{"id":"W3022268149","doi":"10.2196/14064","title":"Privacy-Preserving Deep Learning for the Detection of Protected Health Information in Real-World Data: Comparative Evaluation","year":2020,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universitätsklinikum Jena; RWTH Aachen University","keywords":"Confidentiality; Computer science; Private information retrieval; Protocol (science); Information privacy; Artificial neural network; Machine learning; Computer security; Artificial intelligence; Data mining; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007940431,0.0001570457,0.000313199,0.0006321428,0.0005233682,0.0002483159,0.01826376,0.00006808609,0.000003447175],"category_scores_gemma":[0.0258381,0.0001238338,0.0000374895,0.003791598,0.0002220949,0.0056148,0.04395078,0.0011128,0.00001800828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004586136,"about_ca_system_score_gemma":0.0003234361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000722566,"about_ca_topic_score_gemma":0.0009407621,"domain_scores_codex":[0.9957837,0.00111221,0.0007362088,0.0004004485,0.001392808,0.0005745918],"domain_scores_gemma":[0.9929467,0.001448756,0.0005730476,0.003981989,0.0009668284,0.00008263403],"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":[0.0005477832,0.0002157009,0.000697594,0.001112767,0.0001352716,7.997592e-7,0.08505822,0.0083978,0.001848585,0.003121645,0.02092717,0.8779367],"study_design_scores_gemma":[0.0008060841,0.0005571223,0.01079621,0.00008271269,0.000002160137,7.016832e-7,0.002872546,0.9693278,0.003169736,0.009715284,0.002556628,0.000112999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03077244,0.0001559666,0.9216245,0.04064485,0.00008402549,0.006078252,0.00003807887,0.0003111825,0.0002907305],"genre_scores_gemma":[0.9710175,0.0001072575,0.02759542,0.00005899982,0.00002966014,0.001047187,0.0001342358,0.000008184656,0.000001487356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.96093,"threshold_uncertainty_score":0.9870479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2760449451955062,"score_gpt":0.4681315358562635,"score_spread":0.1920865906607573,"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."}}