{"id":"W3113230938","doi":"10.1101/2020.12.17.423213","title":"Random forest model for feature-based Alzheimer’s disease conversion prediction from early mild cognitive impairment subjects","year":2020,"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":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; University of Southern California; Northern California Institute for Research and Education; Foundation for the National Institutes of Health","keywords":"Random forest; Neuroimaging; Cognitive impairment; Cognition; Feature (linguistics); Alzheimer's disease; Computer science; Disease; Medicine; Artificial intelligence; Internal medicine; Psychiatry","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":[0.006472391,0.001261353,0.001162448,0.001164893,0.0004265779,0.0006111378,0.0008915722,0.0009711226,0.00190026],"category_scores_gemma":[0.006160365,0.0002815381,0.001446446,0.0005218798,0.00025709,0.0006169678,0.0004067566,0.001307481,0.00091406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005379384,"about_ca_system_score_gemma":0.0009986887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01161834,"about_ca_topic_score_gemma":0.00794134,"domain_scores_codex":[0.9991104,0.0004631432,0.00003540793,0.0001968905,0.00007594309,0.0001182233],"domain_scores_gemma":[0.9973175,0.001877604,0.0001428772,0.0001185835,0.0004219906,0.0001214506],"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":[0.00235224,0.0006278164,0.03261189,0.000136542,0.0004189188,0.0002788817,0.00007958227,0.8143193,0.002535373,0.001749824,0.008361709,0.1365279],"study_design_scores_gemma":[0.00003897398,0.0001052652,0.001610485,0.00001430432,0.00003289492,0.00002436251,0.000007267917,0.9966992,0.0001918478,0.001038257,0.0002274404,0.000009849888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4383773,0.002270467,0.5499456,0.001137644,0.0004105125,0.0003948351,0.003381866,0.002439598,0.001642203],"genre_scores_gemma":[0.9305702,0.0003201075,0.06220828,0.0002260566,0.000158498,0.0002834001,0.00458375,0.00008627502,0.001563397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01161834,"threshold_uncertainty_score":0.0342297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02972424543919127,"score_gpt":0.267355859716169,"score_spread":0.2376316142769778,"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."}}