2021 Fiscal Year Final Research Report
Wide-band ECoG analysis for establishing epilepsy detection and prediction system based on ECG algorithm
| Project/Area Number |
19K09475
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 56010:Neurosurgery-related
|
|---|
| Research Institution | Tokyo Medical and Dental University |
|---|
Principal Investigator |
MAEHARA TAKETOSHI 東京医科歯科大学, 大学院医歯学総合研究科, 教授 (40211560)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
藤原 幸一 名古屋大学, 工学研究科, 准教授 (10642514)
|
|---|
| Project Period (FY) |
2019-04-01 – 2022-03-31
|
| Keywords | てんかん発作予知 / 心拍変動（HRV）解析 / 頭蓋内電極 / 部分てんかん / 広帯域脳波解析 / Autoencoder (AE) モデル / 定位的頭蓋内脳波 |
|---|
| Outline of Final Research Achievements |
We have proposed an epileptic seizure prediction method using a machine learning anomaly detection technique based on heart rate variability (HRV) during long-term scalp electroencephalogram (EEG) recordings. However, mechanism of epilepsy prediction system using HRV is unclear. In this study, we confirmed usefulness of this system and tried to disclose the mechanism in patients underwent intracranial electrocorticogram (ECoG) recordings. Between May 2019 and January 2022, 11 patients underwent 12 times intracranial ECoG recordings for detection of epileptic focus. Epilepsy prediction rate is 78% and the number of false-positive prediction is 1.42 times/hr, that were almost same as those of EEG recording. These results suggested that HRV change is preceded before epileptic seizures. We also found that electrical seizure without clinical manifestation is predicted by HRV analysis. Therefore, we need to pay attention the possibility that false-negative prediction might be a true seizure.
|
| Free Research Field |
脳神経外科
|
| Academic Significance and Societal Importance of the Research Achievements |
てんかんは全人口の1%が罹患する疾患で日本だけでも約30万人の患者はてんかん発作が制御できずに苦しんでいるのが実情である。我々は心拍変動を解析しててんかん発作を予知し、臨床発作の消失、軽減を行うシステム開発に取り組んできた。今回、頭蓋内電極を用いた解析を行い、心拍変動はてんかん発作以前に起こることを証明した。また頭皮脳波で偽陽性とされた場合にも頭蓋内脳波では臨床症状を伴わない電気的発作である可能性も示唆された。今回の検討で心拍変動によるてんかん発作の機序が一部解明されたことは、本システムの臨床応用につながり、てんかん患者に対する非侵襲的な発作予知への道を開くものと考えられた。
|
