{"id":"W4411798232","doi":"10.2196/60204","title":"Proposal for Using AI to Assess Clinical Data Integrity and Generate Metadata: Algorithm Development and Validation","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Machine learning; Data quality; Naive Bayes classifier; Quality assurance; Data mining; Clinical decision support system; Decision tree; Metadata; Artificial intelligence; Data integrity; Decision support system; Support vector machine; Medicine; Database","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0783205,0.00174356,0.001844883,0.009984819,0.001743511,0.00787005,0.006940288,0.004197523,0.003842033],"category_scores_gemma":[0.1337586,0.001024917,0.002941629,0.00579926,0.004460905,0.007479919,0.004272786,0.004357733,0.002287394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003440766,"about_ca_system_score_gemma":0.01221257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006418179,"about_ca_topic_score_gemma":0.002413913,"domain_scores_codex":[0.9636223,0.01921698,0.004174544,0.004371858,0.007839776,0.0007745739],"domain_scores_gemma":[0.8762965,0.06459107,0.005367262,0.01238784,0.03903353,0.00232376],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007257195,0.001117713,0.03158348,0.001470825,0.0007878084,0.0004158464,0.001271744,0.05146462,0.006684204,0.1165656,0.01865322,0.7692592],"study_design_scores_gemma":[0.0004850801,0.001167833,0.006161288,0.00147616,0.0004547195,0.0008694085,0.0008995547,0.8046461,0.01312768,0.1315898,0.03886659,0.0002558062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002844361,0.0005256702,0.9889541,0.003154149,0.000169053,0.001093993,0.0001572181,0.001602407,0.001499],"genre_scores_gemma":[0.02566912,0.0002379114,0.9715466,0.0004022876,0.00008330859,0.001142316,0.0003554884,0.0000700236,0.0004931229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9958025,"threshold_uncertainty_score":0.4142033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4724608969169193,"score_gpt":0.5724694932640425,"score_spread":0.1000085963471232,"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."}}