{"id":"W4401103145","doi":"","title":"Generative models of MRI-derived neuroimaging features and associated dataset of 18,000 samples.","year":2024,"lang":"en","type":"preprint","venue":"PubMed","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"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; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; Eisai; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; BioClinica; University of Southern California; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Generative grammar; Generative model; Artificial intelligence; Psychology; Neuroscience; Pattern recognition (psychology); Computer science","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":[0.003742148,0.0008518493,0.0006746173,0.001369923,0.0004093215,0.0009608636,0.00200961,0.001785304,0.005092497],"category_scores_gemma":[0.01240785,0.0006396137,0.001841081,0.001290883,0.001136206,0.0007345715,0.001195948,0.002055855,0.002250201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074104,"about_ca_system_score_gemma":0.001097892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007170528,"about_ca_topic_score_gemma":0.01295689,"domain_scores_codex":[0.9990522,0.0004390005,0.00004987584,0.0002499328,0.0001428055,0.00006616543],"domain_scores_gemma":[0.9938881,0.004074849,0.0003300802,0.001121606,0.0004389122,0.0001464518],"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":[0.001618522,0.0008351379,0.09239843,0.0008217956,0.0008207309,0.001506803,0.0006582119,0.5899569,0.008805635,0.04709719,0.1247666,0.1307141],"study_design_scores_gemma":[0.0003977917,0.0002902166,0.02381873,0.0001601277,0.0001906226,0.001394556,0.0001539008,0.8858591,0.005192922,0.05109857,0.03133029,0.0001131223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.324725,0.003275277,0.4851989,0.004223242,0.0007263127,0.001280763,0.1652504,0.009293948,0.006026213],"genre_scores_gemma":[0.6257522,0.001196486,0.1585844,0.001119962,0.000252795,0.002041398,0.2047836,0.0005910712,0.005678061],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.007170528,"threshold_uncertainty_score":0.01979059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04231343947932548,"score_gpt":0.2963193423201924,"score_spread":0.2540059028408669,"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."}}