| Presentation | 2022-07-23 Pilot Study on Early Prediction of Sleep Apnea Based on Heart Rate Variability Time-Series Forecasting Muhammad Shaufil Adha, Tomohiko Igasaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A widely accepted alternative to address the continuous positive airway pressure adherence problem is the use of its automatic counterpart known as automatic positive airway pressure (APAP). Most APAP machines utilize the algorithmic apnea event detection or prediction strategies to initiate the appropriate therapies. The primary motivation for predicting apnea events is to provide intervention before clinical symptoms occur and improve therapeutic results and long-term patient tolerance to the device. The main objective of this study is to predict apnea state for various lead times by utilizing several physiological components extracted from a forecast heart rate variability time series. We further introduced a sequence of physiological components to mitigate the poor state prediction performance owing to the forecast error. Moreover, we adopted the long short-term memory sequence classification approach to automate the state prediction. Finally, we showed that the mean prediction performance in terms of sensitivity, specificity, accuracy, and combined objective for 1.4 min lead time is 85 ± 15%, 92 ± 11%, 93 ± 2%, and 90 ± 5%, respectively. We also demonstrated that the proposed approach could predict the occurrence of apnea for up to 5 min with a combined objective of 78%, which is the highest compared to previous works. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | heart rate variability / sleep apnea, / sleep-disordered breathing / time-series prediction / long short-term memory |
| Paper # | MBE2022-14 |
| Date of Issue | 2022-07-16 (MBE) |
| Conference Information | |
| Committee | MBE |
|---|---|
| Conference Date | 2022/7/23(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Junichi Hori(Niigata Univ.) |
| Vice Chair | Hisashi Yoshida(Kinki Univ.) |
| Secretary | Hisashi Yoshida(Setsunan Univ) |
| Assistant | Emi Yuda(Tohoku Univ) / Miki Kaneko(Osaka Univ.) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Pilot Study on Early Prediction of Sleep Apnea Based on Heart Rate Variability Time-Series Forecasting |
| Sub Title (in English) | |
| Keyword(1) | heart rate variability |
| Keyword(2) | sleep apnea, |
| Keyword(3) | sleep-disordered breathing |
| Keyword(4) | time-series prediction |
| Keyword(5) | long short-term memory |
| 1st Author's Name | Muhammad Shaufil Adha |
| 1st Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| 2nd Author's Name | Tomohiko Igasaki |
| 2nd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| Date | 2022-07-23 |
| Paper # | MBE2022-14 |
| Volume (vol) | vol.122 |
| Number (no) | MBE-130 |
| Page | pp.pp.9-12(MBE), |
| #Pages | 4 |
| Date of Issue | 2022-07-16 (MBE) |