{"id":"W4409435779","doi":"10.21203/rs.3.rs-6099872/v1","title":"FedWeight: Mitigating Covariate Shift of Federated Learning on Electronic Health Records Data through Patients Re-weighting","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of British Columbia; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; National University Health System","keywords":"Covariate; Health records; Weighting; Electronic health record; Computer science; Meaningful use; Statistics; Data science; Econometrics; Data mining; Medicine; Machine learning; Mathematics; Economics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01286046,0.001090069,0.001966591,0.001210173,0.0007933619,0.001639095,0.002601846,0.001592527,0.002316675],"category_scores_gemma":[0.03489606,0.0005592182,0.001220464,0.002079442,0.001136687,0.003679035,0.005015742,0.002450889,0.0008844344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007154036,"about_ca_system_score_gemma":0.002257961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002427497,"about_ca_topic_score_gemma":0.002829847,"domain_scores_codex":[0.9934861,0.003089617,0.0004025151,0.001404264,0.001203631,0.0004138238],"domain_scores_gemma":[0.9837182,0.006707021,0.0009501713,0.007065833,0.001166354,0.0003923249],"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":[0.003042776,0.0009243146,0.02702096,0.0002475806,0.0005950663,0.0002802045,0.0006759651,0.1273842,0.007455253,0.01950771,0.01448732,0.7983787],"study_design_scores_gemma":[0.0001472032,0.0003804707,0.00339611,0.00004729131,0.0001269478,0.0002047952,0.0001360339,0.9189571,0.007594645,0.06475665,0.004210904,0.0000418836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07636139,0.0007971264,0.9171778,0.00107584,0.0002598839,0.0001409202,0.0008659139,0.002601113,0.0007200057],"genre_scores_gemma":[0.7415791,0.000417616,0.2506289,0.0006631957,0.0003938256,0.0001534465,0.00214328,0.0002699486,0.003750802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01286046,"threshold_uncertainty_score":0.06801343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1348270868542429,"score_gpt":0.419843559732994,"score_spread":0.2850164728787511,"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."}}