{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02284434,0.001059108,0.001663448,0.001790936,0.001143041,0.002998335,0.003659401,0.003466791,0.001951491],"category_scores_gemma":[0.0843607,0.0005925857,0.001356417,0.001837721,0.002519677,0.003894026,0.003926494,0.002961374,0.0004977721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004756059,"about_ca_system_score_gemma":0.006666803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00508387,"about_ca_topic_score_gemma":0.003026682,"domain_scores_codex":[0.9871721,0.006596114,0.0007788202,0.001783643,0.002786943,0.0008825131],"domain_scores_gemma":[0.900752,0.0771185,0.004694968,0.008648562,0.007538182,0.001247804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008082892,0.0004827328,0.01222628,0.0001855377,0.0001397974,0.0001416902,0.0002517684,0.8755329,0.002227189,0.01516599,0.002377632,0.09046017],"study_design_scores_gemma":[0.00005980115,0.00004327028,0.0002878976,0.00001409789,0.00000775329,0.00004834608,0.00002463328,0.9928293,0.000875705,0.005615752,0.0001877189,0.000005743782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1396925,0.0008538745,0.8508024,0.002372281,0.00008156306,0.0005771573,0.0004331771,0.003026203,0.002160755],"genre_scores_gemma":[0.6041981,0.0002641304,0.3931796,0.0004460971,0.0000699583,0.0004317545,0.0006331862,0.0001238012,0.000653438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02284434,"threshold_uncertainty_score":0.1208139,"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."}}