{"id":"W2580744997","doi":"10.1016/j.neuroimage.2017.01.066","title":"Predictive modelling using neuroimaging data in the presence of confounds","year":2017,"lang":"en","type":"article","venue":"NeuroImage","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":128,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Janssen Research and Development; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Eisai; Servier; U.S. Department of Defense; Eli Lilly and Company; Lundbeckfonden; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; IXICO; Takeda Pharmaceutical Company; AbbVie; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb Foundation; Wellcome Trust; Roche; Merck; Alzheimer's Drug Discovery Foundation; Wellcome; Fujirebio Europe; Alzheimer's Association; Foundation for the National Institutes of Health; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Neuroimaging; Weighting; Population; Confounding; Context (archaeology); Sample (material); Computer science; Artificial intelligence; Machine learning; Psychology; Statistics; Mathematics; Geography; Medicine","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":[0.0008130833,0.0001042893,0.0001304906,0.00007730658,0.0003372651,0.0005450566,0.00414632,0.00002149716,0.000003030522],"category_scores_gemma":[0.0004344528,0.00008717546,0.00002719337,0.0001388457,0.0001687983,0.001906347,0.0009782482,0.0002880779,0.000004091939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008037003,"about_ca_system_score_gemma":0.00006260077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001765511,"about_ca_topic_score_gemma":0.000005972555,"domain_scores_codex":[0.9985319,0.0001962175,0.0002321159,0.000441836,0.0003749878,0.0002229219],"domain_scores_gemma":[0.9968908,0.0002721997,0.0002553141,0.002489369,0.00005724673,0.00003506746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001379408,0.0005584832,0.05407744,0.0002071507,0.0000500713,0.001219119,0.03224415,0.7247383,0.0422037,0.08273421,0.0008380185,0.06099142],"study_design_scores_gemma":[0.0002144482,0.0000205594,0.01511497,0.0000252442,0.00000403248,0.00002033484,0.00009302337,0.9829441,0.00007705182,0.0005764213,0.0008349694,0.00007488471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06936673,0.0000387092,0.9213831,0.0006980893,0.0002713051,0.0001679659,0.000006305268,0.0000394704,0.008028339],"genre_scores_gemma":[0.9808769,0.00001363256,0.01875142,0.0002694841,0.00003826543,0.000001808304,0.000001949614,0.000008628404,0.00003791661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9115102,"threshold_uncertainty_score":0.7704962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1630712135925384,"score_gpt":0.3450921845634498,"score_spread":0.1820209709709114,"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."}}