Repository logo
  • English
  • 中文
  • Log In
    New user? Click here to register.Have you forgotten your password?
Repository logo
    Communities & Collections
    Research Outputs
    Fundings & Projects
    People
    Organizations
    Statistics
  • English
  • 中文
  • Log In
    New user? Click here to register.Have you forgotten your password?
  1. Home
  2. .TMU Publications / 北醫出版品(教師升等著作 / 教學實踐 / 學位論文)
  3. .博碩士學位論文
  4. 113學年度
  5. 多模態生成式AI預測老年糖尿病患長期血糖及共病症的準確度: 前驅研究
 
  • Details
Options

多模態生成式AI預測老年糖尿病患長期血糖及共病症的準確度: 前驅研究

Other Title
Accuracy of Multimodal Generative AI in Predicting Long-Term Blood Glucose and Comorbidities in Elderly Diabetic Patients: A Pilot Study
Type
thesis
Date Issued
2025-06-20
Author(s)
林政宇
Advisor
張榮素
Subjects
系所名稱:保健營養學系碩士班
Publisher
保健營養學系碩士班
Description
學位別:碩士
口試委員:黃孟娟; 黃群耀; 張榮素
關鍵字:多模態生成式AI、自動化食物影像評估、臺灣中高齡糖尿病、營養照護
Abstract
隨著生成式人工智慧技術快速進展,而傳統飲食評估方法(如24小時回憶法、飲食日誌)有著耗時且易受主觀偏誤影響。因此,將生成式AI應用於糖尿病營養照護逐漸成為最新的趨勢。圖像飲食估法(IBDA)結合AI技術,可提升飲食紀錄的效率,其中多模態生成式AI(如ChatGPT)具備圖文整合能力,應用潛力廣泛。
本研究納入25位中高齡第2型糖尿病(T2DM)病患,進行為期12個月追蹤。收集血液生化指標與每週飲食影像資料。食物影像由營養專業相關人員與四種ChatGPT模型(客製化/非客製化,輸入/不輸入食物名稱)進行營養素估算,辨識的準確率會依照食物名稱及食物組別分別分析正確辨識比例、錯誤辨識比例及忽略的比例。比較多模態生成式AI估算結果與營養專業相關人員分析之差異性與一致性,並評估多模態生成式AI預測血糖變化及共病症風險之能力。
結果顯示,ChatGPT於食物分類辨識準確率達61%,食物名稱辨識約38%,與營養專業相關人員分析結果具中至高一致性。多模態生成式AI估算之營養素與血液生化值的變化呈顯著相關。結論上,多模態生成式AI有預測血糖變化及共病風險之潛力。
URI
https://203.71.86.71/handle/123456789/9498

Copyright Notice

● The digital content on this platform is part of the Taipei Medical University Institutional Repository, featuring various academic works and outputs from the institution. It offers free access to academic research and public education for non-commercial use.

● Please use the content appropriately and within legal boundaries to respect copyright owners' rights. For commercial use, please obtain prior authorization from the copyright owner. Users must not use TMUIR for any illegal purposes.

● By utilising the platform, users are deemed to have fully accepted and understood all the regulations set out in this statement, relevant laws of the Republic of China, all international internet regulations, and usage conventions.

● TMUIR is committed to protecting the interests of copyright owners. If you believe that any material on this website infringes copyright, please contact our staff at libirtmu@gmail.com, and we will remove the work from the repository.

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Cookie settings
  • Privacy policy
  • End User Agreement
  • Send Feedback