2023 Fiscal Year Final Research Report
Statistical Inference Based on Real-World-Data
| Project/Area Number |
19H04072
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 60030:Statistical science-related
|
|---|
| Research Institution | Waseda University (2023)
Yokohama City University (2019-2022) |
|---|
Principal Investigator |
Wang Jinfang 早稲田大学, 国際学術院, 教授 (10270414)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
田栗 正隆 東京医科大学, 医学部, 主任教授 (20587589)
橋口 陽子 (小野陽子) 横浜市立大学, データサイエンス学部, 准教授 (60339140)
|
|---|
| Project Period (FY) |
2019-04-01 – 2024-03-31
|
| Keywords | Bayesian inference / Real-World-Data / Cell Regression / Data-Driven Prior / Real-World-Data / Machine Learning / Diabetes |
|---|
| Outline of Final Research Achievements |
In this study, we developed advanced statistical analysis and machine learning techniques utilizing real-world data. We conducted various empirical studies, particularly in the fields of health science and medicine, to verify the effectiveness of the proposed methods. Specifically, we integrated different data sources to develop accurate statistical methods using Bayesian regression models, constructed prediction models for Covid-19 positive cases using deep learning, and developed blood glucose prediction models using statistical and machine learning algorithms. Additionally, we also proposed personalized management methods to improve individual health conditions and confirmed their effectiveness through simulations and empirical studies. The research findings have been compiled into papers, books, and conference presentations, and we plan to release widely usable computational programs in the near future.
|
| Free Research Field |
統計学
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は、リアルワールドデータを活用して高度な統計解析および機械学習手法を開発し、データサイエンスにおける新たな理論の提唱と、健康科学や医療分野の発展に貢献を果たしました。学術的には、異なる形式のデータを統合する手法の提案や、統計的推論と機械学習を組み合わせた個別管理のための新たな理論的枠組みを提示しました。これにより、膨大で多様なリアルワールドデータの効果的な活用方法を提供し、また極めて社会的意義の大きい個人の健康管理や疾患予防における実践的なアプローチをもたらす可能性を示しました。
|
