| Project/Area Number |
26460868
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Medical and hospital managemen
|
|---|
| Research Institution | Kagoshima University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
村永 文学 鹿児島大学, 医歯学域附属病院, 講師 (00325812)
宇都 由美子 鹿児島大学, 医歯学域医学系, 准教授 (50223582)
岩穴口 孝 鹿児島大学, 医歯学域附属病院, 助教 (80619198)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2014: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
|
|---|
| Keywords | 病院データウェアハウス / 医療コスト分析 / データマイニング / ニューラルネットワーク / クラスタ分析 / アソシエーション分析 / 医療ビッグデータ / データウェアハウス / コスト分析 / アプリオリアルゴリズム |
|---|
| Outline of Final Research Achievements |
The purpose of this study was to construct a DWH for medical cost analysis by DPC, and to evaluate a method suitable for finding a factor affecting medical cost by using data mining technique. We analyzed 365 cases of initial hospitalization and initial treatment of hepatocellular carcinoma from 2011 to 2015. As a result, in clustering by the k - mean method, it was found that only the number of hospital days is related to cost. With regard to the cost analysis, which is a high cost, only machine learning by a neural network could be analyzed. We divide the data into 274 cases for machine learning and 91 cases for evaluation, and in the machine learning model, we judged from expenditure items for evaluation whether or not the cost becomes high. As a result, it was possible to judge from cost item name to high cost with accuracy of 80% or more.
|
