{"id":"W2996889063","doi":"10.2196/16492","title":"Analyzing Medical Research Results Based on Synthetic Data and Their Relation to Real Data Results: Systematic Comparison From Five Observational Studies","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Synthetic data; Computer science; Data mining; Observational study; Process (computing); Relation (database); Statistics; Artificial intelligence; Mathematics","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1946042,0.00120945,0.002498468,0.01491953,0.0009378605,0.00258898,0.001985704,0.001377694,0.001169016],"category_scores_gemma":[0.4085211,0.0008841678,0.008847702,0.009075899,0.003161896,0.002085742,0.003351092,0.001025491,0.0001385527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002146677,"about_ca_system_score_gemma":0.003607531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001165646,"about_ca_topic_score_gemma":0.001680866,"domain_scores_codex":[0.730803,0.1644115,0.06753977,0.01581201,0.02039211,0.00104167],"domain_scores_gemma":[0.263764,0.609698,0.07088684,0.03441085,0.02048339,0.0007569729],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003371543,0.0003902441,0.8365974,0.03173845,0.06125751,0.0009306737,0.008782197,0.004777679,0.001403637,0.001751325,0.0007556195,0.04824371],"study_design_scores_gemma":[0.001828363,0.0105637,0.7241592,0.03887127,0.1350406,0.003908102,0.0222334,0.02806573,0.01043928,0.006680596,0.01766874,0.0005410205],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8725626,0.0474973,0.06877968,0.0003263021,0.0002385577,0.005722303,0.00378635,0.0001277251,0.0009592035],"genre_scores_gemma":[0.971609,0.002838451,0.02034033,0.0001521134,0.00004247771,0.003273816,0.001660528,0.00003874728,0.00004457781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8053958,"threshold_uncertainty_score":0.9931964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2485650051275908,"score_gpt":0.4320103665125674,"score_spread":0.1834453613849766,"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."}}