{"id":"W6981483573","doi":"","title":"Enhancing Alzheimer's prognostic models with cross-domain self-supervised learning and MRI data harmonization","year":2024,"lang":"en","type":"article","venue":"D-Scholarship@Pitt (University of Pittsburgh)","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Medical Research Council; Canadian Institutes of Health Research; State Government of Victoria; Eli Lilly and Company; Edith Cowan University; Dementia Collaborative Research Centres, Australia; National Institutes of Health; Avid Radiopharmaceuticals; University of Melbourne; National Health and Medical Research Council; Commonwealth Scientific and Industrial Research Organisation; Northern California Institute for Research and Education; University of Southern California; Science and Industry Endowment Fund; Alzheimer's Association","keywords":"Comparability; Consistency (knowledge bases); Deep learning; Harmonization; Context (archaeology); Medical imaging; Magnetic resonance imaging; Field (mathematics); Supervised learning","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001161111,0.0002023276,0.000397171,0.0003265166,0.000478912,0.0003145169,0.0004988932,0.0001114812,0.0008054737],"category_scores_gemma":[0.00004778003,0.0002537983,0.00006737695,0.0004067741,0.000215339,0.002574226,0.0005134743,0.0002891077,0.0004544081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007313098,"about_ca_system_score_gemma":0.00005424566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001050003,"about_ca_topic_score_gemma":0.00003106134,"domain_scores_codex":[0.9983538,0.00003042152,0.0002879837,0.0009133617,0.00008296825,0.0003314734],"domain_scores_gemma":[0.9991032,0.00008897001,0.0001957467,0.0004116893,0.00007417933,0.0001262019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004505763,0.0006710057,0.5307235,0.001532577,0.006680367,0.0004618236,0.06135834,0.005444929,0.0005808913,0.3691404,0.008729701,0.01422595],"study_design_scores_gemma":[0.007043822,0.0007622351,0.09625139,0.001225236,0.001211365,0.00008522163,0.0301698,0.3426329,0.0001539953,0.1909971,0.3256109,0.003855979],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7638916,0.01777149,0.1965056,0.0006211222,0.001205556,0.000814005,0.0005612099,0.0004545207,0.01817485],"genre_scores_gemma":[0.9872956,0.001140701,0.008780333,0.00002832843,0.00005437458,0.000001128493,0.00007716769,0.00003611382,0.002586308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4344721,"threshold_uncertainty_score":0.9999914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05817080456652605,"score_gpt":0.2302712028150507,"score_spread":0.1721003982485247,"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."}}