2018 Fiscal Year Final Research Report
Network analysis for prognostic factors of heart failure using longitudinal data from huge cohort data
| Project/Area Number |
16K00039
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | Tohoku University |
|---|
Principal Investigator |
Miyata Satoshi 東北大学, 医学系研究科, 准教授 (60360343)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
坂田 泰彦 東北大学, 医学系研究科, 准教授 (90379206)
|
|---|
| Research Collaborator |
Miura Masanobu
Yamauchi Takeshi
Onose Takeshi
Tsuji Kanako
Oikawa Takuya
Kasahara Shintaro
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Keywords | コホート研究 / ネットワーク解析 / 関数主成分分析 / 慢性心不全 / 生物統計学 |
|---|
| Outline of Final Research Achievements |
In the present study, the cohort data of the chronic heart failure of 10,219 patients registered from 2006 to 2010 in Chronic Heart Failure Analysis and Registry in the Tohoku District 2 (CHART-2 study) was used.
We developed functional component analysis using longitudinal data as functional data for risk stratification, which was treated as supervised learning model with survival data.
The implication of the results of the present study was clinically examined by the specialist of the cardiovascular internal medicine. It was confirmed that the patients were effectively classified according to the risk of the occurrence of the heart failure by the proposed methodology.
|
| Free Research Field |
生物統計学
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究の結果，膨大なコホートデータに蓄積された経時データを関数主成分分析によって解析することにより、心不全患者の発症リスクを効果的に判別することに成功した。
研究の成果は，約30編の原著論文（査読あり）と多数の国際学会において報告した．
|
