Generalized deep neural network model for cuffless blood pressure estimation with photoplethysmogram signal only

Yan Cheng Hsu, Yung Hui Li, Ching Chun Chang, Latifa Nabila Harfiya

Research output: Contribution to journalArticlepeer-review

45 Scopus citations


Due to the growing public awareness of cardiovascular disease (CVD), blood pressure (BP) estimation models have been developed based on physiological parameters extracted from both electrocardiograms (ECGs) and photoplethysmograms (PPGs). Still, in order to enhance the usability as well as reduce the sensor cost, researchers endeavor to establish a generalized BP estimation model using only PPG signals. In this paper, we propose a deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation. The effectiveness and accuracy of our proposed model was evaluated by the root mean square error (RMSE), mean absolute error (MAE), the Association for the Advancement of Medical Instrumentation (AAMI) standard and the British Hypertension Society (BHS) standard. Experimental results showed that the RMSEs in systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 4.643 mmHg and 3.307 mmHg, respectively, across 9000 subjects, with 80.63% of absolute errors among estimated SBP records lower than 5 mmHg and 90.19% of absolute errors among estimated DBP records lower than 5 mmHg. We demonstrated that our proposed model has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works.

Original languageEnglish
Article number5668
Pages (from-to)1-18
Number of pages18
JournalSensors (Switzerland)
Issue number19
StatePublished - 1 Oct 2020


  • Artificial neural network
  • Cardiovascular disease (CVD) prevention
  • Photoplethysmogram (PPG), cuffless blood pressure (BP) estimation
  • Wearable biomedical applications


Dive into the research topics of 'Generalized deep neural network model for cuffless blood pressure estimation with photoplethysmogram signal only'. Together they form a unique fingerprint.

Cite this