{"id":"W3135275361","doi":"10.1093/jamiaopen/ooab012","title":"Evaluating the utility of synthetic COVID-19 case data","year":2021,"lang":"en","type":"article","venue":"JAMIA Open","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Proxy (statistics); Confidence interval; Synthetic data; Computer science; Missing data; Data mining; Coronavirus disease 2019 (COVID-19); Data set; Comorbidity; Statistics; Medicine; Artificial intelligence; Machine learning; Mathematics; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003937441,0.0001050678,0.0001923436,0.00002958053,0.0002601166,0.0003641959,0.08155264,0.00006805151,0.0002127805],"category_scores_gemma":[0.1170236,0.00007782849,0.00002660266,0.0005894634,0.000179504,0.0008587523,0.4411306,0.0002353433,0.00002511938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004790903,"about_ca_system_score_gemma":0.0007810959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00123007,"about_ca_topic_score_gemma":0.0003171097,"domain_scores_codex":[0.9978786,0.0004896887,0.0003025774,0.0007542483,0.0003456791,0.0002292721],"domain_scores_gemma":[0.9633772,0.001313747,0.0001783753,0.03494953,0.0001082247,0.00007291208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002354803,0.0002083047,0.001287728,0.0001584788,0.00009471399,0.002728,0.0006346296,0.00003389914,0.0009702624,0.008392139,0.668884,0.3165842],"study_design_scores_gemma":[0.0002983556,0.0000355562,0.0003126598,0.00003209947,0.00001791006,0.001233092,0.0003037223,0.8351809,0.002386614,0.1502952,0.009764041,0.0001398433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09497579,0.001086229,0.5273471,0.3557922,0.00102836,0.001965137,0.0008196824,0.0008119977,0.01617351],"genre_scores_gemma":[0.636202,0.00001827049,0.3626612,0.0009624713,0.00001466895,0.00002291174,0.00003435345,0.000007332356,0.0000768184],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.835147,"threshold_uncertainty_score":0.9234166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3792201548995654,"score_gpt":0.4740288269975024,"score_spread":0.09480867209793703,"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."}}