RESUMEN
The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.
Asunto(s)
Electroencefalografía , Redes Neurales de la Computación , Electroencefalografía/métodos , Procesamiento de Señales Asistido por Computador , Benchmarking , Diseño Interior y MobiliarioRESUMEN
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.
Asunto(s)
Algoritmos , Aprendizaje Profundo , Electrocardiografía , Procesamiento de Señales Asistido por Computador , Humanos , Electrocardiografía/métodos , Dispositivos Electrónicos Vestibles , Adulto , Oído/fisiologíaRESUMEN
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.
Asunto(s)
Racismo , Pigmentación de la Piel , Humanos , Melaninas , Oximetría/métodos , OxígenoRESUMEN
This work aims to classify physiological states using heart rate variability (HRV) features extracted from electrocardiograms recorded in the ears (ear-ECG). The physiological states considered in this work are: (a) normal breathing, (b) controlled slow breathing, and (c) mental exercises. Since both (b) and (c) cause higher variance in heartbeat intervals, breathing-related features (SpO2 and mean breathing interval) from the ear Photoplethysmogram (ear-PPG) are used to facilitate classification. This work: 1) proposes a scheme that, after initialization, automatically extracts R-peaks from low signal-to-noise ratio ear-ECG; 2) verifies the feasibility of extracting meaningful HRV features from ear-ECG; 3) quantitatively compares several ear-ECG sites; and 4) discusses the benefits of combining ear-ECG and ear-PPG features.
Asunto(s)
Oído , Fotopletismografía , Frecuencia Cardíaca/fisiología , Respiración , ElectrocardiografíaRESUMEN
At present, a medium-level microcontroller is capable of performing edge computing and can handle the computation of neural network kernel functions. This makes it possible to implement a complete end-to-end solution incorporating signal acquisition, digital signal processing, and machine learning for the classification of cardiac arrhythmias on a small wearable device. In this work, we describe the design and implementation of several classifiers for atrial fibrillation detection on a general-purpose ARM Cortex-M4 microcontroller. We used the CMSIS-DSP library, which supports Naïve Bayes and Support Vector Machine classifiers, with different kernel functions. We also developed Python scripts to automatically transfer the Python model (trained in Scikit-learn) to the C environment. To train and evaluate the models, we used part of the data from the PhysioNet/Computing in Cardiology Challenge 2020 and performed simple classification of atrial fibrillation based on heart-rate irregularity. The performance of the classifiers was tested on a general-purpose ARM Cortex-M4 microcontroller (STM32WB55RG). Our study reveals that among the tested classifiers, the SVM classifier with RBF kernel function achieves the highest accuracy of 96.9%, sensitivity of 98.4%, and specificity of 95.8%. The execution time of this classifier was 720 µs per recording. We also discuss the advantages of moving computing tasks to edge devices, including increased power efficiency of the system, improved patient data privacy and security, and reduced overall system operation costs. In addition, we highlight a problem with false-positive detection and unclear significance of device-detected atrial fibrillation.
Asunto(s)
Fibrilación Atrial , Humanos , Fibrilación Atrial/diagnóstico , Teorema de Bayes , Algoritmos , Frecuencia Cardíaca , Redes Neurales de la ComputaciónRESUMEN
Depression diagnosis is a challenging clinical task currently conducted mostly using subjective criteria. It is well known that depression alters the neural activity in the brain, so that the corresponding neurophysiological signature may be measured using non-invasive electroencephalography (EEG) signals. These, in turn, may be possible to decode using machine learning algorithms. Despite the extensive literature, the existing techniques rely on several channels and obtrusive systems. In this paper, and for the first time, the diagnostic power of each EEG channel for depression detection is analyzed using Neighborhood Component Analysis (NCA). Our results indicate that a mere two features collected from one EEG channel suffice for reliable diagnosis. To evaluate the performance of the proposed method, a dataset comprising seven minutes of EEG recording from 84 subjects is used. The data was divided into two separate sets, one for feature selection and one for diagnostic classification. We delineate brain regions that have the strongest discriminative power linked to depression diagnosis. Thus, we identified one electrode (i.e., AF4) located on the frontal lobe, which can be used to diagnose depression with high accuracy. After evaluation of a series of shallow machine learning methods, we achieved the classification accuracy of 80.8%, sensitivity of 60% and specificity of 99.7% with two features from one electrode. We also achieved the highest classification accuracy of 91.8%, the specificity of 93.5%, and sensitivity of 90% with two electrodes and three features. Our findings show that it is possible to significantly reduce the complexity of algorithms to diagnose depression with the motivation of use in highly accessible wearable devices.