{"id":"W4402747738","doi":"10.1371/journal.pdig.0000299","title":"Boosting efficiency in a clinical literature surveillance system with LightGBM","year":2024,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"Mitacs","keywords":"Boosting (machine learning); Computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08853213,0.001446945,0.003527673,0.01187253,0.001176193,0.004937278,0.003105804,0.002573615,0.002587701],"category_scores_gemma":[0.1842291,0.001125086,0.002159483,0.005130053,0.001128532,0.004100134,0.004607711,0.001887235,0.003024737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00237844,"about_ca_system_score_gemma":0.005129573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004712546,"about_ca_topic_score_gemma":0.004522087,"domain_scores_codex":[0.9682214,0.01741537,0.004519796,0.004550458,0.004549054,0.0007439967],"domain_scores_gemma":[0.8701783,0.08856568,0.01032896,0.0135641,0.01581191,0.001551122],"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":[0.003844809,0.000961189,0.1146319,0.002835684,0.001392798,0.0004986731,0.001658666,0.05980768,0.006943117,0.005301171,0.02605667,0.7760677],"study_design_scores_gemma":[0.0006458213,0.0006699128,0.01489277,0.0005988355,0.000614276,0.0004536466,0.0002776708,0.9417751,0.009134282,0.01857189,0.01223916,0.0001266113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2139901,0.006501155,0.7035596,0.006688562,0.0004479761,0.003869216,0.005246369,0.05265308,0.007043859],"genre_scores_gemma":[0.4446317,0.0004604937,0.545292,0.001812019,0.0002396211,0.001500175,0.004563226,0.0004842894,0.001016591],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9114679,"threshold_uncertainty_score":0.4682083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02264850416043103,"score_gpt":0.3076604598499421,"score_spread":0.2850119556895111,"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."}}