| Project/Area Number |
24590615
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Medical sociology
|
|---|
| Research Institution | Kochi University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
HATAKEYAMA Yutaka 高知大学, 教育研究部医療学系, 準教授 (00376956)
WATABE Teruaki 高知大学, 教育研究部医療学系, 講師 (90325415)
KATAOKA Hiromi 高知大学, 教育研究部医療学系, 助教 (80398049)
NAKAJIMA Noriaki 高知大学, 教育研究部医療学系, 助教 (00335928)
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2014: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2013: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2012: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | 病態推移予測 / 病院情報システム / 予防医学 / 病態予測 / 医療データ2次利用 / 糖尿病 / 病態予測モデル / 状態空間モデル / 粒子型フィルタ / 階層ベイズモデル / 数理生理学 / 電子化医療データ |
|---|
| Outline of Final Research Achievements |
Combining theoretical considerations and the data stored in the hospital information system, we tried to build a model to describe and predict the disease state transition such as lifestyle-related diseases. With this approach , we aimed at creation of dynamic patho-mechanics utilizing the data of the hospital information system.
The increase of the prediction error due to the presence of missing values in the actual clinical data, has been solved by using a particle filter, and enables long-term prediction process. Also, instead of estimating from the data alone, the application of hierarchical Bayesian model that incorporates the appropriate mathematical model has shown to be promising for transition prediction of the condition. Furthermore, even when the rapid prediction is required, we have shown examples of useful predictions from limited data. With these results, we have shown the possibility of a dynamic patho-mechanics utilizing the data of the hospital information system.
|
