{"id":"W4408218591","doi":"10.1007/s10140-025-02328-3","title":"Forecasting trends of rising emergency department chest imaging using machine learning","year":2025,"lang":"en","type":"article","venue":"Emergency Radiology","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Institutes of Health","keywords":"Medicine; Emergency department; Computed tomography; Medical physics; Medical emergency; Radiology; Emergency medicine","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004561683,0.0002074066,0.0005167888,0.000300697,0.0002096984,0.000002311544,0.0001569639,0.0001129648,0.001903152],"category_scores_gemma":[0.0007851897,0.0001977554,0.0002352725,0.0008579891,0.0001094477,0.00005595627,0.00007962928,0.0003989523,0.000008042655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009401087,"about_ca_system_score_gemma":0.00007007869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001638392,"about_ca_topic_score_gemma":0.00003710404,"domain_scores_codex":[0.9978458,0.0001176424,0.00108166,0.0004301866,0.0001308476,0.0003938211],"domain_scores_gemma":[0.9989288,0.0001885159,0.0003162681,0.0003598559,0.0001080972,0.00009840036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000566594,0.0001881041,0.952054,0.00008747024,0.0001818342,0.000005358608,0.0001363676,0.000274401,0.03051581,0.0006013083,0.00103522,0.0148635],"study_design_scores_gemma":[0.003467465,0.0006812703,0.6107149,0.0003149407,0.001745257,0.0005452545,0.0004052889,0.2747929,0.007110122,0.007563073,0.09169323,0.0009662689],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9650024,0.004005307,0.01527571,0.001116008,0.001186149,0.0002468626,0.00001546544,0.0001010514,0.01305109],"genre_scores_gemma":[0.9873272,0.0005917238,0.009783634,0.00006053382,0.0002231776,0.00003101667,0.000119531,0.00002821329,0.001835008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3413391,"threshold_uncertainty_score":0.9990093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0563222376748988,"score_gpt":0.3717548073809127,"score_spread":0.3154325697060139,"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."}}