| Project/Area Number |
16K20899
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Life / Health / Medical informatics
Obstetrics and gynecology
|
|---|
| Research Institution | Tohoku University |
|---|
Principal Investigator |
SATOSHI MIZUNO 東北大学, 東北メディカル・メガバンク機構, 助手 (80646795)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | バイオインフォマティクス / 機械学習 / フェノタイピング / 早期診断支援 / 深層学習 / 産科 / 妊娠高血圧症候群 / HDP / 情報学 / 生命情報学 / 産婦人科学 / 産科学 / 生命情報 / 人工知能 / 社会医学 / 医学情報学 |
|---|
| Outline of Final Research Achievements |
We considered the work-flow to develop supervised machine learning model for prediction of hypertensive disorders of pregnancy (HDP) with large-scale birth cohort dataset. To obtain class-label of supervised learning, we developed rule-based phenotyping algorithm according to clinical guidelines. The developed algorithm was applied into phenotyping of Birthree cohort subjects. We tried to develop the ML model to predict HDP with phenotyped disease types as class labels of supervised machine learning. In this study, we used Birthree cohort data before data-cleaning to develop the work-flow. In the future work, we will study with data after cleaning to develop precise informatics bases of HDP study in Birthree cohort study.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で検討を行った大規模出生コホートでの妊娠高血圧症候群のフェノタイピングアルゴリズムによる病型分類と、病型分類の結果を正解ラベルとした機械学習モデル構築のワークフローは、三世代コホート調査における妊娠高血圧症候群の研究の重要な情報リソースの一つとなりうる。
|
