{"id":"W2110349231","doi":"10.1140/epjds/s13688-015-0054-0","title":"Enhancing disease surveillance with novel data streams: challenges and opportunities","year":2015,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":239,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute of General Medical Sciences; Economic and Social Research Council; National Institutes of Health; Santa Fe Institute","keywords":"Computer science; Data science; Public health surveillance; Social media; Public health; Key (lock); Big data; Management science; Computer security; Data mining; World Wide Web; Engineering; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.002388034,0.000213357,0.0003123267,0.0001267842,0.0001403518,0.0001241859,0.001997999,0.00002402518,0.00001748331],"category_scores_gemma":[0.001866544,0.0001647302,0.000008689292,0.0002650831,0.001318246,0.002806684,0.002764277,0.0001263065,0.00001750232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098374,"about_ca_system_score_gemma":0.001901258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007822122,"about_ca_topic_score_gemma":0.0004962185,"domain_scores_codex":[0.9969103,0.00004501318,0.0002377401,0.001305895,0.001036141,0.0004649216],"domain_scores_gemma":[0.9932521,0.0001141957,0.0001207,0.005026563,0.0002629769,0.001223466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.004306178,0.00329751,0.2516147,0.002801885,0.0004747644,0.003965703,0.004473478,0.00004233699,0.01000939,0.01391057,0.04613005,0.6589734],"study_design_scores_gemma":[0.005964432,0.000639134,0.6634562,0.001166581,0.0002245035,0.0004627774,0.007252555,0.02477258,0.0003060361,0.0001575678,0.2939999,0.001597773],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7751907,0.06946392,0.006442674,0.02535396,0.001283554,0.002383196,0.100505,0.00123511,0.0181419],"genre_scores_gemma":[0.985813,0.00358789,0.005029009,0.0004913386,0.0001917333,0.000008925834,0.004632716,0.0000285175,0.0002168411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6573756,"threshold_uncertainty_score":0.6717502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2809649834510432,"score_gpt":0.349388351430047,"score_spread":0.06842336797900378,"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."}}