{"id":"W4320024352","doi":"10.1109/bigdata55660.2022.10020258","title":"Review of Publically Available Health Big Data Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Health informatics; Public health informatics; Computer science; Informatics; Usability; Data science; Dashboard; Data mining; Information retrieval; World Wide Web; Public health; Medicine; Health policy; International health; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.02283281,0.0003446123,0.0007724446,0.0006014536,0.0004136508,0.0007487819,0.03879162,0.00005472701,0.01333064],"category_scores_gemma":[0.007644592,0.0003099359,0.00007111667,0.00131025,0.0002171208,0.002426151,0.03510995,0.0006791715,0.001720524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001647721,"about_ca_system_score_gemma":0.001615119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001394118,"about_ca_topic_score_gemma":0.001752737,"domain_scores_codex":[0.9871895,0.001328427,0.002143914,0.002861492,0.005934084,0.0005425894],"domain_scores_gemma":[0.9789383,0.0009062659,0.001566848,0.01765819,0.0006188772,0.0003115143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004630001,0.0002833316,0.00003851975,0.0001514346,0.00007721219,0.00001125277,0.00001722076,0.000002242099,0.000018643,0.006074741,0.6461211,0.347158],"study_design_scores_gemma":[0.0004644484,0.0001475755,0.0001167916,0.0005437565,0.00002954715,0.0000162624,0.0003093175,0.006916731,0.000007550864,0.001921572,0.9892234,0.0003030168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001490502,0.005669428,0.0188944,0.1130892,0.02354572,0.0015442,0.7918164,0.0001433642,0.04514833],"genre_scores_gemma":[0.02511134,0.0704499,0.002573376,0.07330798,0.002118886,0.0001657913,0.8058515,0.000081982,0.0203393],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.346855,"threshold_uncertainty_score":0.9999353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8077064389291911,"score_gpt":0.5061207953285485,"score_spread":0.3015856436006427,"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."}}