{"id":"W2801170057","doi":"10.2196/10281","title":"A Deep Learning Method to Automatically Identify Reports of Scientifically Rigorous Clinical Research from the Biomedical Literature: Comparative Analytic Study","year":2018,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"U.S. National Library of Medicine; National Institute of Diabetes and Digestive and Kidney Diseases; Advanced Research Projects Agency; National Cancer Institute; Canadian Institutes of Health Research; Defense Advanced Research Projects Agency","keywords":"Computer science; Data science; Artificial intelligence; Management science; Information retrieval; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0736534,0.0001924855,0.0007352925,0.000467009,0.0002379505,0.0002558376,0.002238358,0.000606921,0.0004360174],"category_scores_gemma":[0.0467621,0.000109661,0.0002892524,0.001522987,0.004009271,0.00001116192,0.001623623,0.00351147,0.00004872985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005658631,"about_ca_system_score_gemma":0.0007917367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002179445,"about_ca_topic_score_gemma":0.0002317956,"domain_scores_codex":[0.98182,0.008208741,0.002106819,0.0007258845,0.006393686,0.0007448316],"domain_scores_gemma":[0.9900855,0.004172083,0.0004305314,0.0007382574,0.003566885,0.001006748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004772643,0.008878425,0.05367419,0.0001306255,0.003727963,0.005508809,0.03112501,0.00001153553,0.03801664,0.0002667875,0.5002296,0.3536578],"study_design_scores_gemma":[0.007885877,0.0922336,0.2612905,0.004801972,0.0003943446,0.002943935,0.04288785,0.02699903,0.01936084,0.004660266,0.5354298,0.001112026],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9552241,0.001057866,0.03746993,0.004822288,0.0008054769,0.0003696684,0.00000447838,0.00001066219,0.0002355018],"genre_scores_gemma":[0.9875772,0.00006258862,0.009612339,0.0001784317,0.001959424,0.00001251635,0.00001874753,0.00001772234,0.0005610179],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3525457,"threshold_uncertainty_score":0.9987875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2043903966499804,"score_gpt":0.5821262361261871,"score_spread":0.3777358394762066,"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."}}