{"id":"W2954901872","doi":"10.1016/j.compbiomed.2019.103347","title":"Optimized machine learning methods for prediction of cognitive outcome in Parkinson's disease","year":2019,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael J. Fox Foundation for Parkinson's Research","keywords":"Artificial intelligence; Feature selection; Hyperparameter; Machine learning; Computer science; Regression; Linear discriminant analysis; Feature (linguistics); Linear regression; Pattern recognition (psychology); Statistics; Mathematics","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":[0.002375607,0.0008050055,0.001173885,0.0009699598,0.0003300725,0.001128794,0.001145568,0.001162255,0.001236586],"category_scores_gemma":[0.006457184,0.0004872527,0.0008043115,0.0006917492,0.0004143307,0.0006703068,0.0005953239,0.001298423,0.0003999109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001134919,"about_ca_system_score_gemma":0.001635249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01071865,"about_ca_topic_score_gemma":0.007696106,"domain_scores_codex":[0.9994462,0.0002515244,0.0000555386,0.0001013703,0.00008703309,0.00005838853],"domain_scores_gemma":[0.9968965,0.002355438,0.0001752276,0.0001172186,0.000395538,0.00006019796],"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":[0.0002439936,0.0001015795,0.003378819,0.00005650125,0.0001296354,0.00004354493,0.00001936628,0.913311,0.0004292958,0.001342348,0.001822321,0.0791216],"study_design_scores_gemma":[0.00001191791,0.00001360978,0.0004357629,0.000005396277,0.000009475098,0.00000689451,0.000002262781,0.9981512,0.0001374179,0.001143022,0.00007958333,0.000003443419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2174609,0.004936594,0.7705335,0.001480072,0.0002532413,0.0001484372,0.001306278,0.001883956,0.001997011],"genre_scores_gemma":[0.860594,0.0008716899,0.1332704,0.0002305701,0.0001827988,0.000234806,0.001561994,0.0001337673,0.002919913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01071865,"threshold_uncertainty_score":0.02131253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03452543756524992,"score_gpt":0.3762549476332722,"score_spread":0.3417295100680222,"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."}}