| Project/Area Number |
18K11438
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | Shimane University |
|---|
Principal Investigator |
Hirano Shoji 島根大学, 学術研究院医学・看護学系, 准教授 (60333506)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2020: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 時系列データマイニング / ファジイ状態区間 / 医療データ / 状態区間 / データマイニング |
|---|
| Outline of Final Research Achievements |
In this research, we have developed a time-series medical data mining method that can describe the temporal course of disease and treatment. In contrast to conventional mining methods based on interval relations, the proposed method introduces the concept of fuzzy ranged relations, allowing the extraction of frequent patterns that include abstract periods such as several weeks or a few days. Furthermore, experiments on a synthetic dataset demonstrated that the introduction of fuzziness allows for a single sequence to belong to multiple relations, making it possible to suppress the decrease of support values when we define many relations.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で開発した手法により，イベント発生に至るまでの患者病態・治療等の特徴的推移をMPTP(Minimal Predictive Temporal Pattern)として診療データベースから抽出することができ，背景理解，治療計画立案，アウトカム予測等への活用が期待される。また，プロセスマイニングの一手法として医療以外の様々な分野へも応用可能である。
|
