Evaluating and Mitigating Carbon Dioxide Equivalent Emissions in Stroke Management: A Modeling Study
脳卒中管理における二酸化炭素相当排出量の評価と緩和：モデリング研究 (AI 翻訳)
Alireza Vafaei Sadr, Seyyed Sina Hejazian, Ajith Vemuri, Abhishek Thakur, Peter Boor, Ramin Zand, Vida Abedi
🤖 gxceed AI 要約
日本語
AIを活用した脳卒中画像診断の二酸化炭素相当（CO2eq）排出量を推定。米国データを用いたモデリングにより、Ideal AIシナリオで年間約1.6万トンのCO2eqを排出し、計算処理をクリーンエネルギー州に移すことで54.75%削減可能と示した。
English
This study estimates CO2 equivalent emissions from AI-assisted stroke imaging in the US. The Ideal AI scenario emits ~16,375 metric tons CO2eq/year, and relocating computation to cleaner-energy states reduces emissions by 54.75%, highlighting a carbon-aware mitigation strategy.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本でもAI画像診断の普及が進む中、AIのカーボンフットプリントは重要な論点。本研究の手法は、日本の医療機関におけるグリーンAI導入の参考となる。
In the global GX context
This work provides a robust methodology for quantifying AI's carbon footprint in clinical settings, directly relevant to global healthcare sustainability and carbon-aware computing practices.
👥 読者別の含意
🔬研究者:Novel integration of AI carbon footprint quantification with healthcare imaging workflows.
🏢実務担当者:Hospitals can adopt carbon-aware routing of AI computations to reduce environmental impact.
🏛政策担当者:Supports policies promoting green AI in healthcare and carbon-aware infrastructure.
📄 Abstract（原文）
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.
🔗 Provenance — このレコードを発見したソース
- crossref https://doi.org/10.1161/jaha.125.047556first seen 2026-07-16 07:27:01
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。