{"id":"W4414890836","doi":"10.1007/978-981-96-6938-7_39","title":"Addressing Overfitting in an Imbalanced Dataset for MS Progression Prediction","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Overfitting; Oversampling; Bootstrap aggregating; Generalization; Resampling; Stability (learning theory); Principal component analysis; Perceptron; Ensemble learning; Interpretability","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"],"consensus_categories":[],"category_scores_codex":[0.0007269683,0.0003271041,0.0005004014,0.0002887021,0.0001196595,0.0003946339,0.000573702,0.0006493171,0.000001136455],"category_scores_gemma":[0.00008722841,0.0002946058,0.00003707169,0.0001416871,0.00004714871,0.0004138494,0.0002038294,0.0005542,2.498001e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371585,"about_ca_system_score_gemma":0.00006547706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002428619,"about_ca_topic_score_gemma":0.0001265078,"domain_scores_codex":[0.9978718,0.00008318137,0.0006488475,0.000848097,0.0002193963,0.0003286571],"domain_scores_gemma":[0.9982297,0.0003806442,0.000406618,0.0008494042,0.00007667598,0.00005695502],"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":[0.000191622,0.0001212001,0.005396558,0.002207472,0.00007131435,0.00005313961,0.0005157411,0.03867437,0.0003657735,0.1051408,0.0175123,0.8297497],"study_design_scores_gemma":[0.0004154239,0.0001089869,0.0002435744,0.004765266,0.00001044372,0.00001014575,0.000002028947,0.9687871,0.00004279598,0.004291196,0.02098269,0.0003402926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00001092377,0.003373452,0.9921672,0.0000878697,0.0008623995,0.001389712,0.0008044938,0.0001721729,0.001131829],"genre_scores_gemma":[0.8005345,0.002791163,0.1340949,0.001354786,0.004817073,0.002379974,0.05085862,0.0002998162,0.002869167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9301128,"threshold_uncertainty_score":0.9999506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04537730595900261,"score_gpt":0.3195773059497233,"score_spread":0.2741999999907206,"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."}}