{"id":"W4389229885","doi":"10.1182/blood-2023-180132","title":"High Prevalence of Subjective Minimizing Language in Clinical Trials of Hematologic Malignancies: Natural Language Processing (NLP) Validation Study and Systematic Review of Randomized Controlled Trials Presented at ASH 2009-2021","year":2023,"lang":"en","type":"article","venue":"Blood","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Queen's University; University of Toronto; Western University","funders":"","keywords":"Medicine; Randomized controlled trial; Chin; Clinical trial; Natural language processing; Artificial intelligence; Medical physics; Computer science; Internal medicine","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":[0.5461682,0.001616518,0.00605805,0.0158057,0.002037711,0.007027011,0.003578279,0.003508263,0.002772729],"category_scores_gemma":[0.830716,0.001960109,0.01164459,0.01610349,0.006407345,0.007290385,0.007138948,0.003721199,0.0003773067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005303693,"about_ca_system_score_gemma":0.01396007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00224675,"about_ca_topic_score_gemma":0.004745918,"domain_scores_codex":[0.2237982,0.4997133,0.2143531,0.02508539,0.03581715,0.001232887],"domain_scores_gemma":[0.04033133,0.7942056,0.1220997,0.02627671,0.0162775,0.0008091147],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.008628991,0.0003626885,0.1402644,0.5442848,0.09194849,0.001285139,0.01828673,0.004131615,0.002684758,0.0103685,0.01389201,0.1638619],"study_design_scores_gemma":[0.01143049,0.00594352,0.2336405,0.3842155,0.1707925,0.005479342,0.00947014,0.02844224,0.009275647,0.05313074,0.0862296,0.001949827],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.3079568,0.3784175,0.2069997,0.02990484,0.001955957,0.0409331,0.02508274,0.001105309,0.007644081],"genre_scores_gemma":[0.8011882,0.02089968,0.1197951,0.009420144,0.0004683602,0.0401977,0.007334485,0.0003229536,0.0003733456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4538318,"threshold_uncertainty_score":0.5596554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2641413947815868,"score_gpt":0.4866435178447698,"score_spread":0.222502123063183,"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."}}