{"id":"W1945159329","doi":"10.1136/amiajnl-2012-001027","title":"Privacy-preserving heterogeneous health data sharing","year":2012,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Center for Research Resources; U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; Agency for Healthcare Research and Quality","keywords":"Differential privacy; Computer science; Data mining; Scalability; Data publishing; Information privacy; Discriminative model; Information sensitivity; Raw data; Private information retrieval; Privacy software; Probabilistic logic; Data anonymization; Machine learning; Computer security; Artificial intelligence; Database; Publishing","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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.008202399,0.0001293188,0.0003859244,0.0001365841,0.0001861799,0.0001932493,0.06106177,0.00008110655,0.0000109833],"category_scores_gemma":[0.09491753,0.00008825002,0.00009670809,0.000718871,0.00008031651,0.002625424,0.1162925,0.0008099324,0.00001397754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007237261,"about_ca_system_score_gemma":0.0003342688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004952521,"about_ca_topic_score_gemma":0.000004882179,"domain_scores_codex":[0.995923,0.0001860547,0.001188659,0.0001078758,0.002036179,0.0005582392],"domain_scores_gemma":[0.9863616,0.0005129517,0.005102895,0.007518768,0.0001746775,0.0003290592],"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":[0.000008354402,0.0001846439,0.09584627,0.00007395226,0.0002940044,0.000003960592,0.001887342,0.00007350372,0.00002235756,0.000380288,0.7468331,0.1543922],"study_design_scores_gemma":[0.000691683,0.0002272547,0.02226106,0.0004164531,0.00004482186,0.000411181,0.0005130746,0.9282295,0.0003594064,0.01873713,0.02771682,0.0003916949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2290561,0.0005589802,0.5542895,0.2126669,0.002587606,0.0002424386,0.0000268112,0.0002239231,0.0003477504],"genre_scores_gemma":[0.5902758,0.0006797598,0.4003251,0.008172444,0.0004991489,0.000002113156,0.000009328736,0.00001749958,0.00001881829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281559,"threshold_uncertainty_score":0.9440184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05159888266659976,"score_gpt":0.3364032246551978,"score_spread":0.2848043419885981,"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."}}