{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00631636,0.002200684,0.002140294,0.003412268,0.001168075,0.001515109,0.001802569,0.001633827,0.001881075],"category_scores_gemma":[0.009251404,0.0003585679,0.001718671,0.001395554,0.0003570858,0.001066266,0.00107774,0.001573064,0.001152089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007632934,"about_ca_system_score_gemma":0.00167465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01289175,"about_ca_topic_score_gemma":0.01240976,"domain_scores_codex":[0.9965081,0.001210509,0.0003982726,0.0008981384,0.0006542167,0.0003307415],"domain_scores_gemma":[0.9950475,0.002309365,0.0002948891,0.0005130153,0.001647323,0.0001879579],"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":[0.0008122555,0.0006168221,0.03581306,0.0002099744,0.0007531132,0.0003160527,0.0001847692,0.1174937,0.004111059,0.001056316,0.01277331,0.8258595],"study_design_scores_gemma":[0.0000445703,0.0002333305,0.004779278,0.00005736792,0.0002147615,0.0001454121,0.0001183392,0.9861921,0.003678057,0.002357727,0.002136967,0.00004208518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3606609,0.003685522,0.6147294,0.001414817,0.001249044,0.0007708687,0.003107288,0.007758459,0.006623629],"genre_scores_gemma":[0.7400326,0.0004887517,0.2472841,0.0005104728,0.0004653985,0.000298523,0.006878052,0.0002099529,0.003832242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01289175,"threshold_uncertainty_score":0.03340453,"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."}}