Joana S. Paiva

An automatic method for arterial pulse waveform recognition using KNN and SVM classifiers

AbstractThe measurement and analysis of the arterial pulse waveform (APW) are the means for cardiovascular risk assessment. Optical sensors represent an attractive instrumental solution to APW assessment due to their truly non-contact nature that makes the measurement of the skin surface displacement possible, especially at the carotid artery site. In this work, an automatic method to extract and classify the acquired data of APW signals and noise segments was proposed. Two classifiers were implemented: k-nearest neighbours and support vector machine (SVM), and a comparative study was made, considering widely used performance metrics. This work represents a wide study in feature creation for APW. A pool of 37 features was extracted and split in different subsets: amplitude features, time domain statistics, wavelet features, cross-correlation features and frequency domain statistics. The support vector machine recursive feature elimination was implemented for feature selection in order to identify the most relevant feature. The best result (0.952 accuracy) in discrimination between signals and noise was obtained for the SVM classifier with an optimal feature subset .

Spontaneous Fluctuations in Sensory Processing Predict Within-Subject Reaction Time Variability

When engaged in a repetitive task our performance fluctuates from trial-to-trial. In particular, inter-trial reaction time variability has been the subject of considerable research. It has been claimed to be a strong biomarker of attention deficits, increases with frontal dysfunction, and predicts age-related cognitive decline. Thus, rather than being just a consequence of noise in the system, it appears to be under the control of a mechanism that breaks down under certain pathological conditions. Although the underlying mechanism is still an open question, consensual hypotheses are emerging regarding the neural correlates of reaction time inter-trial intra-individual variability. Sensory processing, in particular, has been shown to covary with reaction time, yet the spatio-temporal profile of the moment-to-moment variability in sensory processing is still poorly characterized. The goal of this study was to characterize the intra-individual variability in the time course of single-trial visual evoked potentials and its relationship with inter-trial reaction time variability. For this, we chose to take advantage of the high temporal resolution of the electroencephalogram (EEG) acquired while participants were engaged in a 2-choice reaction time task. We studied the link between single trial event-related potentials (ERPs) and reaction time using two different analyses: (1) time point by time point correlation analyses thereby identifying time windows of interest; and (2) correlation analyses between single trial measures of peak latency and amplitude and reaction time. To improve extraction of single trial ERP measures related with activation of the visual cortex, we used an independent component analysis (ICA) procedure. Our ERP analysis revealed a relationship between the N1 visual evoked potential and reaction time. The earliest time point presenting a significant correlation of its respective amplitude with reaction time occurred 175 ms after stimulus onset, just after the onset of the N1 peak. Interestingly, single trial N1 latency correlated significantly with reaction time, while N1 amplitude did not. In conclusion, our findings suggest that inter-trial variability in the timing of extrastriate visual processing contributes to reaction time variability.

Single Particle Differentiation through 2D Optical Fiber Trapping and Back-Scattered Signal Statistical Analysis: An Exploratory Approach

Recent trends on microbiology point out the urge to develop optical micro-tools with multifunctionalities such as simultaneous manipulation and sensing. Considering that miniaturization has been recognized as one of the most important paradigms of emerging sensing biotechnologies, optical fiber tools, including Optical Fiber Tweezers (OFTs), are suitable candidates for developing multifunctional small sensors for Medicine and Biology. OFTs are flexible and versatile optotools based on fibers with one extremity patterned to form a micro-lens. These are able to focus laser beams and exert forces onto microparticles strong enough (piconewtons) to trap and manipulate them. In this paper, through an exploratory analysis of a 45 features set, including time and frequency-domain parameters of the back-scattered signal of particles trapped by a polymeric lens, we created a novel single feature able to differentiate synthetic particles (PMMA and Polystyrene) from living yeasts cells. This single statistical feature can be useful for the development of label-free hybrid optical fiber sensors with applications in infectious diseases detection or cells sorting. It can also contribute, by revealing the most significant information that can be extracted from the scattered signal, to the development of a simpler method for particles characterization (in terms of composition, heterogeneity degree) than existent technologies.

Supervised learning methods for pathological arterial pulse wave differentiation: A SVM and neural networks approach

OBJECTIVE The main goal of this study was to develop an automatic method based on supervised learning methods, able to distinguish healthy from pathologic arterial pulse wave (APW), and those two from noisy waveforms (non-relevant segments of the signal), from the data acquired during a clinical examination with a novel optical system. MATERIALS AND METHODS The APW dataset analysed was composed by signals acquired in a clinical environment from a total of 213 subjects, including healthy volunteers and non-healthy patients. The signals were parameterised by means of 39pulse features: morphologic, time domain statistics, cross-correlation features, wavelet features. Multiclass Support Vector Machine Recursive Feature Elimination (SVM RFE) method was used to select the most relevant features. A comparative study was performed in order to evaluate the performance of the two classifiers: Support Vector Machine (SVM) and Artificial Neural Network (ANN). RESULTS AND DISCUSSION SVM achieved a statistically significant better performance for this problem with an average accuracy of 0.9917±0.0024 and a F-Measure of 0.9925±0.0019, in comparison with ANN, which reached the values of 0.9847±0.0032 and 0.9852±0.0031 for Accuracy and F-Measure, respectively. A significant difference was observed between the performances obtained with SVM classifier using a different number of features from the original set available. CONCLUSION The comparison between SVM and NN allowed reassert the higher performance of SVM. The results obtained in this study showed the potential of the proposed method to differentiate those three important signal outcomes (healthy, pathologic and noise) and to reduce bias associated with clinical diagnosis of cardiovascular disease using APW.

Changes in ST, QT and RR ECG intervals during acute stress in firefighters: A pilot study

Firefighting is a stressful occupation. The monitoring of psychophysiological measures in those professionals can be a way to prevent and early detect cardiac diseases and other stress-related problems. The current study aimed to assess morphological changes in the ECG signal induced by acute stress. A laboratory protocol was conducted among 6 firefighters, including a laboratory stress-inducer task - the Trier Social Stress Task (TSST) - and a 2-choice reaction time task (CRTT) that was performed before (CRTT1) and after (CRTT2) the stress condition. ECG signals were continuously acquired using the VitalJacket®, a wearable t-shirt that acts as a medical certified ECG monitor. Results showed that ECG morphological features such as QT and ST intervals are able to differentiate stressful from non stressful events in first responders. Group mean Visual Analogue Scale (VAS) for stress assessment significantly increased after the stress task (TSST), relatively to the end of CRTT2 (after TSST: 4.67±1.63; after CRTT2: 3.17±0.75), a change that was accompanied by a significant increase in group mean QT and ST segments corrected for heart rate during TSST. These encouraging results will be followed by larger studies in order to explore those measures and its physiological impact under realistic environments in a higher scalability.

Computational modeling of red blood cells trapping using Optical Fiber Tweezers

Optical Tweezers (OT) are able to trap/manipulate dielectric particles with few microns in a contactless manner due to forces exerted on them by a strongly focused optical beam. OT are being applied in Biology/Medicine, especially Optical Fiber Tweezers (OFT), for being simpler and more flexible than the conventional setups. Despite of the trapping phenomena of symmetrical particles by OFTs being already modeled, effects regarding complex bodies remain poorly understood. Here we provide a 2D characterization of the trapping forces exerted by a laser OFT on a geometric form of a Red Blood Cell (RBC), occupying different positions in a grid, using the method proposed by Barnett&Loudon. Comparisons were made between the forces exerted on a RBC having the mean normal size; a RBC with 80% of the normal size and an 1.5μm circular particle, due to the size and shape variability of biological-derived structures. The influence of RBCs inclination angles regarding its major axis on trapping performance was also evaluated for angles of π/4 and π/2. Simulation results showed that trapping phenomena are possible for all the conditions evaluated, as well as calculated trapping forces range was according with the literature (pN). We observed that, despite of modeled particles having the same optical characteristics, features such as particle geometry, size, position and inclination degree influence trapping. Trapping forces magnitude was higher for RBC relatively to the circular symmetrical particle; for large RBCs than RBCs with smaller dimensions; and for inclined RBCs than erythrocytes horizontally aligned. Those results reinforce the importance of modeling optical experiments to determine relevant parameters which affect trapping performance.

A Wearable System for the Stress Monitoring of Air Traffic Controllers During An Air Traffic Control Refresher Training and the Trier Social Stress Test: A Comparative Study

Background: Air Traffic Control (ATC) is a complex and demanding process, exposing Air Traffic Controllers (ATCs) to high stress. Recently, efforts have been made in ATC to maintain safety and efficiency in the face of increasing air traffic demands. Computer simulations have been a useful tool for ATC training, improving ATCs skills and consequently traffic safety. Objectives: This study aims to: a) evaluate psychophysiological indices of stress in an ATC simulation environment using a wearable biomonitoring platform. In order to obtain a measure of ATCs stress levels, results from an experimental study with the same participants, that included a stress-induced task were used as a stress ground truth; b) understand if there are differences in stress levels of ATCs with different job functions (“advisors” vs “operationals”) when performing an ATC Refresher Training, in a simulator environment. Methods: Two studies were conducted with ATCs: Study 1, that included a stress-induced task the Trier Social Stress Test (TSST) and Study 2, that included an ATC simulation task. Linear Heart Rate Variability (HRV) features from ATCs were acquired using a medicalgrade wearable Electrocardiogram (ECG) device. Self-reports were used to measure perceived stress. Results: TSST was self-reported as being much more stressful than the simulation task. Physiological data supports these results. Results from study 2 showed more stress among the “advisors” group when comparing to the “operational” group. Conclusion: Results point to the importance of the development of quantified Occupational Health (qOHealth) devices to allow monitoring and differentiation of ATCs stress responses.

Fabrication of Multimode-Single Mode Polymer Fiber Tweezers for Single Cell Trapping and Identification with Improved Performance

Optical fiber tweezers have been gaining prominence in several applications in Biology and Medicine. Due to their outstanding focusing abilities, they are able to trap and manipulate microparticles, including cells, needing any physical contact and with a low degree of invasiveness to the trapped cell. Recently, we proposed a fiber tweezer configuration based on a polymeric micro-lens on the top of a single mode fiber, obtained by a self-guided photopolymerization process. This configuration is able to both trap and identify the target through the analysis of short-term portions of the back-scattered signal. In this paper, we propose a variant of this fabrication method, capable of producing more robust fiber tips, which produce stronger trapping effects on targets by as much as two to ten fold. These novel lenses maintain the capability of distinguish the different classes of trapped particles based on the back-scattered signal. This novel fabrication method consists in the introduction of a multi mode fiber section on the tip of a single mode (SM) fiber. A detailed description of how relevant fabrication parameters such as the length of the multi mode section and the photopolymerization laser power can be tuned for different purposes (e.g., microparticles trapping only, simultaneous trapping and sensing) is also provided, based on both experimental and theoretical evidences.

Cognitive Impact and Psychophysiological Effects of Stress Using a Biomonitoring Platform

Stress can impact multiple psychological and physiological human domains. In order to better understand the effect of stress on cognitive performance, and whether this effect is related to an autonomic response to stress, the Trier Social Stress Test (TSST) was used as a testing platform along with a 2-Choice Reaction Time Task. When considering the nature and importance of Air Traffic Controllers (ATCs) work and the fact that they are subjected to high levels of stress, this study was conducted with a sample of ATCs (n = 11). Linear Heart Rate Variability (HRV) features were extracted from ATCs electrocardiogram (ECG) acquired using a medical-grade wearable ECG device (Vital Jacket® (1-Lead, Biodevices S.A, Matosinhos, Portugal)). Visual Analogue Scales (VAS) were also used to measure perceived stress. TSST produced statistically significant changes in some HRV parameters (Average of normal-to-normal intervals (AVNN), Standard Deviation of all NN (SDNN), root mean square of differences between successive rhythm-to-rhythm (RR) intervals (RMSSD), pNN20, and LF/HF) and subjective measures of stress, which recovered after the stress task. Although these short-term changes in HRV showed a tendency to normalize, an impairment on cognitive performance was evident. Despite that participant’s reaction times were lower, the accuracy significantly decreased, presenting more errors after performing the acute stress event. Results can also point to the importance of the development of quantified occupational health (qOHealth) devices to allow for the monitoring of stress responses.

Beat-to-beat ECG features for time resolution improvements in stress detection

In stress sensing, Window-derived Heart Rate Variability (W-HRV) methods are by far the most heavily used feature extraction methods. However, these W-HRV methods come with a variety of tradeoffs that motivate the development of alternative methods in stress sensing. We compare our method of using HeartBeat Morphology (HBM) features for stress sensing to the traditional W-HRV method for feature extraction. In order to adequately evaluate these methods we conduct a Trier Social Stress Test (TSST) to elicit stress in a group of 13 firefighters while recording their ECG, actigraphy, and psychological self-assessment measures. We utilize the data from this experiment to analyze both feature extraction methods in terms of computational complexity, detection resolution performance, and event localization performance. Our results show that each method has an ideal niche for its use in stress sensing. HBM features tend to be more effective in an online, stress detection context. W-HRV shows to be more suitable for offline post processing to determine the exact localization of the stress event.