{"id":"W4415153955","doi":"10.1002/sim.70269","title":"Specification of Estimands for Complex Disease Processes Using Multistate Models and Utility Functions","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Jackknife resampling; Ranking (information retrieval); Disease; Simplicity; Variance (accounting); Resampling; Clinical trial","routes":{"ca_aff":true,"ca_fund":true,"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":[0.06095469,0.002016053,0.003377179,0.002818011,0.0005175565,0.003990479,0.002298286,0.002495771,0.003046621],"category_scores_gemma":[0.1248375,0.001093173,0.003150172,0.002290722,0.002645534,0.003477145,0.002681852,0.005292518,0.000468523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001933759,"about_ca_system_score_gemma":0.003151704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003338509,"about_ca_topic_score_gemma":0.002477831,"domain_scores_codex":[0.9710675,0.02493439,0.0008380593,0.001295418,0.001177837,0.0006868174],"domain_scores_gemma":[0.8301061,0.1584147,0.005359966,0.003778886,0.001760086,0.0005802506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002799246,0.0001359087,0.006223742,0.0003816402,0.0004949355,0.0002778287,0.0003160864,0.5413386,0.0003361795,0.417163,0.00151721,0.03153495],"study_design_scores_gemma":[0.00006471457,0.0001416165,0.0009161208,0.0001108247,0.00008396801,0.00006490995,0.00006249078,0.7212766,0.0002886939,0.2758564,0.001095062,0.00003863374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009505335,0.0004755075,0.9879972,0.0008097407,0.00003303939,0.0001927188,0.0002557457,0.0001086785,0.0006221267],"genre_scores_gemma":[0.5611824,0.002508289,0.4266909,0.0007732066,0.0002155982,0.003268925,0.001412008,0.0001636257,0.00378502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06095469,"threshold_uncertainty_score":0.3223631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7557390693740194,"score_gpt":0.6269280900231367,"score_spread":0.1288109793508827,"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."}}