| Project/Area Number |
22500432
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Medical systems
|
|---|
| Research Institution | Chiba University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
SUZUKI Takahiro 千葉大学, 医学部附属病院, 准教授 (40323422)
|
|---|
| Research Collaborator |
TU Bao・Ho 北陸先端科学技術大学院大学, 知識科学研究科, 教授 (60301199)
土井 俊祐 千葉大学, 医学部附属病院, 客員研究員 (90639072)
|
|---|
| Project Period (FY) |
2010 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2011: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2010: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 薬剤反応性 / 生体生命情報学 / 人口知能 / 危機管理 / 診療録 / 退院時サマリー / テキストマイニング / 副作用 / 薬疹 / 糖尿病 / 血小板減少 / 人工知能 / 肝障害 / データマイニング |
|---|
| Research Abstract |
We squeezed the adverse reaction cases from the pattern of laboratory data change in admitted patients. Then checked the drugs used before the change and calculated the occurrence related to the adverse reaction cases for each drug. By comparing the occurrence of the cases with expected occurrence rate of the drug combination, we selected the specific combinations. However, they were considered not as the new unknown combination but the bystanders with other drugs, or treated for provocation or therapy. We concluded that each case must be evaluated by human, though computers can choose the high possibility cases .The approach from text mining of discharge summary failed because of many false positive and false negative cases. For example, only 82.9% was described about drug eruption in the diagnosed cases as drug eruption. Thus we need the education of writing discharge summaries as well as the development of syntactic mining.
|
