{"id":"W4394007271","doi":"10.48550/arxiv.2404.03208","title":"HiMAL: A Multimodal Hierarchical Multi-task Auxiliary Learning framework for predicting and explaining Alzheimer disease progression","year":2024,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Task (project management); Disease; Computer science; Artificial intelligence; Cognitive psychology; Psychology; Medicine; Internal medicine; Economics","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001224127,0.0006884083,0.0006319341,0.0003148751,0.0007305013,0.0004852961,0.001217772,0.0006744137,0.00000870875],"category_scores_gemma":[0.002837202,0.0006474727,0.0002885311,0.0002887314,0.0001682994,0.0002417441,0.006101863,0.005948876,0.00003472463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000102293,"about_ca_system_score_gemma":0.0005252187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000109637,"about_ca_topic_score_gemma":0.000005447728,"domain_scores_codex":[0.994793,0.0005818843,0.0007760406,0.002287306,0.0005987664,0.0009630244],"domain_scores_gemma":[0.9960016,0.001540319,0.0004375268,0.001121085,0.0001746492,0.0007248233],"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":[0.00009567173,0.00009511422,0.9088685,0.001479085,0.0001374858,0.0001594177,0.004841278,0.003692043,0.00002625067,0.002391964,0.00004198009,0.07817124],"study_design_scores_gemma":[0.0003858094,0.000152984,0.1840878,0.003342097,0.0001257114,0.00001366024,0.00007239892,0.8057168,0.00002128616,0.004779423,0.0006916219,0.0006103937],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6905092,0.00914565,0.2881129,0.005688909,0.00248871,0.001997829,0.00003892403,0.00197779,0.00004006766],"genre_scores_gemma":[0.7400093,0.00006318365,0.2579789,0.0002374418,0.0007605083,0.0007137624,0.00006852295,0.0001151481,0.00005320087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8020247,"threshold_uncertainty_score":0.9995977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0652903193922114,"score_gpt":0.3763629050315728,"score_spread":0.3110725856393614,"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."}}