Jamal Esmaelpoor1, Mohammad Hassan Moradi2, Abdolrahim Kadkhodamohammadi3. 1. Amirkabir University of Technology, Tehran, Iran. Electronic address: JEsmaelpoor@aut.ac.ir. 2. Amirkabir University of Technology, Tehran, Iran. 3. Digital Surgery Ltd, London, United Kingdom.
Abstract
OBJECTIVE: Easy access bio-signals are useful to alleviate the shortcomings and difficulties of cuff-based and invasive blood pressure (BP) measuring techniques. This study proposes a multistage model based on deep neural networks to estimate systolic and diastolic blood pressures using the photoplethysmogram (PPG) signal. METHODS: The proposed model consists of two key ingredients, using two successive stages. The first stage includes two convolutional neural networks (CNN) to extract morphological features from each PPG segment and then to estimate systolic and diastolic BPs separately. The second stage relies on long short-term memory (LSTM) to capture temporal dependencies. Further, the method incorporates the dynamic relationship between systolic and diastolic BPs to improve accuracy. RESULTS: The proposed multistage model was evaluated on 200 subjects using the standards of the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The results revealed that our model performance met the requirements of the AAMI standard. Also, according to the BHS standard, it achieved grade A in estimating both systolic and diastolic BPs. The mean and standard deviation of error for systolic and diastolic blood pressure estimations were +1.91±5.55mmHg and +0.67±2.84mmHg, respectively. CONCLUSION: Our results highlight the benefits of the proposed model in terms of appropriate feature extraction as well as estimation consistency.
OBJECTIVE: Easy access bio-signals are useful to alleviate the shortcomings and difficulties of cuff-based and invasive blood pressure (BP) measuring techniques. This study proposes a multistage model based on deep neural networks to estimate systolic and diastolic blood pressures using the photoplethysmogram (PPG) signal. METHODS: The proposed model consists of two key ingredients, using two successive stages. The first stage includes two convolutional neural networks (CNN) to extract morphological features from each PPG segment and then to estimate systolic and diastolic BPs separately. The second stage relies on long short-term memory (LSTM) to capture temporal dependencies. Further, the method incorporates the dynamic relationship between systolic and diastolic BPs to improve accuracy. RESULTS: The proposed multistage model was evaluated on 200 subjects using the standards of the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI). The results revealed that our model performance met the requirements of the AAMI standard. Also, according to the BHS standard, it achieved grade A in estimating both systolic and diastolic BPs. The mean and standard deviation of error for systolic and diastolic blood pressure estimations were +1.91±5.55mmHg and +0.67±2.84mmHg, respectively. CONCLUSION: Our results highlight the benefits of the proposed model in terms of appropriate feature extraction as well as estimation consistency.
Authors: Majid Nour; Derya Kandaz; Muhammed Kursad Ucar; Kemal Polat; Adi Alhudhaif Journal: Comput Math Methods Med Date: 2022-07-19 Impact factor: 2.809
Authors: Peter H Charlton; Birutė Paliakaitė; Kristjan Pilt; Martin Bachler; Serena Zanelli; Dániel Kulin; John Allen; Magid Hallab; Elisabetta Bianchini; Christopher C Mayer; Dimitrios Terentes-Printzios; Verena Dittrich; Bernhard Hametner; Dave Veerasingam; Dejan Žikić; Vaidotas Marozas Journal: Am J Physiol Heart Circ Physiol Date: 2021-12-24 Impact factor: 4.733