{"id":"W1548832181","doi":"10.1109/jbhi.2015.2432832","title":"Feature Selection Based on the SVM Weight Vector for Classification of Dementia","year":2015,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Support vector machine; Feature selection; Artificial intelligence; Pattern recognition (psychology); Voxel; Computer science; Dementia; Feature (linguistics); Selection (genetic algorithm); Kernel (algebra); Feature vector; Feature extraction; Neuroimaging; Mathematics; Medicine; Disease; Pathology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002037802,0.00006398837,0.0001968877,0.0001693904,0.00007265686,0.00001316673,0.00005696407,0.00006187159,0.00001851956],"category_scores_gemma":[0.0001908985,0.0000337933,0.00005577925,0.0001764204,0.00008895215,0.00007233074,0.000005624971,0.0002252411,0.00000184604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006501134,"about_ca_system_score_gemma":0.0007207113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001932082,"about_ca_topic_score_gemma":9.434766e-7,"domain_scores_codex":[0.9986176,0.00004062211,0.0005216488,0.00003254728,0.0006273572,0.0001602608],"domain_scores_gemma":[0.9985442,0.0001198371,0.0004650102,0.00005478472,0.0005018917,0.0003143194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003543905,0.001733589,0.04573196,0.003996481,0.0005177102,0.000004739175,0.00289552,0.000007104025,0.002072304,0.001350321,0.7464619,0.1916845],"study_design_scores_gemma":[0.01889696,0.03825839,0.2955114,0.001968554,0.0004811533,0.0002697778,0.004070914,0.1661852,0.005632402,0.0008043515,0.4676757,0.0002452012],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5048011,0.0006325114,0.1864042,0.3038967,0.00108051,0.001889079,0.00004485428,0.0000195317,0.001231484],"genre_scores_gemma":[0.9918029,0.0001479414,0.004426223,0.003201014,0.0003188758,0.000008850333,0.00001367434,0.000005187297,0.0000753168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4870018,"threshold_uncertainty_score":0.1378051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07899907698726526,"score_gpt":0.3756823318387058,"score_spread":0.2966832548514405,"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."}}