Evaluating and Mitigating Carbon Dioxide Equivalent Emissions in Stroke Management: A Modeling Study
Journal of the American Heart Association · 07.07.2026 · 15 (13)
DOI: 10.1161/jaha.125.047556 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Heart Association, erschienen am 07.07.2026. Verfasst von Alireza Vafaei Sadr und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health Sciences, College of Medicine Pennsylvania State University Hershey PA USA. Hauptthemen laut MEDLINE: Stroke, Carbon Dioxide, Artificial Intelligence, Carbon Footprint. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Schlaganfall
Abstract (Originalsprache)
Background
Artificial intelligence (AI) can improve stroke imaging workflows, but its computational carbon footprint remains poorly quantified. We estimated carbon dioxide equivalent (CO 2 eq) emissions from AI use in US stroke management and evaluated carbon‐aware mitigation.
Methods
We combined TriNetX neuroimaging utilization data with Global Burden of Disease stroke burden estimates for 2018 to 2019. Imaging utilization rates were aligned by state, year, stroke type, sex, and age group. We modeled 2 AI scenarios: Minimal AI, defined as one 2‐dimensional classification model and one 2‐dimensional segmentation model; and Ideal AI, defined as two 2‐dimensional classification models, two 3‐dimensional segmentation models, and one 3‐dimensional classification model. Model energy use was converted to CO 2 eq using state‐level grid carbon intensity from Electricity Maps.
Results
Ideal AI generated 16 375.09 metric tons CO 2 eq/year (95% CI, 16 340.83–16 409.36), compared with 7692.70 metric tons CO 2 eq/year (95% CI, 7676.08–7709.32) for Minimal AI. Computed tomography angiography and magnetic resonance imaging were the largest modality contributors. Per‐capita emissions varied substantially by state, reflecting local grid composition. Relocating AI‐related processing to cleaner‐energy states reduced modeled Ideal AI emissions to 7408.68 metric tons CO 2 eq/year (95% CI, 7386.99–7430.38), a 54.75% reduction.
Conclusions
AI‐assisted stroke imaging has a measurable carbon footprint that depends on model intensity, imaging modality, and grid carbon intensity. Carbon‐aware routing of computation offers an immediate mitigation strategy while preserving clinical AI use.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Public Health Sciences, College of Medicine Pennsylvania State University Hershey PA USA.
- Department of Neurology, College of Medicine The Pennsylvania State University Hershey PA USA.
- Department of Data Sciences Harrisburg University Harrisburg PA USA.
- Institute of Pathology University Hospital Aachen, RWTH Aachen University Aachen Germany.
ORCID-Profile: Alireza Vafaei Sadr, Seyyed Sina Hejazian, Ajith Vemuri, Peter Boor, Ramin Zand, Vida Abedi
Zitieren
APA
Vafaei Sadr, A., Hejazian, S. S., Vemuri, A., Thakur, A., Boor, P., Zand, R., & Abedi, V. (2026). Evaluating and Mitigating Carbon Dioxide Equivalent Emissions in Stroke Management: A Modeling Study. Journal of the American Heart Association, 15(13). https://doi.org/10.1161/jaha.125.047556
Vancouver
Vafaei Sadr A, Hejazian SS, Vemuri A, Thakur A, Boor P, Zand R, et al. Evaluating and Mitigating Carbon Dioxide Equivalent Emissions in Stroke Management: A Modeling Study. Journal of the American Heart Association. 2026;15(13). doi:10.1161/jaha.125.047556
BibTeX
@article{VafaeiSadr2026,
author = {Vafaei Sadr, Alireza and Hejazian, Seyyed Sina and Vemuri, Ajith and Thakur, Abhishek and Boor, Peter and Zand, Ramin and Abedi, Vida},
title = {Evaluating and Mitigating Carbon Dioxide Equivalent Emissions in Stroke Management: A Modeling Study},
journal = {Journal of the American Heart Association},
year = {2026},
volume = {15},
number = {13},
doi = {10.1161/jaha.125.047556}
}
EUVIMED