{"id":"W4415158621","doi":"10.1007/s13755-025-00384-0","title":"Timelygpt: extrapolatable transformer pre-training for long-term time-series forecasting in healthcare","year":2025,"lang":"en","type":"article","venue":"Health Information Science and Systems","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Health care; Trajectory; State (computer science); Key (lock); Health data","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":[0.0008089175,0.001054756,0.0005065949,0.0005176977,0.0002114242,0.0004508557,0.001186013,0.0007483221,0.00308116],"category_scores_gemma":[0.003154201,0.0004371348,0.000858653,0.0005641561,0.000299258,0.001058266,0.0009174988,0.001923298,0.000988223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005303278,"about_ca_system_score_gemma":0.001172964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008345421,"about_ca_topic_score_gemma":0.009333805,"domain_scores_codex":[0.9997655,0.00005345095,0.00001586581,0.00008851375,0.00004515368,0.00003158614],"domain_scores_gemma":[0.9994305,0.0003259265,0.00004838223,0.00006461157,0.00009592956,0.00003466885],"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":[0.0004737214,0.0002555657,0.00856722,0.0001985528,0.0001712581,0.0004253515,0.0001386172,0.4619716,0.007689485,0.0040707,0.01485553,0.5011825],"study_design_scores_gemma":[0.00001077057,0.00005777765,0.0004271298,0.000009321755,0.0000127551,0.00005011238,0.00001009768,0.9951593,0.001239693,0.00233261,0.0006838682,0.000006548155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05613866,0.001341928,0.9310586,0.0008406344,0.0002026084,0.0001040016,0.001038802,0.007442509,0.001832215],"genre_scores_gemma":[0.8232009,0.0008698138,0.1672404,0.0006870417,0.0001539487,0.0001898003,0.003413322,0.000430282,0.003814427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008345421,"threshold_uncertainty_score":0.01659369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06041971627833059,"score_gpt":0.3547379458841999,"score_spread":0.2943182296058693,"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."}}