{"id":"W4404569722","doi":"10.48550/arxiv.2411.10342","title":"EHRs Data Harmonization Platform, an easy-to-use shiny app based on recodeflow for harmonizing and deriving clinical features","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministero dell'Università e della Ricerca; University of Toronto; Canadian Institutes of Health Research; European Commission; Dipartimenti di Eccellenza","keywords":"Harmonization; Computer science; Data science; Art","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001383279,0.0004282851,0.0004548975,0.0004785568,0.0003522422,0.0008420338,0.002800374,0.0004824866,0.000006546576],"category_scores_gemma":[0.000968996,0.0004802447,0.0001335784,0.0005814139,0.00006808955,0.0008194267,0.004585091,0.001602355,0.00002687824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000185394,"about_ca_system_score_gemma":0.0004132423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003173733,"about_ca_topic_score_gemma":0.0002791786,"domain_scores_codex":[0.9959551,0.0003362946,0.0004023002,0.002654739,0.0001717233,0.0004798121],"domain_scores_gemma":[0.9951808,0.001080401,0.0002723999,0.002811993,0.0001983712,0.0004560731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004403817,0.0002527419,0.06771985,0.00162354,0.0001829963,0.0004173674,0.0009046028,0.8097453,0.00002094413,0.05375748,0.003361309,0.06157354],"study_design_scores_gemma":[0.0003724637,0.0002197952,0.0117775,0.0004840216,0.00007010835,0.00000383841,0.00002497312,0.9790928,0.00001213778,0.006082119,0.001367576,0.00049261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1806994,0.00006313113,0.8149799,0.0009832387,0.001459231,0.0009424235,0.0001536887,0.0005994745,0.0001195898],"genre_scores_gemma":[0.9218233,0.00007027728,0.07606548,0.000987215,0.0002216597,0.000003931221,0.0002885281,0.00006401061,0.0004755451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.741124,"threshold_uncertainty_score":0.9997649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.305942905694652,"score_gpt":0.3054172830560536,"score_spread":0.0005256226385983997,"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."}}