{"id":"W2302532339","doi":"10.1007/s12021-015-9292-3","title":"Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia","year":2016,"lang":"en","type":"article","venue":"Neuroinformatics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":88,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; CSC – IT Center for Science; National Institutes of Health; National Institute on Aging; Universidad Carlos III de Madrid; U.S. Department of Defense","keywords":"Feature selection; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Computer science; Feature (linguistics); Context (archaeology); Stability (learning theory); Resampling; Test set; Machine learning","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":[0.0002324683,0.00008484218,0.0001492437,0.0002417867,0.00004495253,0.00001697168,0.0001129099,0.00006939659,0.00001038523],"category_scores_gemma":[0.0007562384,0.00006741517,0.00003396432,0.0003654088,0.00003967453,0.0002370559,0.0000222364,0.0002058654,0.000004277188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004915752,"about_ca_system_score_gemma":0.00002051912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003457356,"about_ca_topic_score_gemma":0.00006129441,"domain_scores_codex":[0.9991072,0.00008316315,0.0003858251,0.0001237613,0.0001419649,0.0001580986],"domain_scores_gemma":[0.9993148,0.0003373967,0.0002036489,0.00009440916,0.00002310319,0.00002661448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001092043,0.0001358704,0.0530591,0.00009956556,0.000001768411,4.729216e-7,0.0006364962,0.0001749024,0.9091839,0.002148189,0.001561025,0.03288949],"study_design_scores_gemma":[0.0006525174,0.0002059899,0.01274049,0.00004538787,0.000003301495,0.000008909305,0.00006287312,0.2173509,0.7552593,0.0001882423,0.01337977,0.0001023557],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9475173,0.00001014019,0.04518693,0.004828865,0.0001482019,0.0008482765,0.00001094257,0.0002012565,0.001248047],"genre_scores_gemma":[0.9982545,0.00001646198,0.001320317,0.0002565285,0.00001025869,0.00002472865,0.000002186188,0.00000977333,0.000105293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.217176,"threshold_uncertainty_score":0.2749111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03200646911059092,"score_gpt":0.3149345874072208,"score_spread":0.2829281182966299,"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."}}