{"id":"W2884594816","doi":"10.1016/j.neuroimage.2018.07.032","title":"Reconstructing subject-specific effect maps","year":2018,"lang":"en","type":"article","venue":"NeuroImage","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute on Aging; Genentech; National Institutes of Health; Eisai; Servier; U.S. Department of Defense; Eli Lilly and Company; Lundbeckfonden; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Alzheimer's Association; Fujirebio US; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; BioClinica; Biogen; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Takeda Pharmaceuticals North America; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Merck; Alzheimer's Drug Discovery Foundation; Meso Scale Diagnostics; Johnson and Johnson; AbbVie","keywords":"Inference; Computer science; Neuroimaging; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Machine learning; A priori and a posteriori; Data mining","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":[0.001002128,0.0008431765,0.0004726568,0.001511072,0.0002300301,0.001248808,0.0005467159,0.001062592,0.003433449],"category_scores_gemma":[0.003823506,0.0006950658,0.001028234,0.00116106,0.0003734661,0.000817484,0.0007062417,0.0009983624,0.001048246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002825847,"about_ca_system_score_gemma":0.001158674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004137145,"about_ca_topic_score_gemma":0.006030417,"domain_scores_codex":[0.999846,0.00004101978,0.000009746034,0.00004260467,0.00003480911,0.00002574034],"domain_scores_gemma":[0.9993754,0.0003225053,0.00004886626,0.0001392597,0.00008092238,0.00003311891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001174746,0.0002050448,0.01031901,0.001134956,0.001142106,0.001684514,0.0008944978,0.1775946,0.1906932,0.01967165,0.01688617,0.5785995],"study_design_scores_gemma":[0.0001533688,0.0003068622,0.02345098,0.0001612103,0.001284588,0.004926006,0.0005067415,0.6935415,0.1562632,0.08494935,0.03430336,0.0001529327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07248142,0.001263235,0.9185131,0.0005357056,0.0001355593,0.00008082096,0.001003396,0.002569578,0.003417189],"genre_scores_gemma":[0.6559398,0.002995762,0.3275535,0.0004406726,0.0001982095,0.0001739396,0.002161637,0.001648673,0.008887953],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004137145,"threshold_uncertainty_score":0.01148599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02241434208180524,"score_gpt":0.3111107581762981,"score_spread":0.2886964160944928,"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."}}