{"id":"W3155150813","doi":"10.1101/2021.04.19.440501","title":"Multi-scale semi-supervised clustering of brain images: deriving disease subtypes","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; 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; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; European Commission; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Cluster analysis; Computer science; Artificial intelligence; Pattern recognition (psychology); Scale (ratio); Identification (biology); Machine learning; Data mining; Biology; Cartography; Geography","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":[0.001092284,0.000744421,0.0009239893,0.0003967206,0.0002530786,0.0006058977,0.002466785,0.0004535715,0.0000451359],"category_scores_gemma":[0.001185013,0.0008676822,0.000334986,0.0008838378,0.000137529,0.0005092848,0.00373042,0.001377293,0.00002049989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000289467,"about_ca_system_score_gemma":0.001486062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003765383,"about_ca_topic_score_gemma":0.0000295548,"domain_scores_codex":[0.9948198,0.0006737727,0.0009828053,0.001907973,0.0007447333,0.0008709615],"domain_scores_gemma":[0.9939617,0.0003106166,0.0006918497,0.003476349,0.0008648693,0.0006946084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004069705,0.0005128009,0.2211965,0.008845209,0.0002376703,0.0005891891,0.0004165056,0.01351163,0.7541737,0.0001667943,0.0002521911,0.00005705038],"study_design_scores_gemma":[0.0006190662,0.00004147121,0.4653143,0.002308789,0.0000618762,6.087041e-8,0.00001219815,0.4901666,0.03988156,0.000001232807,0.0003631218,0.001229702],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.524761,0.002802314,0.4673259,0.001597064,0.001722649,0.0007680852,0.0001061768,0.0009120826,0.000004781575],"genre_scores_gemma":[0.788806,0.0001141166,0.2101806,0.0004209247,0.0002272989,0.0001178425,6.573548e-7,0.0001235554,0.000008990749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7142922,"threshold_uncertainty_score":0.9993774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01706203294913796,"score_gpt":0.2507743958190482,"score_spread":0.2337123628699102,"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."}}