{"id":"W4386465643","doi":"10.36227/techrxiv.24078639","title":"Predicting Progression from Mild Cognitive Impairment to Alzheimer’s Dementia with Adversarial Attacks","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; Genentech; IXICO; H. Lundbeck A/S; Servier; National Institutes of Health; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Eisai; Northern California Institute for Research and Education; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; Biogen; Bristol-Myers Squibb; Eli Lilly and Company; BioClinica; Novartis Pharmaceuticals Corporation; Pfizer; F. Hoffmann-La Roche; Alzheimer's Drug Discovery Foundation","keywords":"Dementia; Adversarial system; Artificial intelligence; Binary classification; Subtyping; Computer science; Machine learning; Cognitive impairment; Alzheimer's disease; Deep learning; Disease; Decision boundary; Cognition; Artificial neural network; Set (abstract data type); Psychology; Cognitive psychology; Psychiatry; Medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001375766,0.0008064163,0.0006076327,0.0004145793,0.0002426318,0.0005682665,0.0006802438,0.0009375947,0.00106781],"category_scores_gemma":[0.003717189,0.0003128678,0.0006317924,0.0002171617,0.0007427025,0.0006601992,0.0009883732,0.001945234,0.0002750595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007939647,"about_ca_system_score_gemma":0.0005808256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004330992,"about_ca_topic_score_gemma":0.00397041,"domain_scores_codex":[0.999598,0.0001604186,0.00002337011,0.00009339569,0.00006371214,0.00006108391],"domain_scores_gemma":[0.998373,0.001157498,0.0001396571,0.0001472367,0.00009084594,0.00009183041],"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":[0.000325366,0.00009467344,0.0069318,0.00003212135,0.00006395682,0.0001962583,0.00006060141,0.928625,0.001697386,0.005662283,0.002699803,0.05361072],"study_design_scores_gemma":[0.000004047078,0.00001644829,0.0004701306,0.000003715568,0.000004308105,0.00001982754,0.000003485204,0.9961873,0.0004284418,0.002726309,0.0001324161,0.000003628978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.308064,0.001103036,0.6814237,0.002778854,0.0001667112,0.0001356555,0.0008069514,0.001153011,0.004367995],"genre_scores_gemma":[0.9549921,0.000262667,0.04055552,0.0003313463,0.0000739684,0.00005995642,0.000746784,0.00003948979,0.002938135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004330992,"threshold_uncertainty_score":0.00861156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06278055037655206,"score_gpt":0.3629973759015641,"score_spread":0.300216825525012,"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."}}