The Analysis of Diabetes Clinical Information Using Data-mining Techniques
| Project/Area Number |
16615006
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
臨床疫学
|
|---|
| Research Institution | Tokyo Women's Medical University |
|---|
Principal Investigator |
SAKURA Hiroshi Tokyo Women's Medical University, Lecturer, 医学部, 講師 (70240710)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KANNO Hiroko Tokyo Women's Medical University, Assistant Professor, 医学部, 助手 (90338971)
MURAYAMA Satoko Tokyo Women's Medical University, Assistant Professor, 医学部, 助手 (60318061)
UTO Yuko Tokyo Women's Medical University, Assistant Professor, 医学部, 助手 (60349652)
IWAMOTO Yasuhiko Tokyo Women's Medical University, Professor, 医学部, 教授 (60143434)
|
|---|
| Project Period (FY) |
2004 – 2005
|
| Project Status |
Completed (Fiscal Year 2005)
|
| Budget Amount *help |
¥3,700,000 (Direct Cost: ¥3,700,000)
Fiscal Year 2005: ¥1,600,000 (Direct Cost: ¥1,600,000)
Fiscal Year 2004: ¥2,100,000 (Direct Cost: ¥2,100,000)
|
|---|
| Keywords | Data-mining / Database / Datamart / Diabetes Mellitus / Medical Information / Oral hypoglycemic Agents / Glycemic Control |
|---|
| Research Abstract |
We have integrated the clinical information such as clinical history, physical examinations and laboratory data into a hospital-based datamart for the analysis of clinical course of diabetes mellitus. The number of total records put in the datamart was more than 6 million, and using the structured query language (SQL), we could easily extract the necessary data.
In this study, we analyzed the factors which predict glycemic control 6 months after the admission to the inpatient clinic using data-mining methods (association rules and decision-tree methods). Duration of diabetes, total number of admission, treatment of diabetes were associated with poor glycemic control. These results were consistent with those analyzed by conventional statistical methods.
Data-mining techniques will become very powerful methods, because computer-system could induce various type of working hypotheses.
|
Report
(3 results)
Research Products
(27 results)
-
-
-
-
-
-
-
-
-
-
-
-
[Journal Article] 「研究成果報告書概要(欧文)」より2005
Author(s)
Tanaka K, Sakura H, Maruyama S, Kanno H, Uto Y, Fujikawa M, Haruki T, Tanaka Y, Iwamoto Y
-
Journal Title
Diabetes (Japanese) 48 (suppl 2)
Related Report
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
