{"id":"W2175727069","doi":"10.1186/s12916-015-0521-2","title":"Naive Bayes classifiers for verbal autopsies: comparison to physician-based classification for 21,000 child and adult deaths","year":2015,"lang":"en","type":"article","venue":"BMC Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Public Health Ontario; University of Toronto; St. Michael's Hospital; Centre for Global Health Research","funders":"Medical Research Council; University of Toronto; University of the Witwatersrand, Johannesburg","keywords":"Medicine; Naive Bayes classifier; Population; Bayes' theorem; Cause of death; Verbal autopsy; Demography; Statistics; Machine learning; Internal medicine; Environmental health; Disease; Bayesian probability; Mathematics; Computer science","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":[0.0006616036,0.0002082189,0.0003873324,0.0001587533,0.0002067851,0.00004546923,0.0004805734,0.00009744213,0.00000305715],"category_scores_gemma":[0.001792085,0.000174088,0.00004957056,0.0003098263,0.0000904756,0.0001235647,0.00005350052,0.0001696185,0.00000562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001326888,"about_ca_system_score_gemma":0.0002010308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00015809,"about_ca_topic_score_gemma":0.00008965663,"domain_scores_codex":[0.9981468,0.0001110564,0.0003975919,0.0005948529,0.0003828229,0.0003668466],"domain_scores_gemma":[0.9976772,0.0007542275,0.0002018268,0.0005328219,0.0004522555,0.0003816836],"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":[0.001941803,0.0004634949,0.1151457,0.002988519,0.0001083703,0.000003873243,0.03363477,0.007738933,0.0007442309,0.2848592,0.2894396,0.2629315],"study_design_scores_gemma":[0.002489998,0.0015212,0.02075985,0.0002918341,0.0000268745,0.000002432069,0.001223091,0.9285391,0.0001510129,0.001348153,0.0434089,0.0002375385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007367413,0.0002921805,0.9649799,0.02412147,0.0006789331,0.001348147,0.0000251254,0.0002208576,0.0009660025],"genre_scores_gemma":[0.8964901,0.000003543265,0.09564343,0.006477468,0.0007406199,0.0003939965,0.00008709646,0.00002740515,0.0001363571],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9208002,"threshold_uncertainty_score":0.7099104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08408265151023099,"score_gpt":0.3649004892459965,"score_spread":0.2808178377357655,"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."}}