{"id":"W2621247707","doi":"10.5540/tema.2017.018.01.0015","title":"Wrappers Feature Selection in Alzheimer's Biomarkers Using kNN and SMOTE Oversampling","year":2017,"lang":"en","type":"article","venue":"TEMA (São Carlos)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institutes of Health; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; U.S. Department of Defense","keywords":"Oversampling; Feature selection; Undersampling; Artificial intelligence; Feature (linguistics); Computer science; Support vector machine; Selection (genetic algorithm); Dementia; Pattern recognition (psychology); Biomarker; Random forest; Bootstrapping (finance); Machine learning; Mathematics; Medicine; Biology; Pathology; Disease","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":[],"consensus_categories":[],"category_scores_codex":[0.0006361139,0.0001755604,0.0002014257,0.0002113554,0.0003970838,0.0004953389,0.0005280424,0.000101936,0.00000396163],"category_scores_gemma":[0.0001736707,0.0001809298,0.00006504358,0.0002376803,0.00008121615,0.001040096,0.0003567904,0.0001941498,0.000003180894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001015829,"about_ca_system_score_gemma":0.0001354071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005031329,"about_ca_topic_score_gemma":0.0001015312,"domain_scores_codex":[0.9986255,0.0001338493,0.0001748066,0.000497725,0.0002760915,0.0002920388],"domain_scores_gemma":[0.9991037,0.0001651189,0.0001640586,0.0004001979,0.00006082347,0.0001060961],"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":[0.0004459922,0.0004135446,0.2152866,0.0004112163,0.002198508,0.000439372,0.01466739,0.1892214,0.05963014,0.06339121,0.003861055,0.4500336],"study_design_scores_gemma":[0.0005844735,0.0000346298,0.09375277,0.0001097443,0.00003701671,0.00007052609,0.0001017445,0.8997585,0.001754567,0.003124105,0.0003268858,0.0003450092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8071106,0.0006404465,0.1889298,0.001352629,0.0005699441,0.0003051369,0.000004811845,0.0001099228,0.0009766717],"genre_scores_gemma":[0.8855223,0.000009883672,0.1141963,0.0001452964,0.00008894932,0.000004031661,0.000001383571,0.00001388447,0.00001797335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7105371,"threshold_uncertainty_score":0.7378101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06376494522503356,"score_gpt":0.3523466314046253,"score_spread":0.2885816861795917,"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."}}