{"id":"W4376130995","doi":"10.1016/j.jbi.2023.104384","title":"Deep learning to refine the identification of high-quality clinical research articles from the biomedical literature: Performance evaluation","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; McMaster University; Impact","funders":"","keywords":"Computer science; Identification (biology); Quality (philosophy); Data science; Artificial intelligence; Deep learning","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":[0.0181019,0.001659442,0.001482571,0.003824393,0.0004620478,0.001666416,0.001570163,0.001812255,0.001606241],"category_scores_gemma":[0.03639668,0.0005445794,0.001388817,0.001884221,0.0005234134,0.001745279,0.002295368,0.002246805,0.0006936986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001960177,"about_ca_system_score_gemma":0.003594494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0108882,"about_ca_topic_score_gemma":0.01238713,"domain_scores_codex":[0.9962708,0.001758624,0.000606204,0.0005148097,0.0006370202,0.0002124941],"domain_scores_gemma":[0.9762408,0.01709487,0.001417261,0.001614313,0.003049254,0.0005834652],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004661677,0.001384942,0.06679279,0.003126366,0.002694291,0.0002066777,0.0002670894,0.2558163,0.006191379,0.001414874,0.01195136,0.6454923],"study_design_scores_gemma":[0.0003629159,0.0008811107,0.007640282,0.0003327513,0.0005519166,0.0001577389,0.0001010498,0.9768395,0.008576254,0.002464894,0.002047112,0.00004459136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7595867,0.023218,0.1871099,0.004876989,0.0005854566,0.001386897,0.008602049,0.00747054,0.007163293],"genre_scores_gemma":[0.8899369,0.001817807,0.09773074,0.0006404709,0.0001216567,0.0003234606,0.007739665,0.00009250163,0.001596873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9818981,"threshold_uncertainty_score":0.09573317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.12669730255499,"score_gpt":0.452121140548754,"score_spread":0.3254238379937641,"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."}}