{"id":"W4410420109","doi":"10.1038/s41746-025-01661-8","title":"FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; McGill University; University of Calgary; University of British Columbia; Vector Institute; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Health records; Covariate; Electronic health record; Weighting; Computer science; Data science; Medicine; Machine learning; Political science; Health care","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001085587,0.0002953521,0.0005987739,0.0001956425,0.0005087748,0.0001537834,0.001364815,0.0001008579,0.00002566683],"category_scores_gemma":[0.00324454,0.0002487788,0.00004257067,0.001058155,0.0001042792,0.0008752698,0.0007081146,0.001035907,0.00001746549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002685932,"about_ca_system_score_gemma":0.000616217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009476264,"about_ca_topic_score_gemma":0.00007727002,"domain_scores_codex":[0.9963388,0.0003276261,0.0009845905,0.0009039532,0.0006878458,0.0007571107],"domain_scores_gemma":[0.997103,0.0008523784,0.0006610748,0.001040425,0.0002034032,0.000139696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001455568,0.0004042584,0.1708948,0.001219774,0.0001879853,0.00002136032,0.007520995,0.0005344073,0.00002724575,0.1347911,0.006557294,0.6776952],"study_design_scores_gemma":[0.01482753,0.02263304,0.1796836,0.02389937,0.0001003877,0.00002719872,0.001982142,0.5129241,0.0005660001,0.07371058,0.1669743,0.002671731],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.453294,0.002079513,0.3067136,0.08356854,0.003779878,0.002145362,0.00007943949,0.001643811,0.1466958],"genre_scores_gemma":[0.9944121,0.00004240114,0.002490681,0.002201036,0.0001399688,0.00000819336,0.0003505746,0.00002523803,0.0003298627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6750235,"threshold_uncertainty_score":0.9999964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03778939891977748,"score_gpt":0.3398083588284275,"score_spread":0.30201895990865,"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."}}