{"id":"W4413879034","doi":"10.1186/s12911-025-03109-1","title":"Enhancing privacy protection of physical examination data through synthetic algorithms based on differential privacy","year":2025,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Differential privacy; Health informatics; Computer science; Privacy protection; Information privacy; Algorithm; Internet privacy; Data mining; Public health; Medicine; Nursing","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":[0.001242398,0.0001868837,0.000318215,0.0002971358,0.0001629887,0.0001989697,0.01060093,0.0001828845,0.00001163068],"category_scores_gemma":[0.03598384,0.0001465306,0.00004825397,0.0005990772,0.0001347851,0.0009919691,0.03651957,0.0003604616,0.000005526145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005165061,"about_ca_system_score_gemma":0.0002102313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004633051,"about_ca_topic_score_gemma":0.000002404399,"domain_scores_codex":[0.9973072,0.00008995683,0.0007562995,0.0003671889,0.001227859,0.0002514404],"domain_scores_gemma":[0.9917791,0.002375679,0.0003256214,0.005368067,0.00009311632,0.00005841146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002226249,0.00013398,0.00002499743,0.0002925924,0.00001007553,0.00000181384,0.0002123497,0.0000836792,0.00006153889,0.003507139,0.0006955201,0.994954],"study_design_scores_gemma":[0.0005090765,0.00009221899,0.0003452438,0.001736424,0.00001092852,0.000003923763,0.00005362173,0.9346815,0.001528415,0.06072764,0.00018407,0.0001269399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05721939,0.00002148854,0.9413977,0.0002760053,0.0002846539,0.0003171036,0.00000947122,0.0001798313,0.0002943811],"genre_scores_gemma":[0.4745992,0.00001269689,0.5252489,0.00009131839,0.00002224301,0.0000114532,0.000008976354,0.000004092619,0.000001069589],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9948271,"threshold_uncertainty_score":0.9947522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05910290888713675,"score_gpt":0.3450175718174333,"score_spread":0.2859146629302965,"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."}}