{"id":"W1983619709","doi":"10.1016/j.neurobiolaging.2014.05.040","title":"Thickness network features for prognostic applications in dementia","year":2014,"lang":"en","type":"article","venue":"Neurobiology of Aging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"DoD Alzheimer's Disease Neuroimaging Initiative; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; GE Healthcare; National Institutes of Health; Genentech; IXICO; Servier; Pfizer; Bristol-Myers Squibb Foundation; Novartis Pharmaceuticals Corporation; Takeda Pharmaceutical Company; Eli Lilly and Company; Alzheimer's Disease Neuroimaging Initiative; Roche; Merck; Alzheimer's Drug Discovery Foundation; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Spec#; Dementia; Neuroimaging; Pattern recognition (psychology); Graph; Cluster analysis; Clustering coefficient; Magnetic resonance imaging; Artificial intelligence; Reproducibility; Computer science; Mathematics; Internal medicine; Disease; Medicine; Neuroscience; Psychology; Statistics; Radiology; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001816357,0.001048794,0.0006610369,0.00417729,0.0005891366,0.001787646,0.0007294804,0.0007724911,0.004447267],"category_scores_gemma":[0.007458755,0.0003247565,0.0004596861,0.001796952,0.000315698,0.001943224,0.0008916941,0.0008208163,0.0007293747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005597459,"about_ca_system_score_gemma":0.0004597435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00448786,"about_ca_topic_score_gemma":0.007624774,"domain_scores_codex":[0.9997775,0.00007030174,0.00003393872,0.00004072114,0.0000496968,0.00002783524],"domain_scores_gemma":[0.9972678,0.0009417781,0.0007377965,0.0002386287,0.0005634603,0.0002504958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001916922,0.0001598274,0.8662105,0.0001852318,0.000498252,0.0005624325,0.0002089623,0.01069391,0.002959816,0.002254705,0.00396608,0.1103832],"study_design_scores_gemma":[0.0001475897,0.0005969937,0.7801293,0.0003872988,0.001174337,0.002736023,0.0008950689,0.1737244,0.004597384,0.03059954,0.004897765,0.0001142332],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9610759,0.003788233,0.01871786,0.0009063933,0.0002333209,0.0001288164,0.006022546,0.0004228941,0.008703969],"genre_scores_gemma":[0.9887816,0.0007058915,0.007982357,0.00003439854,0.0001287149,0.00006166111,0.00115487,0.00002728844,0.001123222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00448786,"threshold_uncertainty_score":0.01487762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01270620023795302,"score_gpt":0.3038396708291737,"score_spread":0.2911334705912207,"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."}}