Abstract
Cardiovascular diseases are the most common causes of death around the world. To detect and treat heart-related diseases, continuous blood pressure (BP) monitoring along with many other parameters are required. Several invasive and non-invasive methods have been developed for this purpose. Most existing methods used in hospitals for continuous monitoring of BP are invasive. On the contrary, cuff-based BP monitoring methods, which can predict systolic blood pressure (SBP) and diastolic blood pressure (DBP), cannot be used for continuous monitoring. Several studies attempted to predict BP from non-invasively collectible signals such as photoplethysmograms (PPG) and electrocardiograms (ECG), which can be used for continuous monitoring. In this study, we explored the applicability of autoencoders in predicting BP from PPG and ECG signals. The investigation was carried out on 12,000 instances of 942 patients of the MIMIC-II dataset, and it was found that a very shallow, one-dimensional autoencoder can extract the relevant features to predict the SBP and DBP with state-of-the-art performance on a very large dataset. An independent test set from a portion of the MIMIC-II dataset provided a mean absolute error (MAE) of 2.333 and 0.713 for SBP and DBP, respectively. On an external dataset of 40 subjects, the model trained on the MIMIC-II dataset provided an MAE of 2.728 and 1.166 for SBP and DBP, respectively. For both the cases, the results met British Hypertension Society (BHS) Grade A and surpassed the studies from the current literature.
Highlights
blood pressure (BP) Prediction from PPG-to-PPG Feature Mapping: Apart from the primary approach of this study which aimed at mapping PPG and ECG features to arterial blood pressure (ABP) features for BP
14 ofin23 creased as the depth of the encoder increased. Based on this direct correlation, we can conclude that as the encoder became deeper, it increasingly looked into complex features of the signals and the network became lesser efficient in capturing peripheral features as systolic blood pressure (SBP) and diastolic blood pressure (DBP)
Histograms of mean absolute error (MAE) for SBP and DBP predictions for all of them are provided in Supplementary Figure S2
Summary
Despite tremendous advancements in the healthcare sector, cardiovascular diseases (CVDs) still secured the top positions last year in the list of leading causes of death globally. The most fatal CVD was Ischaemic Heart Disease which is termed by the World Health. Organization (WHO) as the “world’s biggest killer” as it accounted for 16% of the total deaths from 2000 to 2019 [1]. The second, third, and fourth positions were secured by stroke, chronic pulmonary diseases and lower respiratory infections, respectively which are directly and indirectly, related to CVDs [2,3,4]. Hypertension or high blood pressure (BP) is one of the leading causes of CVDs: Almost 54% of strokes and 47% of coronary heart diseases, worldwide, can be attributed to high BP [5].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
