{"id":"W3097555876","doi":"10.2196/18735","title":"Balancing Accuracy and Privacy in Federated Queries of Clinical Data Repositories: Algorithm Development and Validation","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"U.S. National Library of Medicine; National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Computer science; Homomorphic encryption; Scalability; Benchmarking; Obfuscation; Encryption; Matching (statistics); Masking (illustration); Anonymity; Probabilistic logic; Data mining; Computer network; Computer security; Database","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":[0.0119787,0.00009236311,0.0003822746,0.0001869951,0.0000462178,0.0002719353,0.01378271,0.0001968183,0.00001375733],"category_scores_gemma":[0.2383669,0.00007144056,0.00001823977,0.0004712515,0.0003417553,0.001025977,0.06866267,0.001451396,0.000001242253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004704147,"about_ca_system_score_gemma":0.0007805156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009170856,"about_ca_topic_score_gemma":0.00001076366,"domain_scores_codex":[0.9956418,0.0005497925,0.00130833,0.0003934927,0.001855929,0.0002506493],"domain_scores_gemma":[0.9935486,0.003081714,0.0005354928,0.0018945,0.0005226417,0.0004170825],"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":[0.000117858,0.0001677878,0.03744999,0.000185745,0.000109019,0.0008013476,0.002090471,2.920995e-7,0.0002251305,0.0003470746,0.09793039,0.8605749],"study_design_scores_gemma":[0.003136368,0.001370744,0.02766874,0.002344636,0.00001157894,0.0006562617,0.001359077,0.8791901,0.02866079,0.008160742,0.0470863,0.0003546586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6467475,0.0009267646,0.2641603,0.08756962,0.0003591929,0.0001521326,0.0000038669,0.00003739932,0.00004323934],"genre_scores_gemma":[0.7047887,0.001137109,0.2937394,0.0001187947,0.0001931914,0.00000190206,0.000006452996,0.000007167148,0.00000726181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8791898,"threshold_uncertainty_score":0.9915532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2284963894243774,"score_gpt":0.4713326765640463,"score_spread":0.242836287139669,"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."}}