{"id":"W7125805820","doi":"10.1109/medai67139.2025.00014","title":"Fed-ensemble: Enhancing Federated Learning with Ensemble Models for an Explainable Thyroid Cancer Recurrence Prediction","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Generalizability theory; Ensemble learning; Federated learning; Ensemble forecasting; Transparency (behavior); Thyroid cancer; Robustness (evolution)","routes":{"ca_aff":true,"ca_fund":false,"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","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002126701,0.0008533068,0.0008746474,0.0005361123,0.003866217,0.001781841,0.001209573,0.0004836013,0.00008034325],"category_scores_gemma":[0.0004498625,0.0008173539,0.000141773,0.002389732,0.0001254257,0.003269419,0.0004568224,0.001771641,0.000009770163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008508459,"about_ca_system_score_gemma":0.003360699,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007822756,"about_ca_topic_score_gemma":0.008003868,"domain_scores_codex":[0.9925275,0.0009417532,0.001252299,0.002542797,0.0008449433,0.001890673],"domain_scores_gemma":[0.9950479,0.0007168102,0.000624173,0.001109077,0.002003892,0.0004981625],"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":[0.0008522138,0.0002528753,0.004301804,0.001666497,0.0001599376,0.00001460424,0.005950789,0.7313768,0.00319709,0.02298207,0.003116112,0.2261292],"study_design_scores_gemma":[0.001469191,0.0034401,0.0001958765,0.001979851,0.00008150411,0.00003059281,0.001255323,0.9783309,0.007612229,0.002655727,0.002170919,0.0007777697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0328242,0.002649529,0.9434241,0.002437835,0.002005933,0.00239412,0.00001773941,0.0009067347,0.0133398],"genre_scores_gemma":[0.9359915,0.0006033833,0.03912008,0.0008438246,0.0003165217,0.0009465941,0.00004967983,0.00008190172,0.02204653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.904304,"threshold_uncertainty_score":0.9994277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03027348860040412,"score_gpt":0.3141351028698686,"score_spread":0.2838616142694645,"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."}}