{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1167244,0.0001868496,0.001277762,0.0005923133,0.007155356,0.00002065622,0.0009280429,0.0004020258,0.000004369367],"category_scores_gemma":[0.05240007,0.0001294634,0.00003546147,0.0001072149,0.000823185,0.0004154401,0.001626322,0.005170932,8.467883e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006452738,"about_ca_system_score_gemma":0.0009262113,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1268749,"about_ca_topic_score_gemma":0.1339649,"domain_scores_codex":[0.9367887,0.05877449,0.002618515,0.0004078839,0.0001723846,0.001238032],"domain_scores_gemma":[0.9522307,0.04231753,0.002541945,0.00188276,0.0002945843,0.0007324888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000213008,0.0001026988,0.6501233,0.0005544153,0.00001212924,0.000001165372,0.003151216,4.128754e-7,0.000002585743,0.000939396,0.006405554,0.3384941],"study_design_scores_gemma":[0.0006965651,0.002307236,0.8970635,0.001243155,0.000005332521,0.00003282141,0.01188992,0.001255563,5.012494e-7,0.05598706,0.0294135,0.0001048293],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.518744,0.002909765,0.0009281062,0.4755704,0.0008069127,0.0009431669,0.00006751757,0.000007851771,0.00002224475],"genre_scores_gemma":[0.9370372,0.01017443,0.01908625,0.03275353,0.0007438114,0.00003806176,0.0001253344,0.00002761969,0.00001376715],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4428169,"threshold_uncertainty_score":0.9971242,"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."}}