{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007664636,0.0001227086,0.0002126676,0.0001312923,0.00007652452,0.001027708,0.0003910832,0.00005117046,4.638885e-7],"category_scores_gemma":[0.0001120213,0.000088176,0.00003471276,0.0009352249,0.00002464789,0.0007163024,0.00008561253,0.000404901,0.00008083761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000100665,"about_ca_system_score_gemma":0.000288786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002252699,"about_ca_topic_score_gemma":0.00002281517,"domain_scores_codex":[0.9982917,0.0001372497,0.0004441875,0.0005548096,0.0002689027,0.0003031993],"domain_scores_gemma":[0.998948,0.000344029,0.00009399473,0.0004354265,0.00004169631,0.0001368619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005856879,0.0007601714,0.2159733,0.005328368,0.00004849818,0.000501994,0.004517256,0.0001752906,0.000008506008,0.2536184,0.001501436,0.5175083],"study_design_scores_gemma":[0.0005070365,0.0009573261,0.1149683,0.005780135,0.000002300928,0.0002182283,0.0001161547,0.8667079,0.000003794976,0.0001771829,0.01010961,0.0004519585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3718191,0.01791833,0.5277221,0.02583831,0.001975549,0.001687813,0.0002341232,0.005547823,0.04725694],"genre_scores_gemma":[0.9981646,0.00002867979,0.001344228,0.0001381752,0.0001049908,0.000009508359,0.00004650959,0.00001137549,0.0001519292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8665327,"threshold_uncertainty_score":0.991021,"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."}}