Advanced waveform analysis of the photoplethysmogram signal using complementary signal processing techniques for the extraction of biomarkers of cardiovascular function

Introduction

Photoplethysmogram signals from wearable devices typically measure heart rate and blood oxygen saturation, but contain a wealth of additional information about the cardiovascular system. In this study, we compared two signal-processing techniques: fiducial point analysis and Symmetric Projection Attractor Reconstruction, on their ability to extract new cardiovascular information from a photoplethysmogram signal. The aim was to identify fiducial point analysis and Symmetric Projection Attractor Reconstruction indices that could classify photoplethysmogram signals, according to age, sex and physical activity.

Methods

Three datasets were used: an in-silico dataset of simulated photoplethysmogram waves for healthy male participants (25-75 years old); an in-vivo dataset containing 10-min photoplethysmogram recordings from 57 healthy subjects at rest (18-39 or > 70 years old; 53% female); and an in-vivo dataset containing photoplethysmogram recordings collected for 4 weeks from a single subject, in daily life. The best-performing indices from the in-silico study (5/48 fiducial point analysis and 6/49 Symmetric Projection Attractor Reconstruction) were applied to the in-vivo datasets.

Results

Key fiducial point analysis and Symmetric Projection Attractor Reconstruction indices, which showed the greatest differences between groups, were found to be consistent across datasets. These indices were related to systolic augmentation, diastolic peak positioning and prominence, and waveform variability. Both fiducial point analysis and Symmetric Projection Attractor Reconstruction techniques provided indices that supported the classification of age and physical activity, but not sex.

Conclusions

Both fiducial point analysis and Symmetric Projection Attractor Reconstruction techniques demonstrated utility in identifying cardiovascular differences between individuals and within an individual over time. Future research should investigate the potential utility of these techniques for extracting information on fitness and disease, to support healthcare-decision making.

The need for measurement science in digital pathology

Background

Pathology services experienced a surge in demand during the COVID-19 pandemic. Digitalisation of pathology workflows can help to increase throughput, yet many existing digitalisation solutions use non-standardised workflows captured in proprietary data formats and processed by black-box software, yielding data of varying quality. This study presents the views of a UK-led expert group on the barriers to adoption and the required input of measurement science to improve current practices in digital pathology.

Methods

With an aim to support the UK's efforts in digitalisation of pathology services, this study comprised: (1) a review of existing evidence, (2) an online survey of domain experts, and (3) a workshop with 42 representatives from healthcare, regulatory bodies, pharmaceutical industry, academia, equipment, and software manufacturers. The discussion topics included sample processing, data interoperability, image analysis, equipment calibration, and use of novel imaging modalities.

Findings

The lack of data interoperability within the digital pathology workflows hinders data lookup and navigation, according to 80% of attendees. All participants stressed the importance of integrating imaging and non-imaging data for diagnosis, while 80% saw data integration as a priority challenge. 90% identified the benefits of artificial intelligence and machine learning, but identified the need for training and sound performance metrics.Methods for calibration and providing traceability were seen as essential to establish harmonised, reproducible sample processing, and image acquisition pipelines. Vendor-neutral data standards were seen as a "must-have" for providing meaningful data for downstream analysis. Users and vendors need good practice guidance on evaluation of uncertainty, fitness-for-purpose, and reproducibility of artificial intelligence/machine learning tools. All of the above needs to be accompanied by an upskilling of the pathology workforce.

Conclusions

Digital pathology requires interoperable data formats, reproducible and comparable laboratory workflows, and trustworthy computer analysis software. Despite high interest in the use of novel imaging techniques and artificial intelligence tools, their adoption is slowed down by the lack of guidance and evaluation tools to assess the suitability of these techniques for specific clinical question. Measurement science expertise in uncertainty estimation, standardisation, reference materials, and calibration can help establishing reproducibility and comparability between laboratory procedures, yielding high quality data and providing higher confidence in diagnosis.

Robustness of convolutional neural networks to physiological electrocardiogram noise

The electrocardiogram (ECG) is a widespread diagnostic tool in healthcare and supports the diagnosis of cardiovascular disorders. Deep learning methods are a successful and popular technique to detect indications of disorders from an ECG signal. However, there are open questions around the robustness of these methods to various factors, including physiological ECG noise. In this study, we generate clean and noisy versions of an ECG dataset before applying symmetric projection attractor reconstruction (SPAR) and scalogram image transformations. A convolutional neural network is used to classify these image transforms. For the clean ECG dataset, F1 scores for SPAR attractor and scalogram transforms were 0.70 and 0.79, respectively. Scores decreased by less than 0.05 for the noisy ECG datasets. Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. However, when the network trained on the noisy data was used to classify the clean dataset, the decrease was less than 0.05. We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing supervised networks for ECG classification. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

A novel method to quantify arterial pulse waveform morphology: attractor reconstruction for physiologists and clinicians

Current arterial pulse monitoring systems capture data at high frequencies (100-1000 Hz). However, they typically report averaged or low frequency summary data such as heart rate and systolic, mean and diastolic blood pressure. In doing so, a potential wealth of information contained in the high-fidelity waveform data is discarded, data which has long been known to contain useful information on cardiovascular performance. Here we summarise a new mathematical method, attractor reconstruction, which enables the quantification of arterial waveform shape and variability in real-time. The method can handle long streams of non-stationary data and does not require preprocessing of the raw physiological data by the end user. Whilst the detailed mathematical proofs have been described elsewhere (Aston et al 2008 Physiol. Meas. 39), the authors were motivated to write a summary of the method and its potential utility for biomedical researchers, physiologists and clinician readers. Here we illustrate how this new method may supplement and potentially enhance the sensitivity of detecting cardiovascular disturbances, to aid with biomedical research and clinical decision making.