{"id":"W2078902626","doi":"10.2196/jmir.2001","title":"De-identification Methods for Open Health Data: The Case of the Heritage Health Prize Claims Dataset","year":2012,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"ca_institutions":"Privacy Analytics (Canada); Agricultural Research Institute of Ontario; University of Ottawa","funders":"","keywords":"Health Insurance Portability and Accountability Act; Identification (biology); Context (archaeology); Computer science; Competition (biology); Public health; Big data; Data science; Data mining; Actuarial science; Business; Computer security; Confidentiality; Medicine; Geography","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":["metaresearch","open_science"],"category_scores_codex":[0.1167581,0.00009727562,0.0003276251,0.0001473852,0.0002501237,0.00041672,0.09754165,0.0001259996,0.00005175098],"category_scores_gemma":[0.09050529,0.00005108998,0.00005985305,0.0005994529,0.0005182617,0.001262616,0.1397514,0.001653022,0.000003635069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002964055,"about_ca_system_score_gemma":0.001755992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001748346,"about_ca_topic_score_gemma":0.0002284757,"domain_scores_codex":[0.992632,0.00390206,0.00105717,0.0003083299,0.001394983,0.0007054589],"domain_scores_gemma":[0.9824079,0.004350324,0.001056333,0.01129908,0.0003705639,0.0005158056],"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":[0.00001720547,0.0001339866,0.00008008452,0.00007232359,0.00003628835,0.00001638281,0.0003290175,1.586662e-7,0.00002767109,0.004675519,0.7790638,0.2155476],"study_design_scores_gemma":[0.001366436,0.0009107299,0.001301694,0.0008978713,0.00001724135,0.007471467,0.001868248,0.2196668,0.002594665,0.0994334,0.664266,0.0002054795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001019236,0.002127309,0.6231992,0.3721867,0.000602292,0.0005605172,0.0002819413,0.00001119915,0.00001162254],"genre_scores_gemma":[0.1685528,0.001394749,0.8259131,0.00324218,0.000540731,0.00005168532,0.0001405469,0.00002677023,0.0001373447],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3689445,"threshold_uncertainty_score":0.9171558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3991933750815713,"score_gpt":0.5972340287401202,"score_spread":0.1980406536585489,"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."}}