{"id":"W4414778497","doi":"10.18103/mra.v13i9.6896","title":"How to Measure the Generalizability of Clinical Trials","year":2025,"lang":"en","type":"article","venue":"Medical Research Archives","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Generalizability theory; Clinical trial; Sample size determination; Gold standard (test); Population; Sample (material); Covariate; Randomized controlled trial; Statistical power","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.378264,0.0001282429,0.001709439,0.0004851807,0.0002730975,0.00009795413,0.001200603,0.0001794299,0.0005787817],"category_scores_gemma":[0.6228433,0.00009865596,0.0003704749,0.000554514,0.0009564592,0.0001058819,0.000385193,0.0008655148,0.0002498646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008457041,"about_ca_system_score_gemma":0.001299169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000486628,"about_ca_topic_score_gemma":0.000176682,"domain_scores_codex":[0.9679875,0.0216949,0.007924493,0.000822941,0.0008089676,0.0007611592],"domain_scores_gemma":[0.8210614,0.1716413,0.002389712,0.002798287,0.0003883663,0.001720916],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002156994,0.0003516798,0.1105354,0.0005150439,0.0002519729,0.000001996418,0.001761424,0.00001044724,0.0000158991,0.5256135,0.26845,0.09227682],"study_design_scores_gemma":[0.001196322,0.0001856509,0.08063216,0.0002608664,0.000005556105,6.984002e-7,0.001458356,0.003643287,0.00003041779,0.1807783,0.7316611,0.0001472178],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.07919313,0.004456821,0.04910419,0.8415787,0.000924246,0.002040331,0.0001697119,0.00002892469,0.02250394],"genre_scores_gemma":[0.9590697,0.001361639,0.004356188,0.0234378,0.001702433,0.0005940117,0.00001834239,0.00003074982,0.009429075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8798766,"threshold_uncertainty_score":0.6402081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8714361004299229,"score_gpt":0.6675708400649946,"score_spread":0.2038652603649284,"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."}}