| Project/Area Number |
17K15888
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
General internal medicine(including psychosomatic medicine)
|
|---|
| Research Institution | Chiba University |
|---|
Principal Investigator |
Noda Kazutaka 千葉大学, 医学部附属病院, 助教 (50456076)
|
|---|
| Project Period (FY) |
2017-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 診断推論 / ベイジアンネットワーク / 予測モデル / 病歴 / 電子カルテ / 人工知能 / 総合診療 |
|---|
| Outline of Final Research Achievements |
We compared the medical history information extracted from the medical record texts (extraction data) with those obtained by the comprehensive questionnaire (questionnaire sheet data). The medical record texts alone could not supply effective data for inference engine development based on medical history information. On the other hand, it is possible that the patient's own answer information to the comprehensive questionnaire can be supplied with data suitable for the purpose of diagnostic inference engine development based on medical history information. We constructed Bayesian networks using each of the extraction data and the questionnaire sheet data respectively. The former had many missing values and could not construct a useful network, but the latter had similar predictors as in the previous study and the possibility of extracting different probabilistic causality was shown.
|
| Academic Significance and Societal Importance of the Research Achievements |
診療録データでは病歴情報に基づく診断推論エンジンを開発するためのデータ量を確保できない可能性があり，その開発のためには医療面接で聴取される病歴情報を診療録データ以外に蓄積させる仕組み作りが重要であることを示唆する結果を得た。
|
