{"id":"W4404295861","doi":"10.36227/techrxiv.173143474.47669751/v1","title":"Exploring the Preprocessing of a Time-Series Administrative Healthcare Dataset on Deep Learning to Improve Prediction","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"Canadian Institutes of Health Research; University of Calgary; Alberta Innovates; University of Alberta; Government of Alberta; Alberta Health Services","keywords":"Preprocessor; Computer science; Deep learning; Time series; Series (stratigraphy); Artificial intelligence; Data pre-processing; Health care; Machine learning; Data mining; Data science; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003229812,0.001151322,0.0004964216,0.001096747,0.0003522849,0.001243106,0.001043244,0.0007441023,0.001903314],"category_scores_gemma":[0.01337802,0.0002716615,0.0009276231,0.001396252,0.0003475179,0.001597038,0.000806459,0.002436607,0.0009588417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008646148,"about_ca_system_score_gemma":0.001591427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009534284,"about_ca_topic_score_gemma":0.01340902,"domain_scores_codex":[0.9989756,0.0004348714,0.0000957651,0.000200682,0.0001929381,0.0001001776],"domain_scores_gemma":[0.9954515,0.002712121,0.000283697,0.0007365835,0.0007239138,0.00009217753],"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":[0.0005992895,0.001118857,0.04450272,0.0004082771,0.0003396551,0.0003473383,0.0002336766,0.4172625,0.01457533,0.007436357,0.02490455,0.4882714],"study_design_scores_gemma":[0.00002499376,0.0001633901,0.007691663,0.00004150789,0.00002379528,0.00004299688,0.00007888962,0.9758698,0.00789667,0.00477499,0.003365465,0.00002582997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3758605,0.001081076,0.5968795,0.003679514,0.0006825862,0.0005017663,0.008726246,0.00886998,0.003718888],"genre_scores_gemma":[0.7529049,0.0005317844,0.2287417,0.000468553,0.0001279069,0.0004961134,0.01469099,0.0001787181,0.001859314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009534284,"threshold_uncertainty_score":0.01895761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09581581284355277,"score_gpt":0.3572450434689112,"score_spread":0.2614292306253584,"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."}}