{"id":"W3165172487","doi":"10.3233/shti210147","title":"Federated Deep Learning Architecture for Personalized Healthcare","year":2021,"lang":"en","type":"book-chapter","venue":"Studies in health technology and informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Mitacs; F. Hoffmann-La Roche","keywords":"Computer science; Deep learning; Architecture; Face (sociological concept); Federated learning; Deep neural networks; Data science; Health care; Artificial intelligence; Artificial neural network; Big data; Information privacy; Machine learning; Computer security; Data mining; Political science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004674187,0.000414123,0.0003012742,0.0002975891,0.0002295931,0.0009293889,0.0007445716,0.0008423883,0.004424337],"category_scores_gemma":[0.0007604455,0.00022933,0.0003935236,0.0006264858,0.0004405065,0.001636695,0.0008946046,0.002043397,0.001527747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001065104,"about_ca_system_score_gemma":0.0007742053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002052871,"about_ca_topic_score_gemma":0.002828991,"domain_scores_codex":[0.9998145,0.00003924825,0.00001017955,0.00003983204,0.00007413695,0.00002225581],"domain_scores_gemma":[0.9998518,0.00004558851,0.000006889298,0.00004453662,0.00004230074,0.000008782368],"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":[0.000130923,0.00009151776,0.0004667167,0.0001575553,0.00007852595,0.000118515,0.0001144233,0.2276124,0.004790391,0.2041456,0.0393877,0.5229057],"study_design_scores_gemma":[0.00001076732,0.00004059537,0.0002737164,0.00006599152,0.00002483735,0.0001506375,0.00002501726,0.757919,0.004363273,0.1816979,0.05540973,0.00001857059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009652972,0.005511829,0.9575023,0.002524822,0.0003768974,0.00002776331,0.0002407296,0.00184149,0.02232121],"genre_scores_gemma":[0.4970323,0.0111603,0.382786,0.001763389,0.0003881227,0.0001435567,0.001242527,0.0002553346,0.1052286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004424337,"threshold_uncertainty_score":0.01480085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06651754710366126,"score_gpt":0.3443571886929163,"score_spread":0.2778396415892551,"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."}}