AUTHOR=Fang Xi , Liu Hong-Yun , Wang Zhi-Yan , Yang Zhao , Cheng Tung-Yang , Hu Chun-Hua , Hao Hong-Wei , Meng Fan-Gang , Guan Yu-Guang , Ma Yan-Shan , Liang Shu-Li , Lin Jiu-Luan , Zhao Ming-Ming , Li Lu-Ming
TITLE=Preoperative Heart Rate Variability During Sleep Predicts Vagus Nerve Stimulation Outcome Better in Patients With Drug-Resistant Epilepsy
JOURNAL=Frontiers in Neurology
VOLUME=12
YEAR=2021
URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2021.691328
DOI=10.3389/fneur.2021.691328
ISSN=1664-2295
ABSTRACT=Objective: Vagus nerve stimulation (VNS) is an adjunctive and well-established treatment for patients with drug-resistant epilepsy (DRE). However, it is still difficult to identify patients who may benefit from VNS surgery. Our study aims to propose a VNS outcome prediction model based on machine learning with multidimensional preoperative heart rate variability (HRV) indices.
Methods: The preoperative electrocardiography (ECG) of 59 patients with DRE and of 50 healthy controls were analyzed. Responders were defined as having at least 50% average monthly seizure frequency reduction at 1-year follow-up. Time domain, frequency domain, and non-linear indices of HRV were compared between 30 responders and 29 non-responders in awake and sleep states, respectively. For feature selection, univariate filter and recursive feature elimination (RFE) algorithms were performed to assess the importance of different HRV indices to VNS outcome prediction and improve the classification performance. Random forest (RF) was used to train the classifier, and leave-one-out (LOO) cross-validation was performed to evaluate the prediction model.
Results: Among 52 HRV indices, 49 showed significant differences between DRE patients and healthy controls. In sleep state, 35 HRV indices of responders were significantly higher than those of non-responders, while 16 of them showed the same differences in awake state. Low-frequency power (LF) ranked first in the importance ranking results by univariate filter and RFE methods, respectively. With HRV indices in sleep state, our model achieved 74.6% accuracy, 80% precision, 70.6% recall, and 75% F1 for VNS outcome prediction, which was better than the optimal performance in awake state (65.3% accuracy, 66.4% precision, 70.5% recall, and 68.4% F1).
Significance: With the ECG during sleep state and machine learning techniques, the statistical model based on preoperative HRV could achieve a better performance of VNS outcome prediction and, therefore, help patients who are not suitable for VNS to avoid the high cost of surgery and possible risks of long-term stimulation.