{"id":"W2902761513","doi":"10.12688/gatesopenres.12891.2","title":"Automated verbal autopsy classification: using one-against-all ensemble method and Naïve Bayes classifier","year":2019,"lang":"en","type":"preprint","venue":"Gates Open Research","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Centre for Global Health Research; St. Michael's Hospital; Toronto Metropolitan University","funders":"Bill and Melinda Gates Foundation","keywords":"Verbal autopsy; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Pattern recognition (psychology); Bayes' theorem; Computer science; Natural language processing; Bayesian probability; Support vector machine; Medicine; Pathology; Cause of death","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.006465381,0.0004123055,0.0007167684,0.0004986979,0.0004340498,0.003744357,0.005547997,0.0006459414,0.0000503066],"category_scores_gemma":[0.0003282555,0.000413752,0.0001048739,0.0006035165,0.0001627704,0.0008004652,0.01633154,0.001935042,0.0001661437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004802808,"about_ca_system_score_gemma":0.001528727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009075271,"about_ca_topic_score_gemma":0.00003466664,"domain_scores_codex":[0.9930331,0.001609992,0.0006940964,0.002154203,0.001433849,0.00107483],"domain_scores_gemma":[0.9948791,0.0008371448,0.000259202,0.002885977,0.0008122865,0.000326314],"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":[0.0002659608,0.0009364458,0.004072589,0.003042896,0.001452647,0.0003282973,0.01405493,0.08189851,0.1227741,0.3206405,0.01958898,0.4309441],"study_design_scores_gemma":[0.0004286382,0.00004542906,0.001634426,0.000377776,0.00001452366,0.000016487,0.0001044212,0.9790953,0.001324158,0.01243034,0.004071224,0.000457294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07396822,0.001032565,0.8763973,0.006197074,0.001271766,0.004163859,0.00003391257,0.0008395074,0.03609578],"genre_scores_gemma":[0.4688012,0.0001985308,0.5277619,0.0002360237,0.0001855379,0.0001932155,0.00005058384,0.00006369043,0.002509252],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8971968,"threshold_uncertainty_score":0.9998325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4047329856759461,"score_gpt":0.4866043839533529,"score_spread":0.08187139827740686,"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."}}