{"id":"W3190429369","doi":"10.3389/fmed.2021.541405","title":"Interpretable Trials: Is Interpretability a Reason Why Clinical Trials Fail?","year":2021,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Taipei Veterans General Hospital; National Yang-Ming University","keywords":"Interpretability; Clinical trial; Medicine; Internal medicine; Machine learning; Computer science","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":[0.6896908,0.003060976,0.007481232,0.01393565,0.002468611,0.01374909,0.007088101,0.008113592,0.005663581],"category_scores_gemma":[0.9036596,0.002831812,0.00638318,0.01194222,0.01870678,0.0178392,0.006206216,0.008956178,0.001163346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01129949,"about_ca_system_score_gemma":0.01328089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003905934,"about_ca_topic_score_gemma":0.002781215,"domain_scores_codex":[0.1620796,0.6303601,0.1172054,0.02403112,0.06402272,0.002301101],"domain_scores_gemma":[0.02615495,0.8752309,0.05493542,0.02743696,0.0153348,0.0009069591],"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":[0.01003734,0.0006529359,0.1722354,0.09452971,0.03195978,0.002694084,0.03147313,0.01148044,0.001569274,0.1620045,0.08431228,0.3970512],"study_design_scores_gemma":[0.00451947,0.002089308,0.06338716,0.09214019,0.01087092,0.003364754,0.006251135,0.02357336,0.003412285,0.676703,0.1124217,0.001266799],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06666411,0.241218,0.3522198,0.2665277,0.01923903,0.01415639,0.008898173,0.00166447,0.02941248],"genre_scores_gemma":[0.7393014,0.022415,0.1322075,0.07393353,0.01078934,0.01548793,0.003334072,0.0008354395,0.00169582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3103092,"threshold_uncertainty_score":0.3826666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6255882384944831,"score_gpt":0.5602184036678927,"score_spread":0.06536983482659042,"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."}}