Non-invasive blood pressure estimation combining deep neural networks with pre-training and partial fine-tuning

Photoplethysmography-based cuffless blood pressure estimation: an image encoding and fusion approach

Objective.Photoplethysmography (PPG) is a promising wearable technology that detects volumetric changes in microcirculation using a light source and a sensor on the skin's surface. PPG has been shown to be useful for non-invasive blood pressure (BP) measurement. Deep learning-based BP measurements are now gaining popularity. However, almost all methods focus on 1D PPG. We aimed to design an end-to-end approach for estimating BP using image encodings from a 2D perspective.Approach.In this paper, we present a BP estimation approach based on an image encoding and fusion (BP-IEF) technique. We convert the PPG into five image encodings and use them as input. The proposed BP-IEF consists of two parts: an encoder and a decoder. In addition, three kinds of well-known neural networks are taken as the fundamental architecture of the encoder. The decoder is a hybrid architecture that consists of convolutional and fully connected layers, which are used to fuse features from the encoder.Main results.The performance of the proposed BP-IEF is evaluated on the UCI database in both non-mixed and mixed manners. On the non-mixed dataset, the root mean square error and mean absolute error for systolic BP (SBP) are 13.031 mmHg and 9.187 mmHg respectively, while for diastolic BP (DBP) they are 5.049 mmHg and 3.810 mmHg. On the mixed dataset, the corresponding values for SBP are 4.623 mmHg and 3.058 mmHg, while for DBP the values are 2.350 mmHg and 1.608 mmHg. In addition, both SBP and DBP estimation on the mixed dataset achieved grade A compared to the British Hypertension Society standard. The DBP estimation on the non-mixed dataset also achieved grade A.Significance.The results indicate that the proposed approach has the potential to improve on the current mobile healthcare for cuffless BP measurement.

Analysis of the Chaotic Component of Photoplethysmography and Its Association with Hemodynamic Parameters

Wearable technologies face challenges due to signal instability, hindering their usage. Thus, it is crucial to comprehend the connection between dynamic patterns in photoplethysmography (PPG) signals and cardiovascular health. In our study, we collected 401 multimodal recordings from two public databases, evaluating hemodynamic conditions like blood pressure (BP), cardiac output (CO), vascular compliance (C), and peripheral resistance (R). Using irregular-resampling auto-spectral analysis (IRASA), we quantified chaotic components in PPG signals and employed different methods to measure the fractal dimension (FD) and entropy. Our findings revealed that in surgery patients, the power of chaotic components increased with vascular stiffness. As the intensity of CO fluctuations increased, there was a notable strengthening in the correlation between most complexity measures of PPG and these parameters. Interestingly, some conventional morphological features displayed a significant decrease in correlation, indicating a shift from a static to dynamic scenario. Healthy subjects exhibited a higher percentage of chaotic components, and the correlation between complexity measures and hemodynamics in this group tended to be more pronounced. Causal analysis showed that hemodynamic fluctuations are main influencers for FD changes, with observed feedback in most cases. In conclusion, understanding chaotic patterns in PPG signals is vital for assessing cardiovascular health, especially in individuals with unstable hemodynamics or during ambulatory testing. These insights can help overcome the challenges faced by wearable technologies and enhance their usage in real-world scenarios.

Temporal complexity in photoplethysmography and its influence on blood pressure

Objective: The temporal complexity of photoplethysmography (PPG) provides valuable information about blood pressure (BP). In this study, we aim to interpret the stochastic PPG patterns with a model-based simulation, which may help optimize the BP estimation algorithms. Methods: The classic four-element Windkessel model is adapted in this study to incorporate BP-dependent compliance profiles. Simulations are performed to generate PPG responses to pulse and continuous stimuli at various timescales, aiming to mimic sudden or gradual hemodynamic changes observed in real-life scenarios. To quantify the temporal complexity of PPG, we utilize the Higuchi fractal dimension (HFD) and autocorrelation function (ACF). These measures provide insights into the intricate temporal patterns exhibited by PPG. To validate the simulation results, continuous recordings of BP, PPG, and stroke volume from 40 healthy subjects were used. Results: Pulse simulations showed that central vascular compliance variation during a cardiac cycle, peripheral resistance, and cardiac output (CO) collectively contributed to the time delay, amplitude overshoot, and phase shift of PPG responses. Continuous simulations showed that the PPG complexity could be generated by random stimuli, which were subsequently influenced by the autocorrelation patterns of the stimuli. Importantly, the relationship between complexity and hemodynamics as predicted by our model aligned well with the experimental analysis. HFD and ACF had significant contributions to BP, displaying stability even in the presence of high CO fluctuations. In contrast, morphological features exhibited reduced contribution in unstable hemodynamic conditions. Conclusion: Temporal complexity patterns are essential to single-site PPG-based BP estimation. Understanding the physiological implications of these patterns can aid in the development of algorithms with clear interpretability and optimal structures.