{"id":"W4210721182","doi":"10.2196/preprints.18735","title":"Balancing Accuracy and Privacy in Federated Queries of Clinical Data Repositories: Algorithm Development and Validation (Preprint)","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Homomorphic encryption; Scalability; Encryption; Benchmarking; k-anonymity; Matching (statistics); Anonymity; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03153743,0.0009194927,0.001826246,0.001755534,0.00115428,0.004646329,0.003418393,0.003069439,0.002341483],"category_scores_gemma":[0.1056687,0.0007456359,0.001745872,0.001843894,0.002599673,0.00583537,0.005026138,0.003049703,0.0008003836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004274383,"about_ca_system_score_gemma":0.006591654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003854582,"about_ca_topic_score_gemma":0.002828276,"domain_scores_codex":[0.9796168,0.01127897,0.00123647,0.002313516,0.004397836,0.001156476],"domain_scores_gemma":[0.8835363,0.08600278,0.004878033,0.01418658,0.01000904,0.00138736],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001190787,0.0005891012,0.01787357,0.0003264975,0.0002605919,0.0002979495,0.0005060838,0.7074641,0.004970307,0.05778279,0.00676849,0.2019697],"study_design_scores_gemma":[0.0000441431,0.00005037316,0.0003471087,0.00002282545,0.00001207277,0.00007759067,0.00003747534,0.9807016,0.001839408,0.01645793,0.0003998904,0.000009542646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05613786,0.0005765401,0.9359939,0.002440338,0.00009674235,0.0004176594,0.0004308641,0.002284128,0.001621961],"genre_scores_gemma":[0.5218782,0.0003548954,0.4739177,0.0008064327,0.0001511749,0.0004432818,0.0009150691,0.0001966055,0.001336503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9684626,"threshold_uncertainty_score":0.1667879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1200500064360257,"score_gpt":0.3720999191012157,"score_spread":0.2520499126651899,"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."}}