Blood glucose level prediction from meal photos and behavior change by AR and nudge for avoiding postprandial hyperglycemia

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K19828
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 62:Applied informatics and related fields
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Yasumoto Keiichi 奈良先端科学技術大学院大学, 先端科学技術研究科, 教授 (40273396)
• Project Period (FY): 2021-07-09 – 2024-03-31
• Keywords: 血糖値予測 / 食事摂取量推薦 / 高血糖抑制 / ナッジ

Outline of Final Research Achievements

In this study, a method was developed to predict in advance how much blood glucose levels would increase with the meal about to be consumed, by constructing a blood glucose prediction model for each individual based on time-series data on blood glucose levels and dietary information. In addition, a method was designed to induce a way of eating that is less likely to raise blood glucose levels by means of nudges for each food served, and its effectiveness was investigated. A blood glucose prediction model was constructed and evaluated by collecting time-series data on blood glucose levels and data that were considered to influence blood glucose levels (dietary information, sleep information and physical information of the subjects) from 10 subjects, and the results showed that the RMSE (root mean square error) and MAE (mean absolute error) for the most accurate subjects were 10.68 and 7.71 in the most accurate subjects.

Free Research Field

ユビキタスコンピューティング

Academic Significance and Societal Importance of the Research Achievements

世界の糖尿病人口は2045 年までに約7億人に達すると予測されており、日本でも、糖尿病有病者と糖尿病予備軍は合計約2,200 万人と推計されている。90%を占めるII 型糖尿病の発症を予防するには、インスリンが分泌されても正常に働かない「食後高血糖」の状態になるのを避ける必要がある。本研究は、食後高血糖の状態を食事を摂取する前に高い精度で予測する技術、さらに、目の前の食事をどの程度食べても良いかを分かりやすく提示する技術を開発し、被験者実験によりその有用性を示した点で、学術的・社会的な意義がある。