{"id":"W4387357939","doi":"10.2196/44892","title":"A Multilabel Text Classifier of Cancer Literature at the Publication Level: Methods Study of Medical Text Classification","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Terminology; Information retrieval; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007103955,0.0008285033,0.0009354317,0.005038618,0.0007671016,0.001818099,0.001527309,0.001591585,0.001885704],"category_scores_gemma":[0.01964071,0.0002113494,0.00110125,0.003022821,0.0008448742,0.0028722,0.001284595,0.001828467,0.001179929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001628257,"about_ca_system_score_gemma":0.001898831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003462703,"about_ca_topic_score_gemma":0.003204001,"domain_scores_codex":[0.9964336,0.00130292,0.0003499797,0.0009119182,0.0007559195,0.0002456924],"domain_scores_gemma":[0.9783327,0.01572927,0.00147282,0.001419533,0.002550526,0.0004950934],"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":[0.001648425,0.0009625068,0.06848899,0.0009870578,0.0004852155,0.0004706293,0.0006785411,0.05560931,0.01063542,0.007705152,0.01245684,0.8398718],"study_design_scores_gemma":[0.00006879075,0.000313492,0.01068649,0.000106059,0.0001540069,0.0003175345,0.0002964128,0.9670515,0.007833164,0.009527321,0.003600942,0.00004429135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4362189,0.005681768,0.5423126,0.002609585,0.0005184475,0.000741373,0.004232867,0.002782463,0.004902023],"genre_scores_gemma":[0.7986684,0.0006396916,0.1896796,0.0003017879,0.0004392169,0.0004372509,0.005499216,0.0001149828,0.004219803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.992896,"threshold_uncertainty_score":0.0375697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08301918992268613,"score_gpt":0.4361605030102835,"score_spread":0.3531413130875974,"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."}}