{"id":"W2999310302","doi":"10.1016/j.ejmp.2019.12.022","title":"Machine learning methods for optimal prediction of motor outcome in Parkinson’s disease","year":2020,"lang":"en","type":"article","venue":"Physica Medica","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":55,"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":"Parkinson's disease; Outcome (game theory); Physical medicine and rehabilitation; Motor learning; Computer science; Machine learning; Disease; Medicine; Artificial intelligence; Psychology; Neuroscience; Mathematics; Internal medicine; Mathematical economics","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":[0.000202081,0.0001717456,0.000460639,0.00007190392,0.00004333278,0.000005015072,0.00008629648,0.00004602243,0.00008041162],"category_scores_gemma":[0.0005771262,0.0001444386,0.0002054443,0.0001786745,0.0000454622,0.00006359239,0.00004300304,0.0001774656,0.000009042784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005406613,"about_ca_system_score_gemma":0.0001021812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000210193,"about_ca_topic_score_gemma":2.993068e-7,"domain_scores_codex":[0.9987168,0.00009384043,0.0003321846,0.0003498806,0.0002700267,0.0002373131],"domain_scores_gemma":[0.9990027,0.0001264849,0.0001273239,0.0001676105,0.00004584925,0.0005300638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01216846,0.005282351,0.6322557,0.003179271,0.001321013,0.0003079877,0.003190111,0.0003683213,0.06135143,0.001601003,0.001469702,0.2775046],"study_design_scores_gemma":[0.01154119,0.002107184,0.3381796,0.0002361006,0.001111067,0.000003075815,0.0001513767,0.35695,0.004279859,0.000469762,0.2846877,0.0002830377],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8150113,0.004272834,0.1546788,0.01771726,0.0006621872,0.00455971,0.001324779,0.000520447,0.00125271],"genre_scores_gemma":[0.9761074,0.00007773753,0.02264581,0.0003767277,0.0002366604,0.0002203003,0.0001950854,0.00003316232,0.0001071754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3565817,"threshold_uncertainty_score":0.5890036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04525270077188852,"score_gpt":0.3457994206691636,"score_spread":0.300546719897275,"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."}}