{"id":"W3024338276","doi":"10.1016/j.artmed.2021.102051","title":"Data imputation and compression for Parkinson's disease clinical questionnaires","year":2021,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation pour la Recherche Médicale","keywords":"Missing data; Imputation (statistics); Computer science; Autoencoder; Dimensionality reduction; Artificial intelligence; Residual; Machine learning; Data mining; Pattern recognition (psychology); Deep learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001749579,0.0001084307,0.000223487,0.00008741758,0.0001186158,0.00005318075,0.0005918777,0.00006213134,0.00001738906],"category_scores_gemma":[0.006848758,0.00009408208,0.00002037628,0.000328481,0.0001609678,0.0002959122,0.0003723068,0.00024725,0.000006975046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000203056,"about_ca_system_score_gemma":0.0001649857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001975444,"about_ca_topic_score_gemma":0.0004149315,"domain_scores_codex":[0.9978626,0.0003540775,0.0006476378,0.0006767026,0.0002450779,0.000213866],"domain_scores_gemma":[0.9972519,0.001468282,0.000125103,0.0007761494,0.0001785869,0.0001999217],"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":[0.00004585499,0.00007699056,0.03443187,0.00008469153,0.000003867986,0.00005985583,0.000481122,0.0006250151,0.00003024887,0.0791168,0.0008201856,0.8842235],"study_design_scores_gemma":[0.00006743611,0.0001095583,0.04047505,0.0003394127,0.000007639318,0.000006418563,0.0001534792,0.8550186,0.00008455825,0.09619948,0.007433979,0.0001044252],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02020109,0.002029821,0.9402513,0.03589988,0.001220014,0.0002760126,0.00001020092,0.00007848764,0.00003320456],"genre_scores_gemma":[0.9539314,0.0003619382,0.04397337,0.001112352,0.0004764781,0.00002082783,0.00009681119,0.000008494754,0.00001835395],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9337303,"threshold_uncertainty_score":0.8199098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.219277918788959,"score_gpt":0.486345439007994,"score_spread":0.267067520219035,"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."}}