{"id":"W4400486781","doi":"10.2196/58978","title":"Evaluating the Bias in Hospital Data: Automatic Preprocessing of Patient Pathways Algorithm Development and Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Preprocessor; Data mining; Data science; Artificial intelligence; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.002073963,0.0001446199,0.0002246917,0.0002438907,0.0001302167,0.0004163187,0.0003388625,0.00006179578,0.00002476411],"category_scores_gemma":[0.0004592629,0.00009170177,0.00002212479,0.0007902182,0.00005798031,0.001599051,0.0005095851,0.0002077117,0.0000150217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002182369,"about_ca_system_score_gemma":0.0001950289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005926755,"about_ca_topic_score_gemma":0.00001045941,"domain_scores_codex":[0.9976813,0.00001656249,0.000950731,0.00017152,0.001007234,0.0001727017],"domain_scores_gemma":[0.9991671,0.0001086837,0.0002919544,0.0002776686,0.0001379018,0.0000167243],"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":[0.000001990337,0.0002333095,0.001463198,0.001620861,0.00004444167,0.000006356601,0.01429256,0.0003087547,9.469979e-7,0.00006109597,0.00006630165,0.9819002],"study_design_scores_gemma":[0.0002336926,0.0000252902,0.0006739367,0.0007876579,0.00006242353,0.000001841053,0.01230336,0.9852439,0.000009859373,0.0002516819,0.0002814413,0.00012496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993365,0.0001780836,0.005498124,0.0002294346,0.0001357867,0.0003675404,0.000001561194,0.00009396095,0.0001304774],"genre_scores_gemma":[0.9958062,0.000006633564,0.003782569,0.0001379933,0.0001189795,0.0000658744,0.00006572514,0.00001192295,0.00000416048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9849351,"threshold_uncertainty_score":0.4014571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08648612643729957,"score_gpt":0.3430461926667043,"score_spread":0.2565600662294047,"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."}}