2023 Fiscal Year Final Research Report
Determining the timing of delivery based on analysis of cardiotocogram using artificial intelligence
| Project/Area Number |
20K18233
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 56040:Obstetrics and gynecology-related
|
|---|
| Research Institution | Juntendo University |
|---|
Principal Investigator |
Takeda Jun 順天堂大学, 医学部, 准教授 (60813459)
|
|---|
| Project Period (FY) |
2020-04-01 – 2024-03-31
|
| Keywords | 人工知能 / 機械学習 |
|---|
| Outline of Final Research Achievements |
We created an algorithm to interpret four types of decelerations in accordance with the definitions of obstetrics and gynecology guidelines. However, because late deceleration could not be detected due to the small amount of change, an algorithm was created using a probability dencity. To evaluate the accuracy of the algorithm, we compared the interpretations of the algorithm, an certified obstetrician, and an obstetrics resident using 20 cases of CTG immediately before delivery, using the interpretation of the perinatologist as the absolute standard. The algorithm had the highest positive predictive value of the three for localizing transient bradycardia at 64.1%.
|
| Free Research Field |
周産期
|
| Academic Significance and Societal Importance of the Research Achievements |
経験の少ない臨床医がアルゴリズムによるCTGの機械判読の助けを得ることで、従来では認識に至らなかった少しの変化しかない一過性徐脈を認知することが可能となり、安全な分娩管理を遂行することが可能となりえる。それにより、年間500例程度発生している脳性麻痺症例のうち、分娩管理が不十分であったものが回避できる可能性があり、患者、患者家族はもちろんのこと、社会経済的にも大きな意義がある。また、このアルゴリズムは本邦約2000箇所とされる産科において広く適用できる可能性があることから、本研究成果の意義は大きい。
|
