2022 Fiscal Year Final Research Report
Development of new hemodynamic variables using machine learning.
Project/Area Number |
20K09296
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 55060:Emergency medicine-related
|
Research Institution | Nippon Medical School |
Principal Investigator |
|
Project Period (FY) |
2020-04-01 – 2023-03-31
|
Keywords | 経肺熱希釈法 |
Outline of Final Research Achievements |
Heart rate and its variability (HRV) are reported to be associated with the activity of the autonomic nervous system. Additionally, the relationship between heart rate variability and respiratory states, such as cardiac function, stroke volume, changes in vascular permeability, and pulmonary edema, has been suggested but not clearly understood. In this study, we aimed to develop a new circulatory and respiratory parameter model that can provide insights into novel pathophysiology, aid in treatment response prediction, and contribute to prognosis. We integrated clinical information, transpulmonary thermodilution curves, and heart rate variability data, utilizing machine learning and deep learning analysis. To facilitate data collection and integration of clinical information, we developed an application. We then validated our hypotheses using machine learning and other techniques. Our findings are currently being prepared for publication.
|
Free Research Field |
集中治療
|
Academic Significance and Societal Importance of the Research Achievements |
これまで申請者は、経肺熱希釈法循環動態モニターから算出される、心拍出量や心臓張末期容量、肺血管外水分量や肺血管透過性係数等の循環呼吸動態のパラメータの妥性研究を 多く行ってきた。また、心電図モニターから算出される心拍変動(Heart Rate Variability, HRV)は、自律神経系の活動も反映し、敗血症や外傷症例の転帰を予測し得ることも発表してきた。しかし、これら別モニターの相互関係や組み合わせによる病態生理学的意義や転 予後予測に関しては、明らかになっていなかった。本研究は、上記の2つの関連の可能性を明らかにした。
|