{"id":"W2803144007","doi":"10.1016/j.neuroimage.2018.05.051","title":"Integrating spatial-anatomical regularization and structure sparsity into SVM: Improving interpretation of Alzheimer's disease classification","year":2018,"lang":"en","type":"article","venue":"NeuroImage","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Northern California Institute for Research and Education; Seventh Framework Programme; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; University of California, San Diego; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; European Commission; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Support vector machine; Artificial intelligence; Generalizability theory; Pattern recognition (psychology); Computer science; Neuroimaging; Machine learning; Regularization (linguistics); Regression; Lasso (programming language); Alzheimer's Disease Neuroimaging Initiative; Cognition; Cognitive impairment; Psychology; Mathematics; Neuroscience; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004659199,0.0009233772,0.00129696,0.001073992,0.0003765454,0.000892457,0.001045542,0.001204148,0.0006610574],"category_scores_gemma":[0.009468175,0.0003341339,0.0007692284,0.000851042,0.0007240943,0.001119851,0.001189388,0.001528292,0.0004223506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004105171,"about_ca_system_score_gemma":0.0007553048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002166054,"about_ca_topic_score_gemma":0.002104948,"domain_scores_codex":[0.998774,0.0005819197,0.00008889286,0.0002267293,0.0002326131,0.00009577955],"domain_scores_gemma":[0.9965432,0.001624889,0.0003026427,0.0004946882,0.0008858481,0.000148564],"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":[0.0009708895,0.0003050069,0.01933077,0.000237678,0.0002332786,0.0002814728,0.0004145744,0.2596493,0.02115288,0.009798046,0.009649602,0.6779764],"study_design_scores_gemma":[0.00001306521,0.00003364514,0.000909655,0.00001045231,0.000009618548,0.00002865869,0.00001839434,0.9923918,0.0009268787,0.005226268,0.0004243835,0.000007171988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06840502,0.0008053124,0.9282869,0.0006100136,0.00008886067,0.00003863107,0.0001264915,0.001040885,0.0005979029],"genre_scores_gemma":[0.7248265,0.0004297361,0.2721887,0.0003313761,0.0002029453,0.0000694659,0.0006002924,0.000204153,0.001146778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004659199,"threshold_uncertainty_score":0.0246405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01717239521944189,"score_gpt":0.3034584685260303,"score_spread":0.2862860733065883,"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."}}