{"id":"W3095441110","doi":"10.3389/fneur.2020.576194","title":"Comparison of Transfer Learning and Conventional Machine Learning Applied to Structural Brain MRI for the Early Diagnosis and Prognosis of Alzheimer's Disease","year":2020,"lang":"en","type":"article","venue":"Frontiers in Neurology","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Janssen Alzheimer Immunotherapy Research And Development; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; F. Hoffmann-La Roche; Biogen; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Disease; Neuroscience; Transfer of learning; Medicine; Artificial intelligence; Psychology; Machine learning; Computer science; Pathology","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":[0.0001076425,0.00008679736,0.000206278,0.00007051176,0.0001022385,0.00001159931,0.00008759554,0.00003852313,0.00001124551],"category_scores_gemma":[0.0003495,0.00007501392,0.00003533759,0.0001662719,0.0002090225,0.00003545439,0.00003026894,0.0002241352,1.787838e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002415242,"about_ca_system_score_gemma":0.000009638854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000537399,"about_ca_topic_score_gemma":0.000003541751,"domain_scores_codex":[0.9990714,0.0001779753,0.0002340639,0.0002914279,0.0001008421,0.0001243516],"domain_scores_gemma":[0.9993814,0.0004005648,0.00007563724,0.00004822006,0.00001494625,0.00007922105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001328558,0.00003187463,0.9593478,0.00005621765,0.0000185684,0.000001157297,0.001615952,0.002627657,0.01914907,0.001012047,0.0003342307,0.01447685],"study_design_scores_gemma":[0.001800209,0.001328571,0.7043763,0.000008309777,0.00009623057,0.00000299206,0.0002724874,0.2450052,0.03873537,0.0003183949,0.007871731,0.0001842551],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777249,0.0003393447,0.009949802,0.01109764,0.0001425394,0.0006891389,0.00002208739,0.00002137501,0.00001319],"genre_scores_gemma":[0.9987015,0.00003347063,0.0002152642,0.0008765442,0.00001748726,0.0001372934,0.000003430848,0.00001130627,0.000003734018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2549716,"threshold_uncertainty_score":0.3058979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03842687255133427,"score_gpt":0.2874083135200718,"score_spread":0.2489814409687375,"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."}}