2022 Fiscal Year Final Research Report
Developing a method for resolving bottleneck in analyses of national databases
| Project/Area Number |
19K24222
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
0908:Society medicine, nursing, and related fields
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
Kume Keitaro 筑波大学, 医学医療系, 助教 (70853191)
|
|---|
| Project Period (FY) |
2019-08-30 – 2023-03-31
|
| Keywords | 医療データベース / プライバシー保護 / ビッグデータ / 匿名性 / 医療情報学 |
|---|
| Outline of Final Research Achievements |
National Database of Health Insurance Claims and Specific Health Checkups of Japan (NDB) is a very valuable database, but its full potential has not been utilized because of barrier of restricted and limited access to the data due to its importance of health or medical information privacy. To address this problem, we performed experiments for validation and evaluation of methods to protect sensitive data while preserving the utility of the data and tried to determine the suitable method. As a result, it was shown that methods that substituting the attribute value with more general values or eliminate data bias do not sufficiently maintain the usefulness of the data to ensure sufficient privacy protection, and that methods that add random noise may be promising. In addition, we developed a dummy NDB dataset for these experiments.
|
| Free Research Field |
医療情報学
|
| Academic Significance and Societal Importance of the Research Achievements |
レセプト情報・特定健診等情報データベース（ＮＤＢ）は、多大な価値を有する世界的にも類を見ないデータベースであるが、個人の医療情報という性質上データへのアクセス手段が限定されているというボトルネックが存在するため、その価値に対して利活用が十分には進んでいない。本研究は、プライバシーを保護しつつデータベースの有用性を残すための手法について何が適切なのかという情報を提供することでこれを解消し、社会へＮＤＢの成果を還元するための一端を担うことができると考えている。
|
