{"id":"W2028633780","doi":"10.1016/j.neuroimage.2013.08.015","title":"Bi-level multi-source learning for heterogeneous block-wise missing data","year":2013,"lang":"en","type":"review","venue":"NeuroImage","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Servier; Takeda Pharmaceutical Company; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Drug Discovery Foundation; Merck; Amorfix Life Sciences; Eli Lilly and Company; National Institute on Aging; Alzheimer's Association; GE Healthcare; BioClinica; Abbott Laboratories; Dana Foundation; Roche; Foundation for the National Institutes of Health","keywords":"Missing data; Computer science; Pruning; Block (permutation group theory); Artificial intelligence; Data type; Feature (linguistics); Data mining; Machine learning; Feature selection; Neuroimaging; Data modeling; Alzheimer's Disease Neuroimaging Initiative; Pattern recognition (psychology); Alzheimer's disease; Disease","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":[0.005287871,0.001757343,0.002822009,0.002291992,0.0002721061,0.001498181,0.003319363,0.002380414,0.003183503],"category_scores_gemma":[0.01256758,0.0008086005,0.001880731,0.003689658,0.001350361,0.002484167,0.001771841,0.002957163,0.002507085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006059172,"about_ca_system_score_gemma":0.001716066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002115782,"about_ca_topic_score_gemma":0.002454034,"domain_scores_codex":[0.9988462,0.000378117,0.000112075,0.0002560489,0.0003677574,0.0000397883],"domain_scores_gemma":[0.9924142,0.005763982,0.0003132865,0.0004470169,0.0009924627,0.00006904703],"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":[0.00007055738,0.00005473477,0.0003234158,0.002907844,0.0003357034,0.00005886673,0.00004007702,0.01161516,0.001036635,0.01123958,0.007855969,0.9644614],"study_design_scores_gemma":[0.0001954054,0.0003354079,0.004323708,0.004273362,0.001393125,0.002333802,0.0001866582,0.4039567,0.0114037,0.340085,0.2311728,0.0003402436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007953001,0.2232003,0.7726814,0.001151053,0.0003472878,0.00003152142,0.0002082127,0.0005772444,0.00100778],"genre_scores_gemma":[0.02756375,0.4272823,0.5372698,0.00105246,0.001736431,0.0002348198,0.001301332,0.0003939923,0.003165069],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005287871,"threshold_uncertainty_score":0.02796525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5934927943294889,"score_gpt":0.4905679225777599,"score_spread":0.102924871751729,"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."}}