{"id":"W3080942770","doi":"10.2196/18920","title":"Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Australian Government","keywords":"Cloud computing; Custodians; Computer science; Identifier; Container (type theory); Overhead (engineering); Linkage (software); Record linkage; Database; Computer security; Software; Data mining; Distributed computing; Computer network; Operating system; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008200004,0.0006048988,0.0008216712,0.0009843264,0.00104592,0.002518154,0.002509157,0.000978743,0.001787862],"category_scores_gemma":[0.01402411,0.0002763618,0.0007972908,0.001875805,0.0008761896,0.002849397,0.001960305,0.0007749149,0.0002683298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003700294,"about_ca_system_score_gemma":0.004111241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02782615,"about_ca_topic_score_gemma":0.01243025,"domain_scores_codex":[0.9960716,0.00190631,0.0002910146,0.0004991034,0.0008987678,0.0003332321],"domain_scores_gemma":[0.9868333,0.008260053,0.0007223334,0.001531018,0.002052343,0.0006009528],"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":[0.00348507,0.001014603,0.01385177,0.0003214364,0.0002557777,0.0004102849,0.00033853,0.889585,0.004059779,0.01192921,0.002335545,0.07241312],"study_design_scores_gemma":[0.00007995338,0.0002659238,0.0007725097,0.000009534127,0.00002392511,0.00004163149,0.00011372,0.9954803,0.001064434,0.001764935,0.0003738271,0.000009306665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.710193,0.0005792162,0.2789192,0.00175649,0.0001815595,0.001038069,0.0009530804,0.001523488,0.00485588],"genre_scores_gemma":[0.8642295,0.0002798976,0.1337741,0.0001201731,0.00002787159,0.0002321152,0.0004543741,0.00006377376,0.0008182105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02782615,"threshold_uncertainty_score":0.05532837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3796766782781779,"score_gpt":0.5127085377994934,"score_spread":0.1330318595213155,"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."}}