{"id":"W4410226705","doi":"10.1109/jbhi.2025.3568778","title":"How Deep is Your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Mental Health Research Topics","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"UCLH Biomedical Research Centre; Menzies Centre for Australian Studies, King's College London, University of London; NIHR Maudsley Biomedical Research Centre; Dalhousie University; University College London; King's College London; Engineering and Physical Sciences Research Council; China Scholarship Council; National Institute for Health and Care Research; Maudsley Charity","keywords":"Computer science; Imputation (statistics); Deep learning; Artificial intelligence; Time series; Perspective (graphical); Series (stratigraphy); Machine learning; Data mining; Data science; Missing data","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":[0.002488109,0.0001423389,0.0004231593,0.0004263916,0.0003144244,0.00007040996,0.0002142748,0.0002488527,0.0002457781],"category_scores_gemma":[0.0006369387,0.0001068712,0.00008582397,0.0002291405,0.0002372317,0.0002257272,0.00003808353,0.0008865084,0.00002160693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003418967,"about_ca_system_score_gemma":0.0006291115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003382591,"about_ca_topic_score_gemma":0.00001334111,"domain_scores_codex":[0.9972907,0.0001448586,0.001118696,0.0001003289,0.0008469577,0.000498405],"domain_scores_gemma":[0.9978395,0.0003660336,0.0006449897,0.0001042842,0.000331634,0.0007135683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001198332,0.0004738128,0.000457693,0.00246864,0.0002800032,0.00003667239,0.04592609,0.000007740107,0.000005037391,0.01438082,0.1042277,0.8305375],"study_design_scores_gemma":[0.01641152,0.02529507,0.008196182,0.002840448,0.0001103832,0.0009122023,0.1301046,0.05852017,0.0001171075,0.03147319,0.7253717,0.0006473785],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.07123014,0.006088617,0.3835403,0.5241674,0.005636283,0.002057802,0.00006297146,0.0000871258,0.007129387],"genre_scores_gemma":[0.6582922,0.01880807,0.1110718,0.1748659,0.01101746,0.0003145019,0.0001868605,0.0001945205,0.02524876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8298901,"threshold_uncertainty_score":0.4358082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05066418563227157,"score_gpt":0.4484937576297608,"score_spread":0.3978295719974893,"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."}}