{"id":"W2994848630","doi":"10.1101/2019.12.19.883462","title":"Data-driven algorithm for the diagnosis of behavioral variant frontotemporal dementia","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Western University; Health Sciences Centre; McGill University Health Centre; Sunnybrook Health Science Centre; Toronto Western Hospital; Université Laval; Montreal Neurological Institute and Hospital","funders":"Medical Research Council; Health Canada; National Institutes of Health; Fondation Brain Canada; University of California, San Francisco; Ministero della Salute; University of Southern California","keywords":"Frontotemporal dementia; Random forest; Cohort; Dementia; Neuropsychology; Cognition; Classifier (UML); Audiology; Neuroimaging; Neuropsychological assessment; Psychology; Artificial intelligence; Medicine; Computer science; Pathology; Neuroscience","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":[0.006134363,0.0009952338,0.001273429,0.001692259,0.0006740026,0.001277236,0.001824541,0.00197937,0.00369955],"category_scores_gemma":[0.01408652,0.0003999071,0.001400129,0.0007929648,0.0003787951,0.0006832904,0.0009428989,0.00179422,0.002571809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001194015,"about_ca_system_score_gemma":0.002553935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007057467,"about_ca_topic_score_gemma":0.005917324,"domain_scores_codex":[0.9984698,0.0004923482,0.0001666614,0.0004285478,0.0002894956,0.0001531531],"domain_scores_gemma":[0.9955425,0.002572946,0.0002075122,0.000275643,0.001289073,0.0001123328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001822581,0.0006616546,0.02439432,0.0003117654,0.0004448717,0.0003749102,0.0001130625,0.3180628,0.004734341,0.005650248,0.02377486,0.6196545],"study_design_scores_gemma":[0.0000784214,0.00005934967,0.001030339,0.00002671734,0.00001997775,0.00008273303,0.00001232458,0.993147,0.00115931,0.003223138,0.001151176,0.000009593644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05964797,0.0008600504,0.9244987,0.001125637,0.0002495275,0.0008285029,0.003123653,0.00807631,0.00158968],"genre_scores_gemma":[0.4146209,0.0002166602,0.5726317,0.0007194828,0.0001513759,0.001570148,0.007324073,0.0003546814,0.002411036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007057467,"threshold_uncertainty_score":0.03244197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04783345177284973,"score_gpt":0.3137392735659001,"score_spread":0.2659058217930503,"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."}}