{"id":"W2138998329","doi":"10.1186/1472-6947-12-79","title":"Effective diagnosis of Alzheimer’s disease by means of large margin-based methodology","year":2012,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Bayer HealthCare; Northern California Institute for Research and Education; Amorfix Life Sciences; Biogen; AstraZeneca; University of California, San Diego; BioClinica; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Artificial intelligence; Mahalanobis distance; Pattern recognition (psychology); Support vector machine; Feature extraction; Kernel principal component analysis; Mathematics; Principal component analysis; Dimensionality reduction; Computer science; k-nearest neighbors algorithm; Euclidean distance; Kernel method","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":[0.002978765,0.0001194603,0.0004195878,0.0001957599,0.00004604795,0.000007783901,0.00008729573,0.0001008866,0.0008042522],"category_scores_gemma":[0.002914927,0.00008428884,0.0001172266,0.0001832698,0.0001591172,0.0001068137,0.0001406806,0.0001583309,0.000008775852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001270593,"about_ca_system_score_gemma":0.0001521191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003380879,"about_ca_topic_score_gemma":0.000001782486,"domain_scores_codex":[0.9977348,0.0001745003,0.0006311627,0.00008401345,0.001053143,0.000322352],"domain_scores_gemma":[0.9942779,0.004686964,0.0002018105,0.0001779508,0.0001659511,0.0004894403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008204863,0.0006073053,0.6213413,0.0007435599,0.0001052898,0.000004852283,0.0003036372,0.000003272383,0.00002303639,0.0005077395,0.0021968,0.3733427],"study_design_scores_gemma":[0.01387346,0.001506518,0.7621331,0.004553453,0.001319508,0.00002901396,0.002327752,0.1986979,0.008399431,0.001554196,0.005160268,0.0004453422],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5372651,0.00147398,0.4601554,0.00002586732,0.00006252027,0.0003805324,0.00003012004,0.000007945737,0.0005985353],"genre_scores_gemma":[0.9239426,0.0001479117,0.07515711,0.0006297331,0.00003288968,0.00005658756,0.0000206798,0.00000828658,0.000004226519],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3866775,"threshold_uncertainty_score":0.8805997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06924174914802646,"score_gpt":0.4230580346726993,"score_spread":0.3538162855246729,"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."}}