{"id":"W4414803436","doi":"10.1016/j.jacr.2025.09.027","title":"The Iodine Opportunity for Sustainable Radiology: Quantifying Supply-Chain Strategies to Cut Contrast’s Carbon and Costs","year":2025,"lang":"en","type":"article","venue":"Journal of the American College of Radiology","topic":"Radiation Dose and Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Microsoft Azure; National Institutes of Health; University of Maryland, Baltimore; Association of University Radiologists; National Institute on Minority Health and Health Disparities; University of Maryland","keywords":"Sustainability; Carbon fibers; Carbon footprint; Carbon tax; Sustainable development; Health care; Cost–benefit analysis","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":[0.001351936,0.0001298207,0.0007033143,0.0002345077,0.0002364672,0.0000175646,0.0002570444,0.00004344721,0.000002601914],"category_scores_gemma":[0.0016774,0.00007544881,0.0001403214,0.0003883131,0.0006003312,0.00007018493,0.00006584444,0.0002517183,6.96571e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691751,"about_ca_system_score_gemma":0.001029679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000128289,"about_ca_topic_score_gemma":0.00003953057,"domain_scores_codex":[0.9985796,0.0002976499,0.0005368539,0.0001282814,0.000110341,0.0003472969],"domain_scores_gemma":[0.9975188,0.001116957,0.0006409097,0.0002362672,0.0003577049,0.0001293428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.02300497,0.0004409231,0.2906485,0.0005530424,0.004509816,0.0006984603,0.002055088,0.001602867,0.08578806,0.1706925,0.3782547,0.04175102],"study_design_scores_gemma":[0.02419726,0.01604349,0.4448823,0.001083798,0.002178488,0.01777642,0.2130983,0.01310091,0.01720204,0.01366559,0.2357658,0.001005667],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9520782,0.001809778,0.0005394355,0.04368247,0.0003080987,0.0005846386,0.00001667413,0.000006298192,0.0009744004],"genre_scores_gemma":[0.9960874,0.0006514199,0.0003080465,0.001734348,0.0001383021,0.00001210402,9.051162e-7,0.00001011195,0.001057413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2110432,"threshold_uncertainty_score":0.3076713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01702126670377609,"score_gpt":0.3089991523614547,"score_spread":0.2919778856576786,"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."}}