{"id":"W4404887882","doi":"10.2196/54133","title":"Robust Automated Harmonization of Heterogeneous Data Through Ensemble Machine Learning: Algorithm Development and Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Neurological Disorders and Stroke","keywords":"Computer science; Preprint; Artificial intelligence; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01108472,0.0018141,0.001897079,0.001650007,0.0009372708,0.001225042,0.002394288,0.00169644,0.001567497],"category_scores_gemma":[0.01737846,0.0005188662,0.001659523,0.001675239,0.0007372037,0.001503574,0.002703262,0.002915279,0.0006333028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001151312,"about_ca_system_score_gemma":0.002530389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00997493,"about_ca_topic_score_gemma":0.007687062,"domain_scores_codex":[0.9961029,0.001754256,0.0002690606,0.001016318,0.0005605005,0.0002969517],"domain_scores_gemma":[0.9900563,0.005578309,0.000481988,0.001533209,0.002110383,0.0002398383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004309855,0.0005104154,0.01551232,0.0001693156,0.0006569691,0.0001483588,0.0002040393,0.5762042,0.002756072,0.002001115,0.006619217,0.3947869],"study_design_scores_gemma":[0.00002379681,0.00006262156,0.0008484126,0.00001171,0.00002419458,0.00002357302,0.00003339714,0.9966536,0.0007958804,0.001124472,0.0003903247,0.000008027861],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1536182,0.001786941,0.8372897,0.0005095942,0.0001621559,0.0004566816,0.0005949626,0.00426295,0.001318834],"genre_scores_gemma":[0.5183151,0.0003804406,0.476515,0.0003077593,0.0000858612,0.000526652,0.002490021,0.0002979197,0.001081256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01108472,"threshold_uncertainty_score":0.0586223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06440115396028467,"score_gpt":0.344435159548589,"score_spread":0.2800340055883043,"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."}}