| Project/Area Number |
23590629
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Medical sociology
|
|---|
| Research Institution | Kansai Medical University |
|---|
Principal Investigator |
WATANABE Jun 関西医科大学, 医学部, 准教授 (40148557)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
|
|---|
| Keywords | 医療情報学 / 診療記録 / 意思決定 / 展開予測 / バスケット分析 / APML / 自然言語処理 / 非構造化データ / 社会医学 / 情報セキュリティ / 意志決定 / 行動予測 / 道筋解析 / 暗黙知 / 形式知 / 自然文解析 / 診療チーム |
|---|
| Research Abstract |
To establish a suitable method for determining intendment formed between a medical care team staff and predict the subsequent behavior, we examined the suitability of the association (basket) analysis and the attention profiling mark-up language for this purpose by exposing hidden or implicit relationship from medical records. Comparison with medical plan written in assessment and the actual records of treatments, predictive value was improved by the exposure of implicit knowledge and information using the association analysis (from around 40% to 60 to 70%). Since the importance of the accuracy of natural language processing has been found, we thus developed and introduced a method for syntactic analysis by a combination of the dependency parsing and the syntactic tree analysis. This procedure allowed us to figure out the decision-making process and the subsequent behavior of the team at a certain level (about 80%).
|
