{"id":"W4413051491","doi":"10.3233/shti250954","title":"Evaluating Zero-Shot Foundation Models for Time Series Forecasting in Clinical Settings: A Simulation Study with Electronic Health Records","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Health records; Electronic health record; Foundation (evidence); Series (stratigraphy); Zero (linguistics); Shot (pellet); Computer science; Time series; Machine learning; History; Health care; Geology; Political science; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.007714775,0.0001935519,0.0006337463,0.0008432074,0.0005814387,0.000036773,0.000314455,0.0001391212,2.747699e-7],"category_scores_gemma":[0.002108139,0.0001741052,0.00002137858,0.001499429,0.0001509795,0.0006812268,0.0003428005,0.000773144,6.531005e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004954932,"about_ca_system_score_gemma":0.000872102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006075083,"about_ca_topic_score_gemma":0.0005514936,"domain_scores_codex":[0.9965539,0.0003308197,0.001947203,0.0003196694,0.0001811234,0.0006672823],"domain_scores_gemma":[0.9973464,0.001172867,0.0008233434,0.0003733809,0.0002462171,0.00003776738],"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":[0.0002026411,0.0001645651,0.141164,0.003631748,0.00007661174,0.000001032848,0.0254897,0.1575411,4.24924e-8,0.04804377,0.00008474052,0.6236001],"study_design_scores_gemma":[0.001161363,0.004550394,0.002019529,0.000730078,0.000003729719,0.000005837903,0.005405782,0.9468855,2.546602e-7,0.03887969,0.0002352138,0.0001225817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4778846,0.002340284,0.4921794,0.02103702,0.0004050269,0.005553082,0.000002593112,0.0004546402,0.000143354],"genre_scores_gemma":[0.8708268,0.0003451415,0.126941,0.001504565,0.00001453987,0.0003228907,0.00000605183,0.000009171536,0.00002979905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7893445,"threshold_uncertainty_score":0.7099803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1318690127842805,"score_gpt":0.4816748992979237,"score_spread":0.3498058865136432,"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."}}