| Project/Area Number |
17H06644
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Fundamental nursing
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
Araki Daichi 東京大学, 大学院医学系研究科(医学部), 客員研究員 (10799787)
|
|---|
| Project Period (FY) |
2017-08-25 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 転倒・転落 / 離床センサ / 動作分類 / 機械学習 / 予測 / 看護理工学 / 離床予測 |
|---|
| Outline of Final Research Achievements |
The purpose of this research is to develop a new algorithm for bed departure detection and movement classification, and prevent falling from the bed by capturing patient movement predictively. The main task in the period was the development of an algorithm for motion classification. After obtaining data about motion on the bed using the pressure sensor, we examined the discriminability of motion by performing machine learning. As a result of calculating classification accuracy that it shows 77.5% in SVM and 80.5% in Random Forest by cross-validation using machine learning for 9 kinds of postures and motions. Although adaptation has been confirmed as a stage of capturing postures and motions classification for detecting signs of getting up, it will be necessary to study for finer motion classification in the future.
|
| Academic Significance and Societal Importance of the Research Achievements |
転倒・転落に伴う外傷が患者に与える影響は大きく、長期臥床へと繋がり、QOL・ADLの低下へと至ることが報告されている。予防策としての離床感知センサが対象とするのは主にベッドを起点とした転落であるが、誤報や転落の危険性が少ないケースでの呼び出しも多く、患者側だけでなく、看護師の負荷増加および拘束感に対する看護師の葛藤が存在することも報告されている。本研究は、ベッド上での詳細な動作を分類することで、離床に繋がりやすい動作の同定や転落のリスクなどを判定するアルゴリズムを開発することで、新しい予防方法に関しての知見を導いている。
|
