An approach for a continuous non-invasive blood pressure monitoring with Imaging Photoplethysmography using Long Short-Term Memory (LSTM) Neural Networks. The proposed solution uses the exceptional ability of LSTM neural network to process sequential data, which makes it particularly suitable for time series analysis inherent in PPG signals. Using LSTM networks, we can effectively capture the temporal dependencies and subtle nuances within the PPG data, which are indicative of systolic and diastolic blood pressure fluctuations.
Ваннус М. (науч. рук. Волынский М.А.) Long Short-Term Memory (LSTM) Neural Networks for Cuffless Blood Pressure Monitoring with Imaging Photoplethysmography // Сборник тезисов докладов конгресса молодых ученых. Электронное издание. – СПб: Университет ИТМО, [2024]. URL: https://kmu.itmo.ru/digests/article/13294