{"id":"W2588203234","doi":"10.1186/s41512-016-0001-y","title":"Methods for Evaluating Medical Tests and Biomarkers","year":2017,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Calgary; McGill University; Jewish General Hospital; McMaster University; Population Health Research Institute","funders":"National Health and Medical Research Council; Haukeland Universitetssjukehus; Universiteit Leiden; Assistance publique-Hôpitaux de Paris; Leids Universitair Medisch Centrum; Universitetet i Bergen; Albert-Ludwigs-Universität Freiburg; Universiteit van Amsterdam; Abbott Diagnostics; University of Oxford; University of New South Wales; Medical Research Council; University of Notre Dame","keywords":"Equivalence (formal languages); Confidence interval; Statistics; Margin (machine learning); Sample (material); Medicine; Mathematics; Computer science; Chromatography; Machine learning; Chemistry","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":[],"category_scores_codex":[0.1011458,0.002711876,0.002197006,0.01290488,0.001861902,0.009360328,0.004348035,0.003185081,0.02597077],"category_scores_gemma":[0.3052483,0.001224222,0.003863116,0.006845762,0.004730384,0.007666673,0.006941277,0.003031822,0.006353382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003562614,"about_ca_system_score_gemma":0.007567154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002753841,"about_ca_topic_score_gemma":0.002498989,"domain_scores_codex":[0.8487698,0.1043293,0.01600471,0.009206624,0.02068337,0.001006201],"domain_scores_gemma":[0.6776246,0.2255219,0.02772821,0.03675025,0.03013617,0.002238899],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008187509,0.0003403742,0.01805294,0.004579467,0.0007959435,0.0002293367,0.002281838,0.005765898,0.001776162,0.2217222,0.02229698,0.7213401],"study_design_scores_gemma":[0.0005675708,0.0009332947,0.01574316,0.005789536,0.000935291,0.001354648,0.002643385,0.05655869,0.007942895,0.6713253,0.2356414,0.0005648162],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002700644,0.002066368,0.9720122,0.001776101,0.0003552473,0.003346362,0.002267812,0.001398434,0.0140768],"genre_scores_gemma":[0.03768568,0.00100769,0.9466219,0.000607293,0.0002151455,0.009597639,0.001209228,0.0002511868,0.002804192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8988541,"threshold_uncertainty_score":0.5349168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.269673097928087,"score_gpt":0.6196684686333537,"score_spread":0.3499953707052667,"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."}}