{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005145385,0.001565418,0.001927875,0.001283625,0.0006913448,0.001955657,0.002086604,0.001706882,0.001550071],"category_scores_gemma":[0.01306689,0.0004757555,0.001231897,0.001751912,0.0003996194,0.00212019,0.002203356,0.002725614,0.001578001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006372672,"about_ca_system_score_gemma":0.0009132579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002847754,"about_ca_topic_score_gemma":0.004225079,"domain_scores_codex":[0.9983039,0.0004980568,0.0001290037,0.0004968432,0.0004172915,0.0001549873],"domain_scores_gemma":[0.9941344,0.003488278,0.0004053374,0.0008505016,0.0009382716,0.0001833492],"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":[0.000453948,0.0004799956,0.02354354,0.0003636946,0.0003123132,0.0002733842,0.0002682008,0.1168087,0.007198915,0.003399648,0.04537918,0.8015186],"study_design_scores_gemma":[0.00002534846,0.000128983,0.004662906,0.00006217724,0.00006480237,0.0001537552,0.0001150597,0.974726,0.003421223,0.01142391,0.005193816,0.00002195729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1310413,0.004860961,0.8484235,0.002432891,0.001241235,0.0002273541,0.003795828,0.004323904,0.003653135],"genre_scores_gemma":[0.6625664,0.002233501,0.3069055,0.001206842,0.001910543,0.0003629021,0.01438625,0.0006228352,0.009805257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005145385,"threshold_uncertainty_score":0.02721173,"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."}}