{"id":"W4392607662","doi":"10.1109/jbhi.2024.3368500","title":"MAD-Former: A Traceable Interpretability Model for Alzheimer's Disease Recognition Based on Multi-Patch Attention","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; Takeda Pharmaceutical Company; IXICO; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; AbbVie; Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Drug Discovery Foundation; Merck; Alzheimer's Association; National Science Foundation","keywords":"Interpretability; Computer science; Artificial intelligence; Convolutional neural network; Feature extraction; Pattern recognition (psychology); Deep learning; Feature (linguistics); Machine 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":[],"consensus_categories":[],"category_scores_codex":[0.002033408,0.0001240819,0.0002963507,0.0003301656,0.000102363,0.0000572297,0.00005520185,0.00007279762,0.00004769694],"category_scores_gemma":[0.000102649,0.00008438312,0.000174301,0.0001523452,0.0001114117,0.0002760551,0.00001110113,0.0003507032,0.0000113678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001062347,"about_ca_system_score_gemma":0.0008919773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005036555,"about_ca_topic_score_gemma":0.00000155311,"domain_scores_codex":[0.9979714,0.00003477713,0.001013082,0.00008978408,0.0005884375,0.0003025453],"domain_scores_gemma":[0.998574,0.0001093839,0.0002144789,0.00008113858,0.0002539135,0.0007671529],"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":[0.002622885,0.001654948,0.004961978,0.008510062,0.0002486279,0.00003211911,0.001393316,0.00003961913,0.00006344937,0.00001978349,0.00842149,0.9720317],"study_design_scores_gemma":[0.002694023,0.002699271,0.007303954,0.00191442,0.0002205182,0.00004096267,0.0002458078,0.9820725,0.00004138655,0.0003939721,0.002287599,0.00008562187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2705305,0.0009788496,0.7081261,0.01819156,0.0005835231,0.001223253,0.0002125118,0.00003735732,0.0001163497],"genre_scores_gemma":[0.9803975,0.0005494162,0.0155606,0.003076022,0.0002039267,0.00003331741,0.00008715381,0.00001338439,0.00007866538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9820328,"threshold_uncertainty_score":0.3441044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09961327850566637,"score_gpt":0.403747000303852,"score_spread":0.3041337217981856,"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."}}