294216742,"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."}}