{"id":"W4383265828","doi":"10.1186/s12916-023-02937-0","title":"Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"review","venue":"BMC Medicine","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Robarts Clinical Trials; Canada Research Chairs; Women's College Hospital; University of Toronto","funders":"Genentech; National Institutes of Health; Sierra Oncology; Astellas Pharma; Eisai; National Center for Advancing Translational Sciences; Medical Research Council; Department of Health and Social Care; National Institute for Health and Care Research; Cancer Research UK; Plexxikon; Seagen; Pfizer; NuCana; Sanofi; Celgene; PTC Therapeutics; UK Research and Innovation; Halozyme; Medical Research Charities Group; BeiGene; GlaxoSmithKline; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Consolidated Standards of Reporting Trials; Medicine; Delphi method; Delphi; Clinical trial; Protocol (science); Thematic analysis; Alternative medicine; Medical education; Family medicine; Qualitative research; Computer science; Pathology; Social science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04250966,0.0005350944,0.005889945,0.0005188856,0.0002954931,0.00001776912,0.0004532698,0.0006291519,0.0001130793],"category_scores_gemma":[0.2115499,0.0002744301,0.000489969,0.0007386533,0.0011877,0.00001293679,0.0003772612,0.00208857,0.00003771129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001199732,"about_ca_system_score_gemma":0.004281503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004379934,"about_ca_topic_score_gemma":0.0002940222,"domain_scores_codex":[0.9909133,0.001145781,0.004712144,0.0009369081,0.001740296,0.0005515748],"domain_scores_gemma":[0.8408847,0.154725,0.001564114,0.001326825,0.001005006,0.0004943222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001611036,0.001955132,0.000804765,0.1290245,0.004523795,0.000332064,0.003842616,2.339147e-7,0.00005561059,0.003897555,0.007448432,0.8465043],"study_design_scores_gemma":[0.02489491,0.005277094,0.000736592,0.1266692,0.0118906,0.0001397644,0.003368753,0.00003096723,0.000004954921,0.000792263,0.8256791,0.0005158198],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004267855,0.9791461,0.0002475334,0.001546143,0.0006016982,0.0137499,0.0001003241,0.00008417729,0.0002562347],"genre_scores_gemma":[0.0003572413,0.9888762,0.005697586,0.0001282447,0.0008252415,0.001020513,0.000117808,0.0001387047,0.002838525],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8459885,"threshold_uncertainty_score":0.9999708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9512150326794244,"score_gpt":0.7285636789994865,"score_spread":0.2226513536799379,"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."}}