{"id":"W4247917985","doi":"10.12688/gatesopenres.12891.1","title":"Automated verbal autopsy classification: using one-against-all ensemble method and Naïve Bayes classifier","year":2018,"lang":"en","type":"preprint","venue":"Gates Open Research","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Centre for Global Health Research; St. Michael's Hospital; Toronto Metropolitan University","funders":"Bill and Melinda Gates Foundation","keywords":"Verbal autopsy; Concordance; Classifier (UML); Bayes' theorem; Medical diagnosis; Population; Artificial intelligence; Statistics; Naive Bayes classifier; Cause of death; Medicine; Machine learning; Computer science; Mathematics; Internal medicine; Bayesian probability; Pathology; Environmental health","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"],"consensus_categories":[],"category_scores_codex":[0.006253469,0.0005362972,0.001228367,0.0005595465,0.0004437718,0.001083433,0.001623507,0.0007278355,0.0007137367],"category_scores_gemma":[0.001560068,0.000514625,0.0001607835,0.0006920325,0.0007753069,0.0003188006,0.006830075,0.001889012,0.000457603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006872377,"about_ca_system_score_gemma":0.002302435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007602997,"about_ca_topic_score_gemma":0.00009331857,"domain_scores_codex":[0.9924077,0.0018794,0.0008367701,0.001986336,0.001701521,0.001188262],"domain_scores_gemma":[0.9937441,0.0007630656,0.0003123486,0.002562648,0.001805558,0.0008122865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008223244,0.003869345,0.05786675,0.01095536,0.007128284,0.001981537,0.004341763,0.0003999351,0.2705829,0.006071877,0.487621,0.140958],"study_design_scores_gemma":[0.005358195,0.0006334988,0.2164582,0.004480694,0.0004977057,0.0001624636,0.0006972824,0.6378664,0.006665463,0.005939267,0.1194394,0.001801363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.817633,0.003582836,0.003578608,0.009106772,0.001332722,0.01428999,0.002456288,0.002011486,0.1460083],"genre_scores_gemma":[0.8486974,0.001167687,0.1357161,0.0007882282,0.001100199,0.000808201,0.004638524,0.0003346696,0.006748955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6374664,"threshold_uncertainty_score":0.9999535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3803490711206243,"score_gpt":0.524560363374478,"score_spread":0.1442112922538537,"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."}}