{"id":"W4411373652","doi":"10.2196/72938","title":"Label Accuracy in Electronic Health Records and Its Impact on Machine Learning Models for Early Prediction of Gestational Diabetes: 3-Step Retrospective Validation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Gestational Diabetes Research and Management","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Medical diagnosis; Health records; Gestational diabetes; Electronic health record; Random forest; Computer science; Medicine; Machine learning; Diabetes mellitus; Medical record; Artificial intelligence; Health care; Pregnancy; World Wide Web; Internal medicine; Radiology","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":[],"category_scores_codex":[0.05549866,0.0006762159,0.0005891426,0.001366521,0.0006395967,0.001505069,0.001213965,0.001236707,0.0006214565],"category_scores_gemma":[0.1164358,0.0004514875,0.001981091,0.001018447,0.001013299,0.001328003,0.001305287,0.001361646,0.000396407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009332786,"about_ca_system_score_gemma":0.001119901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004826138,"about_ca_topic_score_gemma":0.003203241,"domain_scores_codex":[0.9802817,0.01133573,0.002206184,0.001936349,0.003627168,0.0006128496],"domain_scores_gemma":[0.802192,0.1245122,0.02349064,0.02394507,0.02479805,0.001062022],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001170246,0.000267773,0.9871997,0.00004649355,0.0004643893,0.0001102353,0.0004286966,0.002602198,0.0004315584,0.00009912447,0.000294634,0.006884951],"study_design_scores_gemma":[0.0001555002,0.002586528,0.9049046,0.0002377872,0.001174283,0.001324052,0.0007867732,0.07761903,0.008093302,0.0005415319,0.002484916,0.00009161651],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931844,0.0003545577,0.005286773,0.00006358585,0.00001931695,0.00008710938,0.0006357983,0.00003911609,0.0003293524],"genre_scores_gemma":[0.9955315,0.00009728038,0.002475759,0.00005686492,0.00001324818,0.00007845563,0.001593922,0.00002302148,0.0001299602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9445013,"threshold_uncertainty_score":0.2935085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02753524143603414,"score_gpt":0.3738763370355161,"score_spread":0.346341095599482,"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."}}