{"id":"W2754051415","doi":"10.1136/jech-2017-209608","title":"A glossary for big data in population and public health: discussion and commentary on terminology and research methods","year":2017,"lang":"en","type":"article","venue":"Journal of Epidemiology & Community Health","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Memorial University of Newfoundland","funders":"","keywords":"Big data; Glossary; Terminology; Data science; Analytics; Population; Population health; Public health; Data analysis; Computer science; Medicine; Data mining; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1015368,0.00294337,0.005468178,0.01635491,0.008614379,0.0153604,0.01478846,0.02428681,0.02041454],"category_scores_gemma":[0.249837,0.002168195,0.006647322,0.02553832,0.02120002,0.02654953,0.01434339,0.04196741,0.009109246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02015725,"about_ca_system_score_gemma":0.02230876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0369254,"about_ca_topic_score_gemma":0.03222983,"domain_scores_codex":[0.9188785,0.03548704,0.02140666,0.004697138,0.01759611,0.001934557],"domain_scores_gemma":[0.6604841,0.2749752,0.009853045,0.01100923,0.04076909,0.00290927],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002103491,0.000008078965,0.00005212325,0.002857837,0.0000223528,0.0001081191,0.002253241,0.0001071276,0.00009573293,0.1089233,0.874904,0.01064703],"study_design_scores_gemma":[0.00001749157,0.00001103917,0.0002387248,0.01318013,0.00002494056,0.0001896771,0.00105038,0.0001018474,0.00005561142,0.02929446,0.9557779,0.0000578254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.0001850406,0.1214781,0.01229958,0.7659726,0.07648539,0.0005002583,0.003840931,0.0001882335,0.01904998],"genre_scores_gemma":[0.005036207,0.1107176,0.02425222,0.7753182,0.05986433,0.004533931,0.003963084,0.000925364,0.01538903],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8984632,"threshold_uncertainty_score":0.5369841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8980856379065626,"score_gpt":0.7287880736224875,"score_spread":0.1692975642840751,"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."}}