{"id":"W3157400911","doi":"10.1016/j.cmpb.2021.106131","title":"Feature selection and machine learning methods for optimal identification and prediction of subtypes in Parkinson's disease","year":2021,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Machine learning; Computer science; Feature selection; Identification (biology); Cluster analysis; Feature (linguistics); Task (project management); Pattern recognition (psychology); Selection (genetic algorithm)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00160776,0.000121673,0.0003346576,0.0002273334,0.00004530407,0.00002316088,0.00002384016,0.00009898644,0.000002130658],"category_scores_gemma":[0.0001979185,0.0001029185,0.00002944465,0.0004541403,0.0001022319,0.0000710332,0.00003988654,0.0001953028,2.400074e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001572017,"about_ca_system_score_gemma":0.00003255248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002563181,"about_ca_topic_score_gemma":0.00001508794,"domain_scores_codex":[0.9988533,0.0003211639,0.00024942,0.0003456399,0.00008164856,0.0001488858],"domain_scores_gemma":[0.9994149,0.0002075966,0.00008549145,0.00009211552,0.00009309648,0.0001068017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002160612,0.0001020231,0.1928103,0.0005236822,0.00002792901,0.000006379811,0.0004502622,0.000007050954,0.007558926,0.00003749241,0.00001732787,0.7982426],"study_design_scores_gemma":[0.004473044,0.001228849,0.6317015,0.000575882,0.000226511,0.0001252185,0.0004150917,0.3079379,0.002568509,0.0007540619,0.04982869,0.0001647424],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.352408,0.01591459,0.6283756,0.002557577,0.0001452127,0.0005614581,0.000004513457,0.00002834775,0.000004690872],"genre_scores_gemma":[0.1170213,0.002326591,0.880123,0.00008637499,0.0001121125,0.0000496769,0.0001842378,0.00001388149,0.00008289935],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7980778,"threshold_uncertainty_score":0.4196894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420528982322956,"score_gpt":0.375434078945144,"score_spread":0.3312287891219144,"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."}}