{"id":"W4405599848","doi":"10.1109/access.2024.3520425","title":"Exploring the Preprocessing of a Time-Series Healthcare Administrative Dataset on Deep Learning to Improve Prediction","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Impact of AI and Big Data on Business and Society","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"Calgary Health Foundation","keywords":"Computer science; Preprocessor; Time series; Series (stratigraphy); Artificial intelligence; Health care; Data mining; Deep learning; Data pre-processing; Machine learning","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001360317,0.0001298625,0.0001955173,0.0001108241,0.0003537751,0.001197091,0.0007497985,0.00004144175,0.00006235907],"category_scores_gemma":[0.0007484732,0.00007246825,0.00006466078,0.0009116912,0.00007592946,0.002657647,0.0001497599,0.0002291686,0.00008203871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002946112,"about_ca_system_score_gemma":0.0001256798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078166,"about_ca_topic_score_gemma":0.00003104033,"domain_scores_codex":[0.9980413,0.0001073246,0.0004000484,0.0004410855,0.0008004577,0.0002098399],"domain_scores_gemma":[0.9986362,0.0005141316,0.0001233719,0.0004335755,0.0002045995,0.00008815074],"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":[0.0005722524,0.0001411204,0.003356813,0.00036933,0.0001064837,0.00003429996,0.02459701,0.003320918,0.007267565,0.0005353054,0.04247831,0.9172206],"study_design_scores_gemma":[0.00137978,0.006067189,0.1432735,0.003650023,0.0002349642,0.00008854891,0.05864603,0.04058332,0.2308766,0.01229221,0.5008317,0.002076203],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9781032,0.0003008051,0.008716394,0.006598425,0.002230571,0.0004552809,0.002900227,0.0001203873,0.0005746774],"genre_scores_gemma":[0.9988286,0.00007297951,0.00007377638,0.0003081263,0.0002892688,0.00004177368,0.0001255764,0.00001062767,0.0002492941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9151444,"threshold_uncertainty_score":0.9998398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3581700213879727,"score_gpt":0.4608876114588395,"score_spread":0.1027175900708668,"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."}}