Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability
A warning prior to seizure onset can help improve the quality of life for epilepsy patients. The feasibility of a wearable system for predicting epileptic seizures using anomaly detection based on machine learning is evaluated. An original telemeter is developed for continuous measurement of R-R int...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/14/3987 |
| _version_ | 1797562224070361088 |
|---|---|
| author | Toshitaka Yamakawa Miho Miyajima Koichi Fujiwara Manabu Kano Yoko Suzuki Yutaka Watanabe Satsuki Watanabe Tohru Hoshida Motoki Inaji Taketoshi Maehara |
| author_facet | Toshitaka Yamakawa Miho Miyajima Koichi Fujiwara Manabu Kano Yoko Suzuki Yutaka Watanabe Satsuki Watanabe Tohru Hoshida Motoki Inaji Taketoshi Maehara |
| author_sort | Toshitaka Yamakawa |
| collection | DOAJ |
| description | A warning prior to seizure onset can help improve the quality of life for epilepsy patients. The feasibility of a wearable system for predicting epileptic seizures using anomaly detection based on machine learning is evaluated. An original telemeter is developed for continuous measurement of R-R intervals derived from an electrocardiogram. A bespoke smartphone app calculates the indices of heart rate variability in real time from the R-R intervals, and the indices are monitored using multivariate statistical process control by the smartphone app. The proposed system was evaluated on seven epilepsy patients. The accuracy and reliability of the R-R interval measurement, which was examined in comparison with the reference electrocardiogram, showed sufficient performance for heart rate variability analysis. The results obtained using the proposed system were compared with those obtained using the existing video and electroencephalogram assessments; it was noted that the proposed method has a sensitivity of 85.7% in detecting heart rate variability change prior to seizures. The false positive rate of 0.62 times/h was not significantly different from the healthy controls. The prediction performance and practical advantages of portability and real-time operation are demonstrated in this study. |
| first_indexed | 2024-03-10T18:25:11Z |
| format | Article |
| id | doaj.art-ec3d80e4324642cbbe1c9431955c706e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T18:25:11Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ec3d80e4324642cbbe1c9431955c706e2023-11-20T07:07:28ZengMDPI AGSensors1424-82202020-07-012014398710.3390/s20143987Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate VariabilityToshitaka Yamakawa0Miho Miyajima1Koichi Fujiwara2Manabu Kano3Yoko Suzuki4Yutaka Watanabe5Satsuki Watanabe6Tohru Hoshida7Motoki Inaji8Taketoshi Maehara9Division of Informatics and Energy, Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto 860-8555, JapanSection of Liaison Psychiatry and Palliative Medicine, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo 113-8510, JapanGraduate School of Engineering, Nagoya University, Nagoya 464-8603, JapanGraduate School of Informatics, Kyoto University, Kyoto 606-8501, JapanSection of Liaison Psychiatry and Palliative Medicine, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo 113-8510, JapanAmekudai Hospital, Naha 900-0005, JapanDepartment of Psychiatry, National Center Hospital of Neurology and Psychiatry, Kodaira 187-8553, JapanNational Hospital Organization Nara Medical Center, Nara 619-1124, JapanDepartment of Neurosurgery, Tokyo Medical and Dental University, Tokyo 113-8510, JapanDepartment of Neurosurgery, Tokyo Medical and Dental University, Tokyo 113-8510, JapanA warning prior to seizure onset can help improve the quality of life for epilepsy patients. The feasibility of a wearable system for predicting epileptic seizures using anomaly detection based on machine learning is evaluated. An original telemeter is developed for continuous measurement of R-R intervals derived from an electrocardiogram. A bespoke smartphone app calculates the indices of heart rate variability in real time from the R-R intervals, and the indices are monitored using multivariate statistical process control by the smartphone app. The proposed system was evaluated on seven epilepsy patients. The accuracy and reliability of the R-R interval measurement, which was examined in comparison with the reference electrocardiogram, showed sufficient performance for heart rate variability analysis. The results obtained using the proposed system were compared with those obtained using the existing video and electroencephalogram assessments; it was noted that the proposed method has a sensitivity of 85.7% in detecting heart rate variability change prior to seizures. The false positive rate of 0.62 times/h was not significantly different from the healthy controls. The prediction performance and practical advantages of portability and real-time operation are demonstrated in this study.https://www.mdpi.com/1424-8220/20/14/3987epilepsyelectrocardiographyheart rate variabilitymultivariate statistical process controlwearable systemmachine learning |
| spellingShingle | Toshitaka Yamakawa Miho Miyajima Koichi Fujiwara Manabu Kano Yoko Suzuki Yutaka Watanabe Satsuki Watanabe Tohru Hoshida Motoki Inaji Taketoshi Maehara Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability Sensors epilepsy electrocardiography heart rate variability multivariate statistical process control wearable system machine learning |
| title | Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability |
| title_full | Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability |
| title_fullStr | Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability |
| title_full_unstemmed | Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability |
| title_short | Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability |
| title_sort | wearable epileptic seizure prediction system with machine learning based anomaly detection of heart rate variability |
| topic | epilepsy electrocardiography heart rate variability multivariate statistical process control wearable system machine learning |
| url | https://www.mdpi.com/1424-8220/20/14/3987 |
| work_keys_str_mv | AT toshitakayamakawa wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT mihomiyajima wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT koichifujiwara wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT manabukano wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT yokosuzuki wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT yutakawatanabe wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT satsukiwatanabe wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT tohruhoshida wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT motokiinaji wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability AT taketoshimaehara wearableepilepticseizurepredictionsystemwithmachinelearningbasedanomalydetectionofheartratevariability |