{"id":"W4399709995","doi":"10.1016/j.media.2024.103231","title":"Interpretable deep clustering survival machines for Alzheimer’s disease subtype discovery","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Genentech; IXICO; U.S. National Library of Medicine; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Cluster analysis; Discriminative model; Artificial intelligence; Machine learning; Computer science; Categorization; Pattern recognition (psychology); Data mining","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007680746,0.000178962,0.0004425702,0.0004217492,0.00008356311,0.0002567143,0.0001660506,0.00005936408,0.004910152],"category_scores_gemma":[0.000763814,0.000129672,0.000633493,0.0009216872,0.0001483911,0.0003189271,0.0001630468,0.00023656,0.00008728766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003981903,"about_ca_system_score_gemma":0.0002098935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001101383,"about_ca_topic_score_gemma":0.0001569345,"domain_scores_codex":[0.997797,0.00007778269,0.0003149041,0.0004662773,0.0009198338,0.0004242313],"domain_scores_gemma":[0.9986892,0.000298069,0.00002554639,0.0002710934,0.0001338718,0.000582184],"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":[0.003107691,0.00166759,0.4963471,0.002128895,0.03973157,0.006482655,0.000521887,0.00004184693,0.002919439,0.0005405227,0.01085489,0.4356559],"study_design_scores_gemma":[0.0009865245,0.0002075209,0.06815796,0.0002486775,0.01762204,0.00001165912,0.0001354911,0.9065,0.0003378417,0.0003171629,0.005210625,0.0002644978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08265632,0.005499873,0.8986596,0.006626459,0.0003724947,0.0005425464,0.00007223508,0.0001741838,0.005396325],"genre_scores_gemma":[0.9919299,0.0001916631,0.0007210986,0.0005903393,0.0003817691,0.0001191539,0.0004223713,0.00003175759,0.005611917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9092736,"threshold_uncertainty_score":0.9959995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01921036101325226,"score_gpt":0.3603439240123461,"score_spread":0.3411335629990939,"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."}}