{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6339834,0.003188723,0.007155071,0.01125806,0.002153451,0.01120192,0.004774048,0.007987923,0.004688053],"category_scores_gemma":[0.8937691,0.002190643,0.01184773,0.009968053,0.01137007,0.01266156,0.006869329,0.01038069,0.001471036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005767614,"about_ca_system_score_gemma":0.01163634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003009035,"about_ca_topic_score_gemma":0.001665394,"domain_scores_codex":[0.2614775,0.5795327,0.08646948,0.02267968,0.04837269,0.0014679],"domain_scores_gemma":[0.05640079,0.8327813,0.03906292,0.04358802,0.02679455,0.0013725],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004427661,0.0005702624,0.06970236,0.03668611,0.03986907,0.0007237006,0.006026027,0.02999267,0.001613791,0.09743746,0.04631731,0.6666335],"study_design_scores_gemma":[0.006156661,0.004907837,0.06551974,0.04531303,0.02379815,0.001529792,0.003190903,0.07360963,0.005998713,0.6266645,0.1419784,0.001332554],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02100389,0.05617491,0.8061892,0.05050049,0.01222182,0.02755651,0.004318287,0.00297376,0.01906116],"genre_scores_gemma":[0.3119629,0.007736458,0.6196473,0.01540285,0.003612678,0.03844949,0.001393821,0.0008291421,0.0009654037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3660166,"threshold_uncertainty_score":0.4513637,"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."}}