From Scalp to Ear-EEG: A Generalizable Transfer Learning Model for Automatic Sleep Scoring in Older People.

OBJECTIVE: Sleep monitoring has extensively utilized electroencephalogram (EEG) data collected from the scalp, yielding very large data repositories and well-trained analysis models. Yet, this wealth of data is lacking for emerging, less intrusive modalities, such as ear-EEG. METHODS AND PROCEDURES: The current study seeks to harness the abundance of open-source scalp EEG datasets by applying models pre-trained on data, either directly or with minimal fine-tuning; this is achieved in the context of effective sleep analysis from ear-EEG data that was recorded using a single in-ear electrode, referenced to the ipsilateral mastoid, and developed in-house as described in our previous work. Unlike previous studies, our research uniquely focuses on an older cohort (17 subjects aged 65-83, mean age 71.8 years, some with health conditions), and employs LightGBM for transfer learning, diverging from previous deep learning approaches. RESULTS: Results show that the initial accuracy of the pre-trained model on ear-EEG was 70.1%, but fine-tuning the model with ear-EEG data improved its classification accuracy to 73.7%. The fine-tuned model exhibited a statistically significant improvement (p < 0.05, dependent t-test) for 10 out of the 13 participants, as reflected by an enhanced average Cohen's kappa score (a statistical measure of inter-rater agreement for categorical items) of 0.639, indicating a stronger agreement between automated and expert classifications of sleep stages. Comparative SHAP value analysis revealed a shift in feature importance for the N3 sleep stage, underscoring the effectiveness of the fine-tuning process. CONCLUSION: Our findings underscore the potential of fine-tuning pre-trained scalp EEG models on ear-EEG data to enhance classification accuracy, particularly within an older population and using feature-based methods for transfer learning. This approach presents a promising avenue for ear-EEG analysis in sleep studies, offering new insights into the applicability of transfer learning across different populations and computational techniques. CLINICAL IMPACT: An enhanced ear-EEG method could be pivotal in remote monitoring settings, allowing for continuous, non-invasive sleep quality assessment in elderly patients with conditions like dementia or sleep apnea.

Physically Meaningful Surrogate Data for COPD.

The rapidly increasing prevalence of debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), calls for a meaningful integration of artificial intelligence (AI) into respiratory healthcare. Deep learning techniques are "data hungry" whilst patient-based data is invariably expensive and time consuming to record. To this end, we introduce a novel COPD-simulator, a physical apparatus with an easy to replicate design which enables rapid and effective generation of a wide range of COPD-like data from healthy subjects, for enhanced training of deep learning frameworks. To ensure the faithfulness of our domain-aware COPD surrogates, the generated waveforms are examined through both flow waveforms and photoplethysmography (PPG) waveforms (as a proxy for intrathoracic pressure) in terms of duty cycle, sample entropy, FEV1/FVC ratios and flow-volume loops. The proposed simulator operates on healthy subjects and is able to generate FEV1/FVC obstruction ratios ranging from greater than 0.8 to less than 0.2, mirroring values that can observed in the full spectrum of real-world COPD. As a final stage of verification, a simple convolutional neural network is trained on surrogate data alone, and is used to accurately detect COPD in real-world patients. When training solely on surrogate data, and testing on real-world data, a comparison of true positive rate against false positive rate yields an area under the curve of 0.75, compared with 0.63 when training solely on real-world data.

The Deep-Match Framework: R-Peak Detection in Ear-ECG.

The Ear-ECG provides a continuous Lead I like electrocardiogram (ECG) by measuring the potential difference related to heart activity by electrodes which are embedded within earphones. However, the significant increase in wearability and comfort enabled by Ear-ECG is often accompanied by a degradation in signal quality - an obstacle that is shared by the majority of wearable technologies. We aim to resolve this issue by introducing a Deep Matched Filter (Deep-MF) for the highly accurate detection of R-peaks in wearable ECG, thus enhancing the utility of Ear-ECG in real-world scenarios. The Deep-MF consists of an encoder stage, partially initialised with an ECG template, and an R-peak classifier stage. Through its operation as a Matched Filter, the encoder searches for matches with an ECG template in the input signal, prior to filtering these matches with the subsequent convolutional layers and selecting peaks corresponding to the ground-truth ECG. The latent representation of R-peak information is then fed into a R-peak classifier, of which the output provides precise R-peak locations. The proposed Deep Matched Filter is evaluated using leave-one-subject-out cross-validation over 36 subjects with an age range of 18-75, with the Deep-MF outperforming existing algorithms for R-peak detection in noisy ECG. The Deep-MF achieves a median R-peak recall of 94.9% and a median precision of 91.2% across subjects when evaluated with leave-one-subject-out cross validation. Overall, this Deep-Match framework serves as a valuable step forward for the real-world functionality of Ear-ECG and, through its interpretable operation, the acceptance of deep learning models in e-Health.

Hearables: feasibility of recording cardiac rhythms from single in-ear locations.

The ear is well positioned to accommodate both brain and vital signs monitoring, via so-called hearable devices. Consequently, ear-based electroencephalography has recently garnered great interest. However, despite the considerable potential of hearable based cardiac monitoring, the biophysics and characteristic cardiac rhythm of ear-based electrocardiography (ECG) are not yet well understood. To this end, we map the cardiac potential on the ear through volume conductor modelling and measurements on multiple subjects. In addition, in order to demonstrate real-world feasibility of in-ear ECG, measurements are conducted throughout a long-time simulated driving task. As a means of evaluation, the correspondence between the cardiac rhythms obtained via the ear-based and standard Lead I measurements, with respect to the shape and timing of the cardiac rhythm, is verified through three measures of similarity: the Pearson correlation, and measures of amplitude and timing deviations. A high correspondence between the cardiac rhythms obtained via the ear-based and Lead I measurements is rigorously confirmed through agreement between simulation and measurement, while the real-world feasibility was conclusively demonstrated through efficacious cardiac rhythm monitoring during prolonged driving. This work opens new avenues for seamless, hearable-based cardiac monitoring that extends beyond heart rate detection to offer cardiac rhythm examination in the community.

Feasibility of Transfer Learning from Finger PPG to In-Ear PPG.

The success of deep learning methods has enabled many modern wearable health applications, but has also highlighted the critical caveat of their extremely data hungry nature. While the widely explored wrist and finger photoplethysmography (PPG) sites are less affected, given the large available databases, this issue is prohibitive to exploring the full potential of novel recording locations such as in-ear wearables. To this end, we assess the feasibility of transfer learning from finger PPG to in-ear PPG in the context of deep learning for respiratory monitoring. This is achieved by introducing an encoder-decoder framework which is set up to extract respiratory waveforms from PPG, whereby simultaneously recorded gold standard respiratory waveforms (capnography, impedance pneumography and air flow) are used as a training reference. Next, the data augmentation and training pipeline is examined for both training on finger PPG and the subsequent fine tuning on in-ear PPG. The results indicate that, through training on two large finger PPG data sets (95 subjects) and then retraining on our own small in-ear PPG data set (6 subjects), the model achieves lower and more consistent test error for the prediction of the respiratory waveforms, compared to training on the small in-ear data set alone. This conclusively demonstrates the feasibility of transfer learning from finger PPG to in-ear PPG, leading to better generalisation across a wide range of respiratory rates.

Reducing racial bias in SpO2 estimation: The effects of skin pigmentation.

Accurate pulse-oximeter readings are critical for clinical decisions, especially when arterial blood-gas tests - the gold standard for determining oxygen saturation levels - are not available, such as when determining COVID-19 severity. Several studies demonstrate that pulse oxygen saturation estimated from photoplethysmography (PPG) introduces a racial bias due to the more profound scattering of light in subjects with darker skin due to the increased presence of melanin. This leads to an overestimation of blood oxygen saturation in those with darker skin that is increased for low blood oxygen levels and can result in a patient not receiving potentially life-saving supplemental oxygen. This racial bias has been comprehensively studied in conventional finger pulse oximetry but in other less commonly used measurement sites, such as in-ear pulse oximetry, it remains unexplored. Different measurement sites can have thinner epidermis compared with the finger and lower exposure to sunlight (such as is the case with the ear canal), and we hypothesise that this could reduce the bias introduced by skin tone on pulse oximetry. To this end, we compute SpO2 in different body locations, during rest and breath-holds, and compare with the index finger. The study involves a participant pool covering 6-pigmentation categories from Fitzpatrick's Skin Pigmentation scale. These preliminary results indicate that locations characterized by cartilaginous highly vascularized tissues may be less prone to the influence of melanin and pigmentation in the estimation of SpO2, paving the way for the development of non-discriminatory pulse oximetry devices.

The 2023 wearable photoplethysmography roadmap.

Photoplethysmography is a key sensing technology which is used in wearable devices such as smartwatches and fitness trackers. Currently, photoplethysmography sensors are used to monitor physiological parameters including heart rate and heart rhythm, and to track activities like sleep and exercise. Yet, wearable photoplethysmography has potential to provide much more information on health and wellbeing, which could inform clinical decision making. This Roadmap outlines directions for research and development to realise the full potential of wearable photoplethysmography. Experts discuss key topics within the areas of sensor design, signal processing, clinical applications, and research directions. Their perspectives provide valuable guidance to researchers developing wearable photoplethysmography technology.

Tracking Cognitive Workload in Gaming with In-Ear [Formula: see text].

The feasibility of using in-ear [Formula: see text] to track cognitive workload induced by gaming is investigated. This is achieved by examining temporal variations in cognitive workload through the game Geometry Dash, with 250 trials across 7 subjects. The relationship between performance and cognitive load in Dark Souls III boss fights is also investigated followed by a comparison of the cognitive workload responses across three different genres of game. A robust decrease in in-ear [Formula: see text] is observed in response to cognitive workload induced by gaming, which is consistent with existing results from memory tasks. The results tentatively suggest that in-ear [Formula: see text] may be able to distinguish cognitive workload alone, whereas heart rate and breathing rate respond similarly to both cognitive workload and stress. This study demonstrates the feasibility of low cost wearable cognitive workload tracking in gaming with in-ear [Formula: see text], with applications to the play testing of games and biofeedback in games of the future.

Wearable In-Ear PPG: Detailed Respiratory Variations Enable Classification of COPD.

An ability to extract detailed spirometry-like breathing waveforms from wearable sensors promises to greatly improve respiratory health monitoring. Photoplethysmography (PPG) has been researched in depth for estimation of respiration rate, given that it varies with respiration through overall intensity, pulse amplitude and pulse interval. We compare and contrast the extraction of these three respiratory modes from both the ear canal and finger and show a marked improvement in the respiratory power for respiration induced intensity variations and pulse amplitude variations when recording from the ear canal. We next employ a data driven multi-scale method, noise assisted multivariate empirical mode decomposition (NA-MEMD), which allows for simultaneous analysis of all three respiratory modes to extract detailed respiratory waveforms from in-ear PPG. For rigour, we considered in-ear PPG recordings from healthy subjects, both older and young, patients with chronic obstructive pulmonary disease (COPD) and idiopathic pulmonary fibrosis (IPF) and healthy subjects with artificially obstructed breathing. Specific in-ear PPG waveform changes are observed for COPD, such as a decreased inspiratory duty cycle and an increased inspiratory magnitude, when compared with expiratory magnitude. These differences are used to classify COPD from healthy and IPF waveforms with a sensitivity of 87% and an overall accuracy of 92%. Our findings indicate the promise of in-ear PPG for COPD screening and unobtrusive respiratory monitoring in ambulatory scenarios and in consumer wearables.

Imaging With Therapeutic Acoustic Wavelets-Short Pulses Enable Acoustic Localization When Time of Arrival is Combined With Delay and Sum.

Passive acoustic mapping (PAM) is an algorithm that reconstructs the location of acoustic sources using an array of receivers. This technique can monitor therapeutic ultrasound procedures to confirm the spatial distribution and amount of microbubble activity induced. Current PAM algorithms have an excellent lateral resolution but have a poor axial resolution, making it difficult to distinguish acoustic sources within the ultrasound beams. With recent studies demonstrating that short-length and low-pressure pulses-acoustic wavelets-have the therapeutic function, we hypothesized that the axial resolution could be improved with a quasi-pulse-echo approach and that the resolution improvement would depend on the wavelet's pulse length. This article describes an algorithm that resolves acoustic sources axially using time of flight and laterally using delay-and-sum beamforming, which we named axial temporal position PAM (ATP-PAM). The algorithm accommodates a rapid short pulse (RaSP) sequence that can safely deliver drugs across the blood-brain barrier. We developed our algorithm with simulations (k-wave) and in vitro experiments for one-, two-, and five-cycle pulses, comparing our resolution against that of two current PAM algorithms. We then tested ATP-PAM in vivo and evaluated whether the reconstructed acoustic sources mapped to drug delivery within the brain. In simulations and in vitro, ATP-PAM had an improved resolution for all pulse lengths tested. In vivo, experiments in mice indicated that ATP-PAM could be used to target and monitor drug delivery into the brain. With acoustic wavelets and time of flight, ATP-PAM can locate acoustic sources with a vastly improved spatial resolution.

In-Ear SpO2: A Tool for Wearable, Unobtrusive Monitoring of Core Blood Oxygen Saturation.

The non-invasive estimation of blood oxygen saturation (SpO2) by pulse oximetry is of vital importance clinically, from the detection of sleep apnea to the recent ambulatory monitoring of hypoxemia in the delayed post-infective phase of COVID-19. In this proof of concept study, we set out to establish the feasibility of SpO2 measurement from the ear canal as a convenient site for long term monitoring, and perform a comprehensive comparison with the right index finger-the conventional clinical measurement site. During resting blood oxygen saturation estimation, we found a root mean square difference of 1.47% between the two measurement sites, with a mean difference of 0.23% higher SpO2 in the right ear canal. Using breath holds, we observe the known phenomena of time delay between central circulation and peripheral circulation with a mean delay between the ear and finger of 12.4 s across all subjects. Furthermore, we document the lower photoplethysmogram amplitude from the ear canal and suggest ways to mitigate this issue. In conjunction with the well-known robustness to temperature induced vasoconstriction, this makes conclusive evidence for in-ear SpO2 monitoring being both convenient and superior to conventional finger measurement for continuous non-intrusive monitoring in both clinical and everyday-life settings.

Scalable automatic sleep staging in the era of Big Data.

Numerous automatic sleep staging approaches have been proposed to provide an eHealth alternative to the current gold-standard - hypnogram scoring by human experts. However, a majority of such studies exploit data of limited scale, which compromises both the validation and the reproducibility and transferability of such automatic sleep staging systems in real clinical settings. In addition, the computational issues and physical meaningfulness of the analysis are typically neglected, yet affordable computation is a key criterion in Big Data analytics. To this end, we establish a comprehensive analysis framework to rigorously evaluate the feasibility of automatic sleep staging from multiple perspectives, including robustness with respect to the number of training subjects, model complexity, and different classifiers. This is achieved for a large collection of publicly accessible polysomnography (PSG) data, recorded over 515 subjects. The trade-off between affordable computation and satisfactory accuracy is shown to be fulfilled by an extreme learning machine (ELM) classifier, which in conjunction with the physically meaningful hidden Markov model (HMM) of the transition between the different sleep stages (smoothing model) is shown to achieve both fast computation and the highest average Cohen's kappa value of κ = 0.73 (Substantial Agreement). Finally, it is shown that for accurate and robust automatic sleep staging, a combination of structural complexity (multi-scale entropy) and frequency-domain (spectral edge frequency) features is both computationally affordable and physically meaningful.

A Transition Probability Based Classification Model for Enhanced N1 Sleep stage Identification During Automatic Sleep Stage Scoring.

Automatic sleep staging provides a cheaper, faster and more accessible alternative for evaluating sleep patterns and quality compared with manual hypnogram scoring performed by a clinician. Traditionally, classification methods treat sleep stages independently of their temporal order, despite sleep patterns themselves being highly sequential. Such independent sleep stage classification can result in poor sensitivity and precision, in particular when attempting to classify the sleep stage N1, otherwise known as the transition stage of sleep which links periods of wakefulness to periods of deep sleep. To this end, we propose a novel transition sleep classification method which aims to improve classification accuracy. This is achieved by utilising both the temporal information of previous stages and treating the transitions between stages as classes in their own right. Simulations on publicly available polysomnography (PSG) data and a comprehensive performance comparison with standard classifiers demonstrate a marked improvement achieved by the proposed method in both N1 sensitivity and precision across all considered classifiers. This includes an increase in N1 precision from 0.01% to 36.75% in an MLP classifier, and an increase in both accuracy and Cohen's kappa value in two of the three classifiers. Overall best mean performance is obtained by transition classification with a random forest classifier (RF) which achieved a kappa value of κ = 0.75 (substantial agreement), and an N1 stage precision of 58%.