Non-invasive arterial blood pressure measurement and SpO2 estimation using PPG signal: a deep learning framework

Preserving shape details of pulse signals for video-based blood pressure estimation

In recent years, imaging photoplethysmograph (iPPG) pulse signals have been widely used in the research of non-contact blood pressure (BP) estimation, in which BP estimation based on pulse features is the main research direction. Pulse features are directly related to the shape of pulse signals while iPPG pulse signals are easily disturbed during the extraction process. To mitigate the impact of pulse feature distortion on BP estimation, it is necessary to eliminate interference while retaining valuable shape details in the iPPG pulse signal. Contact photoplethysmograph (cPPG) pulse signals measured at rest can be considered as the undisturbed reference signal. Transforming the iPPG pulse signal to the corresponding cPPG pulse signal is a method to ensure the effectiveness of shape details. However, achieving the required shape accuracy through direct transformation from iPPG to the corresponding cPPG pulse signals is challenging. We propose a method to mitigate this challenge by replacing the reference signal with an average cardiac cycle (ACC) signal, which can approximately represent the shape information of all cardiac cycles in a short time. A neural network using multi-scale convolution and self-attention mechanisms is developed for this transformation. Our method demonstrates a significant improvement in the maximal information coefficient (MIC) between pulse features and BP values, indicating a stronger correlation. Moreover, pulse signals transformed by our method exhibit enhanced performance in BP estimation using different model types. Experiments are conducted on a real-world database with 491 subjects in the hospital, averaging 60 years of age.

ACNN-BiLSTM: A Deep Learning Approach for Continuous Noninvasive Blood Pressure Measurement Using Multi-Wavelength PPG Fusion

As an essential physiological indicator within the human body, noninvasive continuous blood pressure (BP) measurement is critical in the prevention and treatment of cardiovascular disease. However, traditional methods of blood pressure prediction using a single-wavelength Photoplethysmographic (PPG) have bottlenecks in further improving BP prediction accuracy, which limits their development in clinical application and dissemination. To this end, this study proposed a method to fuse a four-wavelength PPG and a BP prediction model based on the attention mechanism of a convolutional neural network and bidirectional long- and short-term memory (ACNN-BiLSTM). The effectiveness of a multi-wavelength PPG fusion method for blood pressure prediction was evaluated by processing PPG signals from 162 volunteers. The study compared the performance of the PPG signals with different individual wavelengths and using a multi-wavelength PPG fusion method in blood pressure prediction, assessed using mean absolute error (MAE), root mean squared error (RMSE) and AAMI-related criteria. The experimental results showed that the ACNN-BiLSTM model achieved a better MAE ± RMSE for a systolic BP and diastolic BP of 1.67 ± 5.28 and 1.15 ± 2.53 mmHg, respectively, when using the multi-wavelength PPG fusion method. As a result, the ACNN-BiLSTM blood pressure model based on multi-wavelength PPG fusion could be considered a promising method for noninvasive continuous BP measurement.

Towards Non-Invasive and Continuous Blood Pressure Monitoring in Neonatal Intensive Care Using Artificial Intelligence: A Narrative Review

Preterm birth is a live birth that occurs before 37 completed weeks of pregnancy. Approximately 11% of babies are born preterm annually worldwide. Blood pressure (BP) monitoring is essential for managing the haemodynamic stability of preterm infants and impacts outcomes. However, current methods have many limitations associated, including invasive measurement, inaccuracies, and infection risk. In this narrative review, we find that artificial intelligence (AI) is a promising tool for the continuous measurement of BP in a neonatal cohort, based on data obtained from non-invasive sensors. Our findings highlight key sensing technologies, AI techniques, and model assessment metrics for BP sensing in the neonatal cohort. Moreover, our findings show that non-invasive BP monitoring leveraging AI has shown promise in adult cohorts but has not been broadly explored for neonatal cohorts. We conclude that there is a significant research opportunity in developing an innovative approach to provide a non-invasive alternative to existing continuous BP monitoring methods, which has the potential to improve outcomes for premature babies.

Comparative Analysis of Perfusion Index and End-Tidal Carbon Dioxide in Cardiac Arrest Patients: Implications for Hemodynamic Monitoring and Resuscitation Outcomes

BACKGROUND

During cardiopulmonary resuscitation (CPR), some parameters (e.g., intraarterial pressure measurement and end-tidal carbon dioxide (EtCO2)) indicate the quality and outcome of resuscitation. These parameters are generally based on monitoring the hemodynamic status. Perfusion index (PI) is a calculation from the photoplethysmography (PPG) signal and displays the proportion of pulsatile to non-pulsatile light absorption or reflection in the PPG signal. It helps to evaluate cardiac output and tissue perfusion in the care of a critical patient. Its most important advantages are that it can be easily measured with a pulse oximeter probe attached to the finger (non-invasive), can be objectively repeated, can be applied quickly, and is inexpensive. Normal PI values range from 0.2% to 20%. Despite being recognized as a valuable indicator of hemodynamics, there is limited information regarding its relevance in patients experiencing cardiac arrest. Although the PI is known to be a valuable parameter to indicate hemodynamics, information about its value in cardiac arrest patients is limited. This study aims to evaluate the performance of PI and EtCO2 in predicting the return of spontaneous circulation (ROSC) among cardiac arrest patients.

METHODS

This was a single-center, prospective, observational clinical study including both out-of-hospital and in-hospital adult cardiac arrest patients. The study was conducted from November 1, 2018 to April 30, 2019 at the Emergency Department (ED) of the Hacettepe University Hospital, Ankara, Turkey. The EtCO2 values of the patients were recorded at the time they were intubated (t0) and every five minutes (t5, t10, t15...) during CPR. Along with these measurements, PI values were measured with the Masimo Signal Extraction Technology device (Masimo, California, United States). The study's primary outcome was PI's performance in predicting the ROSC among cardiac arrest patients. The secondary outcomes of the study were the performance of EtCO2 in predicting the ROSC among cardiac arrest patients and the association between PI and EtCO2 values.

RESULTS

We included a total of 100 cases. The mean age of patients was 70.4 ± 13.4 years, and 65% were male. The ROSC was achieved in 29 patients. There was no statistical difference in PI values between the ROSC (+) and ROSC (-) groups at any minute. However, in the ROSC (+) group, EtCO2 values were observed to be high starting from the fifth minute (t5, p=0.010; t10, p<0.001; t15, p=0.014; t20, p=0.033; t25, p=0.003, respectively). There was no correlation between the PI and EtCO2 values at 0, 5, 10, 15, 20, and 25 minutes (t0, p=0.436; t5, p=0.154; t10, p=0.557; t15, p=0.740; t20 p=0.241; t25 p=0.201, respectively).

CONCLUSION

Measuring PI values during resuscitation in intubated cardiac arrest patients does not help clinicians predict the outcome. In addition, no correlation was found with EtCO2 values. However, EtCO2 values remained high in patients with the ROSC from the fifth minute onward. Further larger-scale studies are needed regarding the optimal use of PI in cardiac arrest patients.

Patent and Bibliometric Analysis of the Scientific Landscape of the Use of Pulse Oximeters and Their Prospects in the Field of Digital Medicine

This study conducted a comprehensive patent and bibliometric analysis to elucidate the evolving scientific landscape surrounding the development and application of pulse oximeters, including in the field of digital medicine. Utilizing data from the Lens database for the period of 2000-2023, we identified the United States, China, the Republic of Korea, Japan, Canada, Australia, Taiwan, and the United Kingdom as the predominant countries in patent issuance for pulse oximeter technology. Our bibliometric analysis revealed a consistent temporal trend in both the volume of publications and citations, underscoring the growing importance of pulse oximeters in digitally-enabled medical practice. Using the VOSviewer software(version 1.6.18), we discerned six primary research clusters: (1) measurement accuracy; (2) integration with the Internet of Things; (3) applicability across diverse pathologies; (4) telemedicine and mobile applications; (5) artificial intelligence and deep learning; and (6) utilization in anesthesiology, resuscitation, and intensive care departments. The findings of this study indicate the prospects for leveraging digital technologies in the use of pulse oximetry in various fields of medicine, with implications for advancing the understanding, diagnosis, prevention, and treatment of cardio-respiratory pathologies. The conducted patent and bibliometric analysis allowed the identification of technical solutions to reduce the risks associated with pulse oximetry: improving precision and validity, technically improved clinical diagnostic use, and the use of machine learning.