{"id":"W4411300793","doi":"10.2196/75608","title":"Automated Data Harmonization in Clinical Research: Natural Language Processing Approach","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Research Resources; National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute","keywords":"Preprint; Harmonization; Computer science; Natural (archaeology); Natural language processing; Artificial intelligence; World Wide Web; History; Art; Archaeology","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":[0.02691707,0.001700584,0.001441192,0.007376404,0.001337709,0.004477247,0.004043578,0.002029644,0.002684979],"category_scores_gemma":[0.06375527,0.0008769476,0.002442299,0.005072718,0.002253042,0.004962228,0.004679168,0.00362088,0.001889707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00267472,"about_ca_system_score_gemma":0.007347468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00326941,"about_ca_topic_score_gemma":0.005339534,"domain_scores_codex":[0.9762927,0.01403316,0.002651467,0.003783207,0.002919048,0.0003204732],"domain_scores_gemma":[0.9340438,0.04759012,0.00584359,0.005493285,0.006483297,0.0005459351],"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":[0.0004254156,0.0006071765,0.007413085,0.0040387,0.0004397787,0.00104628,0.003056277,0.03197205,0.02033405,0.03183385,0.03168486,0.8671484],"study_design_scores_gemma":[0.0002486922,0.0004102134,0.006498853,0.001365852,0.0004328816,0.001263835,0.002751558,0.559001,0.02992815,0.3105833,0.08721671,0.0002991005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006109038,0.001157108,0.9817535,0.003355739,0.0001872188,0.001184821,0.002260778,0.002700892,0.001290796],"genre_scores_gemma":[0.04266548,0.0005499803,0.9502578,0.0009274888,0.000210224,0.001196344,0.003572918,0.0001502008,0.0004694631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9730829,"threshold_uncertainty_score":0.1423528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2684285756844088,"score_gpt":0.5829767339268984,"score_spread":0.3145481582424896,"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."}}