2019 Fiscal Year Final Research Report
Development of Nonlinear Regression Analyses for Personalized Medicine
| Project/Area Number |
15K00044
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | Wakayama Medical University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2020-03-31
|
| Keywords | 樹木構造接近法 / アンサンブル学習法 / 治療効果(treatment effect) / 生存時間解析 |
|---|
| Outline of Final Research Achievements |
In recent years, personalized medicine, in which optimal treatment is provided to each patient based on registry data or large clinical trials, has been attracting attention.Nonlinear regression methods with treatment × background factors or treatment × gene information interactions have been developed.In addition, statistical methods for predicting the treatment effect (the difference between new and existing treatments/drugs) have recently received much attention.In this study, we have developed a statistical method based on the tree model and its extension to achieve the above goals.
|
| Free Research Field |
医学統計学
|
| Academic Significance and Societal Importance of the Research Achievements |
この研究では，近年注目されている疾患レジストリ及び大規模臨床試験データに基づいて，治療効果を推定するための方法を開発した．このような方法は，治療効果モデル(treatment effect model)と呼ばれ，近年注目されている．一方で，医学においてニーズの高い，生存時間データにおける開発は発展途上である．本研究では，生存時間データに対する非線形回帰モデルに基づく治療効果推定の方法を開発した．これらを疾患レジストリデータに応用することで，複数の治療レジメンの中から最適な治療法をがん患者に届けることができる．
|
