{"id":"W4407674404","doi":"10.1177/0272989x251314010","title":"Expected Value of Sample Information Calculations for Risk Prediction Model Validation","year":2025,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"National Cancer Institute; Canadian Institutes of Health Research; National Institutes of Health; Memorial Sloan-Kettering Cancer Center","keywords":"Sample size determination; False positive paradox; Statistics; Population; Computer science; Sample (material); Computation; Econometrics; Data mining; Mathematics; Algorithm; 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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0113531,0.0001192437,0.0005254183,0.0006205304,0.000254238,0.00005232202,0.0002256541,0.0002400099,0.0002367328],"category_scores_gemma":[0.0526811,0.000141799,0.0001394629,0.0003705081,0.00004502375,0.0006794607,0.00005851508,0.0001473516,0.00007106017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003165973,"about_ca_system_score_gemma":0.000248888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001724618,"about_ca_topic_score_gemma":0.00002467303,"domain_scores_codex":[0.9950253,0.0001439259,0.004084122,0.000277599,0.0002545464,0.0002144408],"domain_scores_gemma":[0.9932817,0.004357952,0.001701025,0.0003640899,0.0001989646,0.00009625294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001055229,0.0001294935,0.04765128,0.0003986846,0.0001004258,7.801697e-8,0.001703618,0.1466947,0.000002466878,0.7319871,0.03668318,0.03454342],"study_design_scores_gemma":[0.0007098899,0.00002560358,0.01085936,0.0002361443,0.00001134367,3.370265e-7,0.0001566952,0.783985,0.000007125186,0.1959002,0.008022703,0.00008557622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08673726,0.0001365672,0.9073375,0.002598809,0.0006321133,0.0006927673,0.0008306192,0.00005520028,0.0009791853],"genre_scores_gemma":[0.8620302,0.00006055677,0.1343816,0.002883884,0.0001278807,0.0001955314,0.0002535989,0.00001344172,0.00005330918],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7752929,"threshold_uncertainty_score":0.9552985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2077751694750198,"score_gpt":0.4581390370143673,"score_spread":0.2503638675393475,"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."}}