We investigate the use of audio-inspired features to characterize ECG-derived skin sympathetic nerve activity (SKNA). Building on concepts from audio signal processing, we designed a set of SKNA-optimized spectral and energy-related features tailored to the transient, burst-like nature of sympathetic activation. High-frequency ECG signals were recorded from 20 participants during rest and during cognitive stress induced by the Stroop Color and Word Test. Applied to this two-phase protocol, the proposed features captured consistent differences between baseline and stress, achieving robust classification performance using support vector machines with leave-one-subject-out cross-validation. Results demonstrate that audio-inspired features, when physiologically constrained, provide a powerful and interpretable representation of SKNA dynamics, highlighting their promise for noninvasive assessment of autonomic function.

Atrial fibrillation (AF) is the most common arrhythmia, increasing the risk of stroke, heart failure, and other cardiovascular complications. While AF detection algorithms perform well in identifying persistent AF, earlystage progression, such as paroxysmal AF (PAF), often goes undetected due to its sudden onset and short duration. However, undetected PAF can progress into sustained AF, increasing the risk of mortality and severe complications. Early prediction of AF offers an opportunity to reduce disease progression through preventive therapies, such as catecholamine-sparing agents or beta-blockers. In this study, we propose a lightweight deep learning model using only RR Intervals (RRIs), combining a Temporal Convolutional Network (TCN) for positional encoding with Mamba, a selective state space model, to enable early prediction of AF through efficient parallel sequence modeling. In subject-wise testing results, our model achieved a sensitivity of 0.908, specificity of 0.933, F1-score of 0.930, AUROC of 0.972, and AUPRC of 0.932. Additionally, our method demonstrates high computational efficiency, with only 73.5 thousand parameters and 38.3 MFLOPs, outperforming traditional Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) approaches in both accuracy and model compactness. Notably, the model can predict AF up to two hours in advance using just 30 minutes of input data, providing enough lead time for preventive interventions.

Most deep learning models of multiclass arrhythmia classification are tested on fingertip photoplethysmographic (PPG) data, which has higher signal-to-noise ratios compared to smartwatch-derived PPG, and the best reported sensitivity value for premature atrial/ventricular contraction (PAC/PVC) detection is only 75%. To improve upon PAC/PVC detection sensitivity while maintaining high AF detection, we use multi-modal data which incorporates 1D PPG, accelerometers, and heart rate data as the inputs to a computationally efficient 1D bi-directional Gated Recurrent Unit (1D-Bi-GRU) model to detect three arrhythmia classes. We used motion-artifact prone smartwatch PPG data from the NIH-funded Pulsewatch clinical trial. Our multimodal model tested on 72 subjects achieved an unprecedented 83% sensitivity for PAC/PVC detection while maintaining a high accuracy of 97.31% for AF detection. These results outperformed the best state-of-the-art model by 20.81% for PAC/PVC and 2.55% for AF detection even while our model was computationally more efficient (14 times lighter and 2.7 faster).

Accurate estimation of sleepiness levels is crucial for managing sleep-related health risks and preventing cognitive degradation that can lead to accidents in the workplace. However, using machine learning (ML) to estimate these levels from speech remains challenging, with reported weak correlations (<0.40) with ground-truth sleepiness levels. Developing effective ML models requires high-quality sleepiness data from noticeably sleepy individuals, but collecting such data through prolonged sleep deprivation is both risky and costly. We propose that acted (feigned) sleepy speech can effectively represent realistic sleepiness and be used to train ML models for estimating sleepiness levels and detecting sleepiness-associated cognitive performance degradation. Our study demonstrates that: (1) human listeners perceive acted sleepy speech as sleepier than both non-sleepy and genuinely sleepy speech, and (2) ML models trained on acted speech can accurately estimate sleepiness levels in individuals who have been awake for 25 hours, achieving a correlation of 0.54 with ground-truth sleepiness levels while using fewer samples. Furthermore, the acted sleepy speech-based ML model detects cognitive performance degradation (F1 score = 0.80) in sleep-deprived individuals, outperforming models trained on real sleepy speech (F1 score = 0.32). Our approach provides efficient, effective, and scalable solutions to not only update benchmarks but also enhance the capabilities of real-world AI applications, from voice assistants to AI agents, ultimately supporting human health, workplace safety, and daily tasks.

The sympathetic nervous system (SNS) is pivotal in cardiovascular regulation. Skin sympathetic nerve activity (SKNA), extracted from electrocardiogram (ECG), is an innovative noninvasive metric for assessing SNS, traditionally evaluated via electrodermal activity (EDA). Identifying sparse drivers—markers of neural discharge onsets in EDA or SKNA signals—enhances SNS analysis. We employed the SparsEDA algorithm to identify SKNA drivers and compared them with EDA phasic drivers derived from cvxEDA and SparsEDA algorithms. Our evaluation included burst detection performance and temporal features: stimulus-to-response time and recovery time. In a thermal grill pain experiment with sixteen subjects, each undergoing six SNS stimulations, we concurrently recorded EDA and SKNA signals. SKNA demonstrated superior performance with a 97% hit rate, 100% recovery rate, and minimal false alarms during control (0.20±0.77) and interstimulus periods (1.27±1.44). In contrast, EDA drivers had hit and recovery rates below 80% and 50%, respectively, and a higher number of false alarms during interstimulus times (SparsEDA: 11.36±5.24; cvxEDA: 10.00±5.88). SKNA drivers closely matched annotated labels, achieving a root mean square error (RMSE) of 0.42 s, outperforming SparsEDA (RMSE: 5.09 s) and cvxEDA (RMSE: 3.73 s) drivers. The SKNA recovery time averaged 5.59±2.44 seconds, closely aligning with the actual pain stimulus duration (∼5 s), whereas EDA recovery times were nearly three times longer. The superior accuracy of SKNA drivers may result from directly measuring nerve activity, unlike EDA signals influenced by sweat pore hydrodynamics. Therefore, SKNA, with its precise onset response and quicker recovery time, holds promise for diverse applications in SNS assessment.

This paper proposes an adjacent channel weight dependable recursive least square adaptive filter (ACWD-RLS) with variational mode decomposition (VMD) based artifact removal mechanism in separating the fetal ECG (FECG) components from the pregnant mother abdominal ECG (AECG). This approach requires the two abdominal, and a single thorax ECG to extract the FECG component present in the AECG. The algorithm uses three independent VMD decomposition algorithms in which one decomposes the thorax ECG while the other two decompose the abdominal ECGs of adjacent channels. The presence of baseline wander (BW) and powerline interference (PLI) is detected and eliminated from the modes obtained from each VMD algorithm. The work also proposes an ACWD-RLS filter that contains two sections of the RLS filter namely the main section and secondary section, where the weight update in the main section depends on the weight estimated in the secondary section. The performance of the VMD-based artifact removal algorithm in suppressing the BW and PLI artifacts was evaluated utilizing the MIT-BIH arrhythmia and MIT-BIH noise stress dataset, while the Synthetic dataset of Physionet and real-world Daisy dataset was utilized in the validation of the proposed ACWD-RLS approach in fetal ECG extraction. The proposed VMD-based BW and PLI artifact removal mechanism result in a correlation coefficient and output signal-to-noise ratio of 0.988 and 14.23 dB respectively with a signal to BW noise ratio of 5 dB. The evaluation results show that the algorithm yields a PDA of 95.54% and 97.96% in real-world Daisy and Synthetic datasets respectively.

Continuous monitoring of non-invasive skin sympathetic nerve activity (SKNA) holds promise for understanding the sympathetic nervous system (SNS) dynamics in various physiological and pathological conditions. However, muscle noise artifacts present a challenge in accurate SKNA analysis, particularly in real-life scenarios. This study proposes a deep convolutional neural network (CNN) approach to detect and remove muscle noise from SKNA recordings obtained via ECG electrodes. Twelve healthy participants underwent controlled experimental protocols involving cognitive stress induction and voluntary muscle movements, while collecting SKNA data. Power spectral analysis revealed significant muscle noise interference within the SKNA frequency band (500–1000 Hz). A 2D CNN model was trained on the spectrograms of the data segments to classify them into baseline, stress-induced SKNA, and muscle noise-contaminated periods, achieving an average accuracy of 89.85% across all subjects. Our findings underscore the importance of addressing muscle noise for accurate SKNA monitoring, advancing towards wearable SKNA sensors for real-world applications.

This study addresses the challenges of arrhythmia detection, including atrial fibrillation (AF), using continuously collected smartwatch photoplethysmography (PPG) data. We propose a novel application of the densely connected convolutional neural network (DenseNet) for AF detection using smartwatch PPG data with effective differentiation from premature atrial contractions (PACs) and premature ventricular contractions (PVCs). While smartwatches offer a convenient platform for continuous monitoring, current research often relies on controlled settings using fingertip PPG and struggles to differentiate AF from other arrhythmias, particularly PAC/PVC$s$. Unlike prior controlled-setting studies, our data collection includes 14 days of continuous smartwatch PPG data in real-world settings, which truly challenges the performance of arrhythmia classification algorithms. Notably, the proposed DenseNet model excelled at distinguishing AF (sensitivity: 0.950, specificity: 0.949), demonstrating promise for real-world continuous AF monitoring. The proposed DenseNet model also achieved high specificity (0.958) for the classification of PAC/PVCs despite the inherent difficulty in their identification from PPG data. These findings demonstrate the efficacy of DenseNet in accurately identifying AF and distinguishing it from other arrhythmias, highlighting its potential for widespread clinical application.

Sleepiness results in an increased susceptibility to workplace accidents due to reduced cognitive functioning. Early detection of signs of sleepiness is crucial for mitigating work-related risks. Establishing a comprehensive database of sleepiness data is fundamental for developing effective sleepiness identification models. However, obtaining data on realistic sleepiness proves challenging in practice. This study explores a more efficient approach to sleepiness simulation to address this challenge. In this paper, we hypothesize that actively inducing feelings of sleepiness can precipitate sleepiness. In our experiment, ten participants simulated sleepiness while listening to a speech delivered by a tired, sleep-deprived individual. We measured self-reported levels of sleepiness and two widely-used physiological biomarkers-electrodermal activity (EDA) and electrocardiogram (ECG) signals-during this induced state. Our results shed light on the potential of this sleepiness simulation approach, unveiling physiological markers linked to induced sleepiness. By introducing this innovative sleepiness simulation method, our research advances building large sleepy datasets, which contribute to the proactive identification of sleepiness-related risks in the workplace.

Pain is typically viewed as an internal perception that is difficult to objectively measure. Current methods attempt to quantify pain intensity using self-reported scores, but these are often subjective or difficult to administer. Three primary sensory nerve fibers carry pain and tactile information: AP- and Ad-flbers carrying short touch and acute pain, respectively, and C-fibers carrying dull prolonged pain. Electrodermal activity (EDA), previously shown to be highly sensitive to pain and stress responses, may allow us to distinguish these different pain signals to more fully express measured pain. In this work, we use machine learning to classify EDA responses associated with these fibers during sine wave transcutaneous electrical nerve stimulation. Using several derived EDA features, we are able to develop models that obtain high accuracy (>75%) of classification across all three fiber types in this multiclass classification task. The ability to measure fiber-specific activation may help greatly improve pain detection and treatment research.

Underwater recording of biosignals such as electrodermal activity has the potential to improve our current understanding of diving medicine. However, the deployment is currently limited by the required waterproofing of EDA electrodes. In this work, we showcase the development and verify our design of a new water-tolerant electrode for underwater EDA collection. In time, frequency, and time-frequency domains, our electrode design performs as well as or better than the standard Ag/AgCI electrodes, showing only a small baseline shift when submerged and produced signal differences no larger than those EDA collected at different sites on the same body. Further development is required to establish the longevity of our electrode and the usability in varied other real-world water environments.

A novel method for tracking the tidal volume (TV) from electrocardiogram (ECG) is presented. The method is based on the amplitude of ECG-derived respiration (EDR) signals. Three different morphology-based EDR signals and three different amplitude estimation methods have been studied, leading to a total of 9 amplitude-EDR (AEDR) signals per ECG channel. The potential of these AEDR signals to track the changes in TV was analyzed. These methods do not need a calibration process. In addition, a personalized-calibration approach for TV estimation is proposed, based on a linear model that uses all AEDR signals from a device. All methods have been validated with two different ECG devices: a commercial Holter monitor, and a custom-made wearable armband. The lowest errors for the personalized-calibration methods, compared to a reference TV, were -3.48% [-17.41% / 12.93%] (median [first quartile / third quartile]) for the Holter monitor, and 0.28% [-10.90% / 17.15%] for the armband. On the other hand, medians of correlations to the reference TV were higher than 0.8 for uncalibrated methods, while they were higher than 0.9 for personal-calibrated methods. These results suggest that TV changes can be tracked from ECG using either a conventional (Holter) setup, or our custom-made wearable armband. These results also suggest that the methods are not as reliable in applications that induce small changes in TV, but they can be potentially useful for detecting large changes in TV, such as sleep apnea/hypopnea and/or exacerbations of a chronic respiratory disease.

Recently, it has been shown that skin sympathetic nerve activity (SKNA) can be obtained using electrocardiogram (ECG) signals at a high sampling rate. More importantly, recent studies have demonstrated that SKNA can be used as a surrogate noninvasive measure for assessing the sympathetic nervous system (SNS) activity. The electrodermal activity (EDA), which is a measure of changes in skin conductance due to sympathetic innervation, has also been shown to be a noninvasive physiomarker of SNS. For example, EDA has successfully shown its sensitivity and classification accuracy in detecting sympathetic elevation due to pain and emotion arousals. Given these two distinct approaches to noninvasive assessment of SNS, we directly compared and evaluated the effectiveness of ECG-derived SKNA and EDA in assessing SNS activity. Moreover, we examined if there is a direct correlation between SKNA and EDA given that both measurements provide SNS information. To this end, nine participants were recruited for Valsalva maneuver (VM) and thermal grill pain tests, while simultaneously recording ECG and EDA. Four features were derived from each of the integral area of rectified SKNA (iSKNA) and the phasic component of EDA signals (EDAphasic): peak amplitude, average amplitude, energy, and standard deviation. We then calculated Fisher’s ratio and area under the receiver operating characteristic curve (AUROC) for each feature. Peak amplitude and standard deviation of iSKNA showed significant difference between baseline and post-stimulation. Standard deviation of iSKNA showed a higher Fisher’s ratio and AUROC than any other EDA and SKNA features. EDAphasicshowed a delay of 4+ seconds from the onset of the stimulation, compared to SKNA. Moreover, by applying a larger window to extract iSKNA, we obtained Pearson correlation coefficient value of 0.78±0.22 between iSKNA and EDAphasicin VM test. In conclusion, SKNA was a better discriminative measure than EDA in obtaining SNS information. In addition, EDA dynamics can be derived from SKNA with the latter providing better onset and endpoint of SNS dynamics than the former.

Sleep deprivation is known to impair cognitive performance and contribute to workplace accidents. Bio-signal-based sleepiness detection approaches, facilitated by mobile healthcare systems, have emerged as a promising tool for preventing such accidents. However, due to the wide-ranging effects of sleep deprivation on human physiology and the sympathetic nervous system, accurately determining sleepiness remains challenging. In this study, we hypothesize that speaking loudly could increase the sensitivity of electrothermal activity (EDA) to sleep deprivation, as EDA measures changes in sympathetic nervous system activity. To validate our hypothesis, twenty participants underwent 25 hours of prolonged wakefulness, during which they vocalized loudly and completed a cognitive performance test, 10-min Psychomotor Vigilance Test (PVT) to measure their prolonged reaction time. Two EDA measures retrieved in speaking versus PVT tasks were compared. As result, EDA obtained during the speaking activity exhibited a stronger group correlation of ~-0.96 and individual correlation of ~-0.53 with sleep deprived indicators (i.e., reaction time) compared to the EDA acquired during the PVT task. We found a feasibility of performance degradation can be predictive by capturing the activity of the sympathetic nervous system precisely during the speaking activity. Moreover, the study emphasizes the importance of speaking activity in investigating sleepiness detection approaches based on speech, which have gained significant attention in recent research.

Data visualization is critical to unraveling hidden information from complex and high-dimensional data. Interpretable visualization methods are critical, especially in the biology and medical fields, however, there are limited effective visualization methods for large genetic data. Current visualization methods are limited to lower-dimensional data and their performance suffers if there is missing data. In this study, we propose a literature-based visualization method to reduce high-dimensional data without compromising the dynamics of the single nucleotide polymorphisms (SNP) and textual interpretability. Our method is innovative because it is shown to (1) preserves both global and local structures of SNP while reducing the dimension of the data using literature text representations, and (2) enables interpretable visualizations using textual information. For performance evaluations, we examined the proposed approach to classify various classification categories including race, myocardial infarction event age groups, and sex using several machine learning models on the literature-derived SNP data. We used visualization approaches to examine clustering of data as well as quantitative performance metrics for the classification of the risk factors examined above. Our method outperformed all popular dimensionality reduction and visualization methods for both classification and visualization, and it is robust against missing and higher-dimensional data. Moreover, we found it feasible to incorporate both genetic and other risk information obtained from literature with our method.

The current method for assessing pain in clinical practice is subjective and relies on self-reported scales. An objective and accurate method of pain assessment is needed for physicians to prescribe the proper medication dosage, which could reduce addiction to opioids. Hence, many works have used electrodermal activity (EDA) as a suitable signal for detecting pain. Previous studies have used machine learning and deep learning to detect pain responses, but none have used a sequence-to-sequence deep learning approach to continuously detect acute pain from EDA signals, as well as accurate detection of pain onset. In this study, we evaluated deep learning models including 1-dimensional convolutional neural networks (1D-CNN), long short-term memory networks (LSTM), and three hybrid CNN-LSTM architectures for continuous pain detection using phasic EDA features. We used a database consisting of 36 healthy volunteers who underwent pain stimuli induced by a thermal grill. We extracted the phasic component, phasic drivers, and time-frequency spectrum of the phasic EDA (TFS-phEDA), which was found to be the most discerning physiomarker. The best model was a parallel hybrid architecture of a temporal convolutional neural network and a stacked bi-directional and uni-directional LSTM, which obtained a F1-score of 77.8% and was able to correctly detect pain in 15-second signals. The model was evaluated using 37 independent subjects from the BioVid Heat Pain Database and outperformed other approaches in recognizing higher pain levels compared to baseline with an accuracy of 91.5%. The results show the feasibility of continuous pain detection using deep learning and EDA.

Sepsis is defined by life-threatening organ dysfunction during infection and is one of the leading causes of critical illness. During sepsis, there is high risk that new-onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. As a result, computer aided automated and reliable detection of new-onset AF during sepsis is crucial, especially for the critically ill patients in the intensive care unit (ICU). In this paper, a novel automated and robust two-step algorithm to detect AF from ICU patients using electrocardiogram (ECG) signals is presented. First, several statistical parameters including root mean square of successive differences, Shannon entropy, and sample entropy were calculated from the heart rate for the screening of possible AF segments. Next, Poincaré plot-based features along with P-wave characteristics were used to reduce false positive detection of AF, caused by the premature atrial and ventricular beats. A subset of the Medical Information Mart for Intensive Care (MIMIC) III database containing 198 subjects was used in this study. During the training and validation phases, both the simple thresholding as well as machine learning classifiers achieved very high segment-wise AF classification performance. Finally, we tested the performance of our proposed algorithm using two independent test data sets and compared the performance with two state-of-the-art methods. The algorithm achieved an overall 100% sensitivity, 98% specificity, 98.99% accuracy, 98% positive predictive value, and 100% negative predictive value on the subject-wise AF detection, thus showing the efficacy of our proposed algorithm in critically ill sepsis patients. The annotations of the data have been made publicly available for other investigators.

In conditions of pressure and temperature associated with immersion in water, humans are more susceptible to severe stress, challenging the human physiological control systems. Reliable tools for the assessment of the stress underwater are needed. Electrodermal activity (EDA) is considered a promising alternative for the assessment of the level of stress in humans. EDA is a measure of the changes in conductance at the skin surface related to sweat production. In normal humidity conditions, EDA changes in response to stress in three main ways: the skin conductance level (SCL) is increased, the occurrence of non-specific skin conductance responses (NS.SCRs) increases, and the normalized spectral power in the band from (EDASympn) 0.045 to 0.25 Hz is elevated. When skin is immersed in water, the humidity blocks the sweat glands, changing the dynamics of EDA. For this reason, we have tested the measures of EDA for subjects immersed in water, as response to cognitive stress. Four subjects were recruited for the experiment. Subjects remained four minutes underwater, prior to performing the Stroop task, a test utilized to induce cognitive stress. The SCL and NS.SCRs, didn't exhibit significant differences due to cognitive stress, compared to baseline measurements. EDASymp exhibited significant differences due to cognitive stress. We conclude that the only measure of EDA sensitive to cognitive stress under water is the EDASymp, and it can be potentially used to assess cognitive stress level in divers.

Motion and noise artifacts (MNAs) impose limits on the usability of the photoplethysmogram (PPG), particularly in the context of ambulatory monitoring. MNAs can distort PPG, causing erroneous estimation of physiological parameters such as heart rate (HR) and arterial oxygen saturation (SpO2). In this study, we present a novel approach, "TifMA," based on using the time-frequency spectrum of PPG to first detect the MNA-corrupted data and next discard the nonusable part of the corrupted data. The term "nonusable" refers to segments of PPG data from which the HR signal cannot be recovered accurately. Two sequential classification procedures were included in the TifMA algorithm. The first classifier distinguishes between MNA-corrupted and MNA-free PPG data. Once a segment of data is deemed MNA-corrupted, the next classifier determines whether the HR can be recovered from the corrupted segment or not. A support vector machine (SVM) classifier was used to build a decision boundary for the first classification task using data segments from a training dataset. Features from time-frequency spectra of PPG were extracted to build the detection model. Five datasets were considered for evaluating TifMA performance: (1) and (2) were laboratory-controlled PPG recordings from forehead and finger pulse oximeter sensors with subjects making random movements, (3) and (4) were actual patient PPG recordings from UMass Memorial Medical Center with random free movements and (5) was a laboratory-controlled PPG recording dataset measured at the forehead while the subjects ran on a treadmill. The first dataset was used to analyze the noise sensitivity of the algorithm. Datasets 2-4 were used to evaluate the MNA detection phase of the algorithm. The results from the first phase of the algorithm (MNA detection) were compared to results from three existing MNA detection algorithms: the Hjorth, kurtosis-Shannon entropy, and time-domain variability-SVM approaches. This last is an approach recently developed in our laboratory. The proposed TifMA algorithm consistently provided higher detection rates than the other three methods, with accuracies greater than 95% for all data. Moreover, our algorithm was able to pinpoint the start and end times of the MNA with an error of less than 1 s in duration, whereas the next-best algorithm had a detection error of more than 2.2 s. The final, most challenging, dataset was collected to verify the performance of the algorithm in discriminating between corrupted data that were usable for accurate HR estimations and data that were nonusable. It was found that on average 48% of the data segments were found to have MNA, and of these, 38% could be used to provide reliable HR estimation.

Two parameters that a breathing status monitor should provide include tidal volume (VT ) and respiration rate (RR). Recently, we implemented an optical monitoring approach that tracks chest wall movements directly on a smartphone. In this paper, we explore the use of such noncontact optical monitoring to obtain a volumetric surrogate signal, via analysis of intensity changes in the video channels caused by the chest wall movements during breathing, in order to provide not only average RR but also information about VT and to track RR at each time instant (IRR). The algorithm, implemented on an Android smartphone, is used to analyze the video information from the smartphone's camera and provide in real time the chest movement signal from N = 15 healthy volunteers, each breathing at VT ranging from 300 mL to 3 L. These measurements are performed separately for each volunteer. Simultaneous recording of volume signals from a spirometer is regarded as reference. A highly linear relationship between peak-to-peak amplitude of the smartphone-acquired chest movement signal and spirometer VT is found (r2= 0.951 ± 0.042, mean ± SD). After calibration on a subject-by-subject basis, no statistically significant bias is found in terms of VT estimation; the 95% limits of agreement are -0.348 to 0.376 L, and the rootmean-square error (RMSE) was 0.182 ± 0.107 L. In terms of IRR estimation, a highly linear relation between smartphone estimates and the spirometer reference was found (r2= 0.999 ± 0.002). The bias, 95% limits of agreement, and RMSE are -0.024 breaths-per-minute (bpm), -0.850 to 0.802 bpm, and 0.414 ±0.178 bpm, respectively. These promising results show the feasibility of developing an inexpensive and portable breathing monitor, which could provide information about IRR as well as VT, when calibrated on an individual basis, using smartphones. Further studies are required to enable practical implementation of the proposed approach.

This paper proposes accurate respiratory rate estimation using nasal breath sound recordings from a smartphone. Specifically, the proposed method detects nasal airflow using a built-in smartphone microphone or a headset microphone placed underneath the nose. In addition, we also examined if tracheal breath sounds recorded by the built-in microphone of a smartphone placed on the paralaryngeal space can also be used to estimate different respiratory rates ranging from as low as 6 breaths/min to as high as 90 breaths/min. The true breathing rates were measured using inductance plethysmography bands placed around the chest and the abdomen of the subject. Inspiration and expiration were detected by averaging the power of nasal breath sounds. We investigated the suitability of using the smartphone-acquired breath sounds for respiratory rate estimation using two different spectral analyses of the sound envelope signals: The Welch periodogram and the autoregressive spectrum. To evaluate the performance of the proposed methods, data were collected from ten healthy subjects. For the breathing range studied (6-90 breaths/min), experimental results showed that our approach achieves an excellent performance accuracy for the nasal sound as the median errors were less than 1% for all breathing ranges. The tracheal sound, however, resulted in poor estimates of the respiratory rates using either spectral method. For both nasal and tracheal sounds, significant estimation outliers resulted for high breathing rates when subjects had nasal congestion, which often resulted in the doubling of the respiratory rates. Finally, we show that respiratory rates from the nasal sound can be accurately estimated even if a smartphone's microphone is as far as 30 cm away from the nose.

We hypothesize that our smartphone-based arrhythmia discrimination algorithm with data acquisition approach reliably differentiates between normal sinus rhythm (NSR), atrial fibrillation (AF), premature ventricular contractions (PVCs) and premature atrial contraction (PACs) in a diverse group of patients having these common arrhythmias. We combine root mean square of successive RR differences and Shannon entropy with Poincare plot (or turning point ratio method) and pulse rise and fall times to increase the sensitivity of AF discrimination and add new capabilities of PVC and PAC identification. To investigate the capability of the smartphone-based algorithm for arrhythmia discrimination, 99 subjects, including 88 study participants with AF at baseline and in NSR after electrical cardioversion, as well as seven participants with PACs and four with PVCs were recruited. Using a smartphone, we collected 2-min pulsatile time series from each recruited subject. This clinical application results show that the proposed method detects NSR with specificity of 0.9886, and discriminates PVCs and PACs from AF with sensitivities of 0.9684 and 0.9783, respectively.

We propose an arrhythmia discrimination algorithm for a smart phone that can reliably distinguish among normal sinus rhythm (NSR), atrial fibrillation (AF), premature ventricular contractions (PVCs) and premature atrial contraction (PACs). To evaluate the algorithm in clinical application, we recruited 27 subjects with 3 PVC and 4 PAC subjects as well as 20 AF pre- and post-electrical cardioversion. From each subjects, two-minute pulsatile time series from a fingertip is measured using a smart phone. Our arrhythmia discrimination approach combines Poincare plot and Kulback-Leibler (KL) divergence with Root Mean Square of Successive RR Differences (RMSSD) and Shannon Entropy (ShE). Clinical results show that our algorithm discriminates PVC and PAC with accuracy of 100% and 97.87%, respectively.

Pulse oximetry is a widely accepted clinical method for noninvasive monitoring of arterial oxygen saturation and pulse rate. Significant improvements aimed at curbing motion artifacts and improving reliability in detecting sufficiently strong photoplethysmographic signals are required to reduce errant measurements before the pulse oximeter can be considered for wider mobile applications. The present work describes the development of a wearable multi-channel reflectance pulse oximeter to investigate if a motion artifact-free signal can be obtained in at least one of the multichannels at any given time. Pilot findings provided a proof of concept to support the hypothesis that photoplethysmograms acquired concurrently from independent channels in a multi-channel pulse oximeter sensor respond differently to motion artifacts, thus laying the foundation for future development of robust active noise cancellation and data fusion based algorithms to mitigate the effects of motion artifacts.

A method to identify switching dynamics in time series, based on Annealed Competition of Experts algorithm (ACE), has been developed by Kohlmorgen et al. Incorrect selection of embedding dimension and time delay of the signal significantly affect the performance of the ACE method, however. In this paper, we utilize systematic approaches based on mutual information and false nearest neighbor to determine appropriate embedding dimension and time delay. Moreover, we obtained further improvements to the original ACE method by incorporating a deterministic annealing approach as well as phase space closeness measure. Using these improved implementations, we have enhanced the performance of the ACE algorithm in determining the location of the switching of dynamic modes in the time series. The application of the improved ACE method to heart rate data obtained from rats during control and administration of double autonomic blockade conditions indicate that the improved ACE algorithm is able to segment dynamic mode changes with pinpoint accuracy and that its performance is superior to the original ACE algorithm.

Volterra models have been increasingly popular in modeling studies of nonlinear physiological systems. In this paper, feedforward artificial neural networks with two types of activation functions (sigmoidal and polynomial) are utilized for modeling the nonlinear dynamic relation between renal blood pressure and flow data, and their performance is compared to Volterra models obtained by use of the leading kernel estimation method based on Laguerre expansions. The results for the two types of artificial neural networks (sigmoidal and polynomial) and the Volterra models are comparable in terms of normalized mean-square error (NMSE) of the respective output prediction for independent testing data. However, the Volterra models obtained via the Laguerre expansion technique achieve this prediction NMSE with approximately half the number of free parameters relative to either neural-network model. Nonetheless, both approaches are deemed effective in modeling nonlinear dynamic systems and their cooperative use is recommended in general, since they may exhibit different strengths and weaknesses depending on the specific characteristics of each application.