{"id":"W4299960305","doi":"10.17615/e7yz-n749","title":"Multi-Task Linear Programming Discriminant Analysis for the Identification of Progressive MCI Individuals","year":2020,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Advanced Algorithms and Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; National Institutes of Health; Genentech; IXICO; National Institute of Biomedical Imaging and Bioengineering; University of California, Los Angeles; U.S. Food and Drug Administration; National Cancer Institute; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Alzheimer's Disease Neuroimaging Initiative; F. Hoffmann-La Roche; Medpace; Elan; Novartis; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Synarc; Foundation for the National Institutes of Health","keywords":"Linear discriminant analysis; Identification (biology); Task (project management); Artificial intelligence; Computer science; Discriminant; Pattern recognition (psychology); Statistics; Machine learning; Mathematics; Engineering; Biology","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":[0.00004915163,0.00009115189,0.0001470647,0.00003899621,0.0001128893,0.00006609537,0.0001806679,0.0000312016,0.000006037144],"category_scores_gemma":[0.00006517676,0.0000634407,0.00009388729,0.0005045901,0.00008194011,0.0002369413,0.00003424777,0.00005863048,0.00000245675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004385372,"about_ca_system_score_gemma":0.0000114944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000235425,"about_ca_topic_score_gemma":0.000001517124,"domain_scores_codex":[0.9993711,0.000005851123,0.0002744937,0.0001351647,0.00008952436,0.0001238474],"domain_scores_gemma":[0.9995491,0.00010454,0.00009701044,0.0001707866,0.00004042192,0.00003815676],"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":[0.00004241969,0.0003636669,0.01168512,0.001075683,0.004507109,0.000002592361,0.03612532,0.4545888,0.03597748,0.1659209,0.001405491,0.2883054],"study_design_scores_gemma":[0.0003376275,0.00004086464,0.008635005,0.0000156126,0.0007674384,3.274294e-7,0.002453843,0.8916836,0.06646971,0.002801283,0.02655072,0.0002440022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003718507,0.001180475,0.9932943,0.0008155127,0.000036647,0.0006161527,0.000165843,0.0001650832,0.000007467181],"genre_scores_gemma":[0.6930888,0.00001399573,0.306016,0.00003446227,0.0001181678,0.0005132907,0.0001494492,0.00002399693,0.00004184233],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6893703,"threshold_uncertainty_score":0.2587037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03383634787583265,"score_gpt":0.2686873847817621,"score_spread":0.2348510369059295,"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."}}