{"id":"W4391335182","doi":"10.1093/bioinformatics/btae264","title":"TA-RNN: an attention-based time-aware recurrent neural network architecture for electronic health records","year":2024,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute of General Medical Sciences; Northern California Institute for Research and Education; University of North Texas; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Recurrent neural network; Computer science; Architecture; Health records; Electronic health record; Artificial neural network; Artificial intelligence; History; Health care; Political science","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00151514,0.0006280892,0.0007151935,0.0003282954,0.0003920051,0.0006645065,0.001988612,0.0004135353,0.00002053029],"category_scores_gemma":[0.00009879328,0.0005760483,0.0004121418,0.0005001583,0.0000458471,0.0001704925,0.001246878,0.002703227,0.0001113236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006344139,"about_ca_system_score_gemma":0.002693694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001045246,"about_ca_topic_score_gemma":0.0001961128,"domain_scores_codex":[0.9956646,0.0003140346,0.001286241,0.0007478854,0.0006224251,0.001364824],"domain_scores_gemma":[0.9964263,0.0002708638,0.0008946164,0.001769907,0.0002381985,0.000400079],"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":[0.00004080149,0.00007736358,0.0003748085,0.01021323,0.00008875122,0.00000355616,0.001776854,0.336289,2.397996e-7,0.003728847,0.03978255,0.607624],"study_design_scores_gemma":[0.0002205024,0.0008605978,0.0002397049,0.0007993144,0.00002366447,0.00001533458,0.00001584297,0.9689835,4.85009e-7,0.008336503,0.01997955,0.0005250116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002616613,0.001755565,0.9630698,0.02016243,0.006668371,0.003460338,0.000314126,0.001707944,0.0002448499],"genre_scores_gemma":[0.06280394,0.0002121889,0.9138522,0.01026837,0.00434769,0.001192,0.006096526,0.000309496,0.0009176105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6326945,"threshold_uncertainty_score":0.9996691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02139770856646895,"score_gpt":0.3124257444798212,"score_spread":0.2910280359133522,"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."}}