{"id":"W2062707524","doi":"10.1371/journal.pone.0115892","title":"Machine Learning for Biomedical Literature Triage","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Genome Alberta; Genome Canada","keywords":"Triage; Computer science; Machine learning; Artificial intelligence; Naive Bayes classifier; Support vector machine; Task (project management); Set (abstract data type); Domain (mathematical analysis); Logistic regression; Data mining; Medicine; Engineering; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0002680598,0.0001004484,0.0001649432,0.00003314909,0.00007405397,0.00002161073,0.0001366996,0.000234484,0.00001937967],"category_scores_gemma":[0.001369339,0.00008027368,0.00006454121,0.00007019348,0.00009016399,0.000001013254,0.00005566388,0.0001421726,0.000009906894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003655784,"about_ca_system_score_gemma":0.00001460521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001560877,"about_ca_topic_score_gemma":0.000001572736,"domain_scores_codex":[0.9992328,0.00005826373,0.0001303918,0.0002395553,0.0001339852,0.0002049574],"domain_scores_gemma":[0.9995909,0.00005678728,0.00004268671,0.0001674817,0.00004867336,0.00009342088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000368997,0.001203428,0.002468053,0.0003000508,0.0003641467,0.000003517182,0.0001532204,0.000001548493,0.9127942,0.0003643058,0.005992644,0.07598586],"study_design_scores_gemma":[0.003163665,0.003352708,0.0005553651,0.0002450759,0.0001226021,0.000008044576,0.00003173529,0.004690174,0.1640988,0.0006745105,0.8226367,0.0004206201],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9264465,0.008934391,0.05369914,0.005492574,0.000336184,0.0006586488,0.000130442,0.0002628594,0.004039262],"genre_scores_gemma":[0.9693316,0.0002302016,0.0234381,0.0005334902,0.0009963058,0.00005426478,0.001016707,0.00002531169,0.00437397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.816644,"threshold_uncertainty_score":0.3273466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02749277960564432,"score_gpt":0.2516060964065917,"score_spread":0.2241133168009473,"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."}}