Strategies for Reliable Stress Recognition: A Machine Learning Approach Using Heart Rate Variability Features.

Stress recognition, particularly using machine learning (ML) with physiological data such as heart rate variability (HRV), holds promise for mental health interventions. However, limited datasets in affective computing and healthcare research can lead to inaccurate conclusions regarding the ML model performance. This study employed supervised learning algorithms to classify stress and relaxation states using HRV measures. To account for limitations associated with small datasets, robust strategies were implemented based on methodological recommendations for ML with a limited dataset, including data segmentation, feature selection, and model evaluation. Our findings highlight that the random forest model achieved the best performance in distinguishing stress from non-stress states. Notably, it showed higher performance in identifying stress from relaxation (F1-score: 86.3%) compared to neutral states (F1-score: 65.8%). Additionally, the model demonstrated generalizability when tested on independent secondary datasets, showcasing its ability to distinguish between stress and relaxation states. While our performance metrics might be lower than some previous studies, this likely reflects our focus on robust methodologies to enhance the generalizability and interpretability of ML models, which are crucial for real-world applications with limited datasets.

Distribution of transition times in a stochastic model of excitable cell: Insights into the cell-intrinsic mechanisms of randomness in neuronal interspike intervals.

In this paper, we develop an analytical approach to studying random patterns of activity in excitable cells. Our analytical approach uses a two-state stochastic model of excitable system based on the electrophysiological properties of refractoriness and restitution, which characterize cell recovery after excitation. By applying the notion of probability density flux, we derive the distributions of transition times between states and the distribution of interspike interval (ISI) durations for a constant applied stimulus. The derived ISI distribution is unimodal and, provided that the time spent in the excited state is constant, can be approximated by a Rayleigh peak followed by an exponential tail. We then explore the role of the model parameters in determining the shape of the derived distributions and the ISI coefficient of variation. Finally, we use our analytical results to study simulation results from the stochastic Morris-Lecar neuron and from a three-state extension of the proposed stochastic model, which is capable of reproducing multimodal ISI histograms.

Dependence of cardiac spectrum on the spatial resolution of the electrode systems in a realistic model of the canine ventricles.

Body-surface dominant frequency (DF) mapping has been proposed as a technique for non-invasively identifying high-frequency cardiac sources during fibrillation. However, previous studies indicate that volume conduction could distort the spectrum of body-surface cardiac signals and hence, affect body-surface DF maps. In this study, we analyze the effects of volume conduction on the spectrum of cardiac signals in a realistic computer model of the canine ventricles. We simulate complex cardiac dynamics on the ventricular model and analyze the dependence of the bandwidth (BW) of simulated unipolar cardiac signals on the spatial resolution of the corresponding unipolar electrode, which we quantify with the lead equivalent volume (LEV). Our analysis shows that the BW decreases for increasing LEV values and saturates for high LEV values. Our results also indicate that the LEV saturation value is low for low degrees of spatiotemporal correlation. We conclude that the spectral effects of volume conduction might limit our ability to accurately identify high-frequency sources in body-surface DF maps during cardiac fibrillation.

An activity-dependent hierarchical clustering method for sensory organization.

Biological and artificial sensory systems share many features and functionalities in common. One shared challenge is the management setup and maintenance of sensory topological information. In the case of a massive artificial sensory receptor array, this is an extremely complex problem. Biological sensory receptor arrays, such as the visual or tactile system, face the same problem and have found excellent solutions by implementing processes of sensory organization. Not only can biological sensory organization initiate the topological data construction, it can deal with growing systems and repair damaged ones. Importantly, it can use the patterned activity of sensory receptors to extract topological relationships. Using inspiration from these biological processes, we propose an activity-dependent clustering method for organizing large arrays of artificial sensory receptors. We present an algorithm that proceeds hierarchically by building a quadtree description of sensory organization and possesses many qualities of its biological counterpart, namely it can operate autonomously, it uses the patterned activity of sensory receptors and it is capable of supporting growth and repair.

The educational value of teaching biomedical engineering history.

It has been previously argued that science and engineering undergraduate students can benefit greatly from learning the history of their discipline. In order to successfully enhance learning by introducing history into undergraduate curriculum, it would be desirable to assess what the current educational uses of history are and to understand the needs and perceptions of teachers. Nevertheless, to our knowledge no quantitative study of the role of the history of science, engineering, and technology in the classroom has been so far conducted. In this paper we present the design of a survey aimed at assessing the current perception of teachers towards using the history of biomedical engineering (HBME) to enhance learning. This survey was part of a broader project originally led by the EMBS History Committee aimed at evaluating the educational value of the HBME, both for future biomedical engineers and for the broader public. The main goals of the survey are (1) to find out the current uses of the HBME in the classroom, and (2) to identify possible obstacles to expanding the HBME in the classroom.

The natural history of the Engineering in Medicine and Biology Society from a modern perspective.

The history of the IEEE EMBS runs hand in hand with the history of Biomedical Engineering both as a scientific discipline and as a profession. The conferences and publications led by IEEE EMBS, amongst other activities were a mirror of the evolution of Biomedical Engineering over the years and they equally contributed to shape Biomedical Engineering as we view it today. The IEEE EMBS provides a testimony of how a broad and diverse scientific community that comes from many diverse areas such as medicine, engineering, physics and chemistry and shares common purposes and interests can successfully work under the same designation of biomedical engineers. This account is a review of the history of Biomedical Engineering and the development of the IEEE EMBS since the inception of its predecessors, the AIEE Committee on Electrical Techniques in Medicine and Biology and the IRE Professional Group in Medical Electronics.

Sensitivity and spatial resolution of transvenous leads in implantable cardioverter defibrillator.

It has been previously documented that the main features and sensing performance of electrograms (EGMs) recorded in implantable cardioverter defibrillators (ICDs) depend on lead configuration. Although this dependence has been ascribed to differences in lead sensitivity and spatial resolution, the quantification of these two properties on ICD has not yet been attempted. In this paper, an operative framework to study the spatial resolution of ICD transvenous leads is presented. We propose to quantify the spatial resolution of ICD transvenous leads based on a new characterization called lead resolution volume (ResV). We analyzed the sensitivity distribution and the ResV of two unipolar (tip-can and coil-can ) and two bipolar (true or tip-ring and integrated or tip-coil) ICD transvenous lead configurations. A detailed 3-D model of the human thorax based on the visible human man dataset was used to compute the lead sensitivity and computer simulations of simple cardiac dynamics were used to quantify the ResV. Differences in the sensitivity distribution throughout the ventricular myocardium (VM) were observed for each lead configuration. In our computer model of the human thorax, the ResV was found to comprise 7%, 35%, 45%, and 70% of the VM for true bipolar, integrated bipolar, tip-can unipolar, and coil-can unipolar ICD leads, respectively. Furthermore, our analysis shows that the spatial resolution depends on both lead sensitivity and cardiac dynamics, and therefore, it can vary for different heart rhythms.

Spectral analysis of sustained and non-sustained ventricular fibrillation in patients with an implantable cardioverter-defibrillator.

The mechanisms responsible for the maintenance and termination of ventricular fibrillation (VF) are poorly understood. The aim of this study was to compare the spectral characteristics of the electrical signal during sustained and non-sustained VF in patients with an implantable cardioverter-defibrillator. The study included 51 patients who had had at least one episode of sustained VF (i.e., duration >5 s and requiring shock administration) and non-sustained VF (i.e., duration >3 s and spontaneously terminated) that were recorded by the device set in a unipolar configuration. Spectral analysis of the first 3 s of each episode was performed. The dominant frequency was higher in sustained VF (4.6+/-0.7 Hz) than in non-sustained VF (4.3+/-0.6 Hz; P=.01), while the other parameters were similar. Although the spectral characteristics of sustained and non-sustained VF were similar, differences were observed during the first 3 s that could be used in algorithms for the early detection of non-sustained VF.

Análisis espectral de la fibrilación ventricular sostenida y no sostenida en portadores de desfibrilador implantable / Spectral analysis of sustained and non sustained ventricular fibrillation in patients with an implantable cardioverter-defibrillator

Los mecanismos de mantenimiento y finalización de la fibrilación ventricular (FV) son poco conocidos. El objetivo del estudio es comparar las características espectrales de la señal eléctrica de la FV sostenida y no sostenida en pacientes portadores de desfibrilador implantable. Se incluyó a 51 pacientes con al menos un episodio de FV sostenida (de más de 5 s y que precisara choque) y no sostenida (de más de 3 s y terminación espontánea) registrados por el dispositivo en configuración monopolar. Se realizó un análisis espectral de los primeros 3 s de cada episodio. La frecuencia dominante fue mayor en las FV sostenidas (4,6 ± 0,7 frente a 4,3 ± 0,6 Hz en las no sostenidas; p = 0,01), y los demás parámetros fueron similares. Durante los primeros 3 s, si bien las características espectrales son parecidas, hay diferencias utilizables en algoritmos de detección precoz de FV no sostenida (AU)

The mechanisms responsible for the maintenance and termination of ventricular fibrillation (VF) are poorly understood. The aim of this study was to compare the spectral characteristics of the electrical signal during sustained and non-sustained VF in patients with an implantable cardioverter-defibrillator. The study included 51 patients who had had at least one episode of sustained VF (i.e., duration >5 s and requiring shock administration) and non-sustained VF (i.e., duration >3 s and spontaneously terminated) that were recorded by the device set in a unipolar configuration. Spectral analysis of the first 3 s of each episode was performed. The dominant frequency was higher in sustained VF (4.6±0.7 Hz) than in non-sustained VF (4.3±0.6 Hz; P=.01), while the other parameters were similar. Although the spectra (..) (AU)

Effects of the location of myocardial infarction on the spectral characteristics of ventricular fibrillation.

BACKGROUND: The location of the myocardial infarction (MI) might modify the spectral characteristics of ventricular fibrillation (VF) in humans. OBJECTIVE: To evaluate the effect of the location of the infarcted area on the spectral parameters of VF. METHODS: Patients with chronic MI (29 anterior, 32 inferior) and induced VF during cardioverter defibrillator implant were retrospectively studied. Dominant frequency (f(d)), organization index (OI), and power of the harmonic peaks were calculated in the device-stored electrograms (EGM) during sinus rhythm (SR) and VF. RESULTS: The f(d) of the VF was not affected by the left ventricular ejection fraction (LVEF) or the MI location (anterior: 4.54 +/- 0.74 Hz, inferior: 4.77 +/- 0.48 Hz, n.s.). The OI was also similar in both groups. However, in patients with inferior MIs, normalized peak power at f(d) was higher (118.3 +/- 18.5 vs 100.6 +/- 28.2, P < 0.01) and the normalized peak power of the harmonics was lower than in the anterior MI group. The analysis of EGM during SR showed similar results. The size of the necrotic area and its distance to the recording electrode might partially explain these results. CONCLUSION: In our series, the spectral characteristics of the EGMs during VF showed significant differences depending on the MI localization. A higher fraction of energy (in the low-frequency region) was seen in inferior MIs, whereas the peak power at the harmonics increased in anterior MIs. A similar effect was seen during SR and VF, suggesting that it is caused by local electrophysiology abnormalities induced by the MI rather than by different intrinsic characteristics of the VF.

Action potential alternans in LQT3 syndrome: a simulation study.

The long QT syndrome type-3 (LQT3) is an inherited cardiac disorder caused by mutations in the sodium channel gene SCN5A. LQT3 has been associated with ventricular arrhythmias and sudden cardiac death, specially at low heart rates. Based on computer simulations and experimental investigations, analysis of the morphology of the Action Potential (AP) has shown that it undergoes early afterdepolarizations (EADs) and spontaneous discharges, which are thought to be the trigger for reentry like-activity. However, dynamic characteristics of cardiac tissue are also important factors of arrhythmia mechanisms. In this work, we propose a dynamical analysis of the LQT3 at cellular level. We use a detailed Markovian model of the DeltaKPQ mutation, which is associated with LQT3, and we study beat-to-beat AP Duration (APD) variations by using a long-term stimulation protocol. Compared to wild-type (WT) cells, DeltaKPQ mutant cells are found to develop APD alternans over a narrow range of stimulation frequencies. Moreover, the interval of frequency dependence of APD alternans is related to the degree of severity of the EADs present in the AP. In conclusion, dynamical analysis of paced cells is a useful approach to understand the mechanisms of rate dependent arrhythmias.

Contribution of the left anterior myocardium to the body surface potentials in case of apical ectopic beat.

The present paper describes a study where effects of anterior myocardium on body surface potentials were investigated. The study combines numerical lead field analysis combined with cardiac automata model. Electric fields are calculated with finite difference method in a 3-D model of male thorax. The cardiac activation applied in the study is an ectopic beat originating in the apex. The correlations and mean differences between signal generated by anterior segments of left ventricle and signal generated by both ventricles were analysed for 117 leads. The results show that there are leads which have high correlation (>0.9) with low the relative mean difference (<0.2) between the signals generated by anterior segments and signals generated by whole ventricles. These electrode locations would be optimal to monitor the activation of anterior segments when ectopic beats originate in apex.

Estimation of the scope of transvenous lead systems in implantable cardioverter defibrillators.

The analysis of intracardiac Electrograms (EGM) recorded by transvenous lead systems in Implantable Cardioverter Defibrillators (ICD) often entails assumptions on the scope of the lead system. Based on bioelectric signal modeling and on numerical analysis, we studied quantitatively the scope of unipolar and bipolar lead configurations in ICD. We defined the scope in terms of the Mean Square Difference (MSD) between EGM generated by the whole myocardium, and EGM generated by different families of regions within the myocardium. For unipolar and bipolar lead systems, simulations showed that the smallest myocardial region involving a given value of MSD is characterized by the highest measurement sensitivity. Furthermore, the scope in the ventricles was found to be an order of magnitude smaller for bipolar leads than for unipolar leads. Bioelectric signal modeling combined with numerical analysis constitutes a powerful method to study quantitatively the scope of transvenous lead systems.

[Early heart rate increase does not predict the result of the head-up tilt test potentiated with nitroglycerin]. / El incremento temprano de la frecuencia cardíaca no predice el resultado de la prueba de basculación potenciada con nitroglicerina.

INTRODUCTION AND OBJECTIVES: The magnitude of the change in heart rate during the first few minutes of the head-up tilt test has been used to predict the test's result. The aim of this study was to investigate whether the heart rate increase during the head-up tilt test potentiated with nitroglycerin is related to the development of syncope. PATIENTS AND METHOD: The study included 158 consecutive patients with syncope, with stable sinus rhythm, and without structural cardiac disease who were undergoing a head-up tilt test with nitroglycerin. The heart rate increment induced by the tilt maneuver and by nitroglycerin administration was calculated, and its relationship to clinical variables and to the test's results was analyzed. RESULTS: The head-up tilt test gave positive results in 117 patients (74%). The heart rate was 68.7 (11.3) bpm in the decubitus position and 85.1 (15.4) bpm during the first 6 min of tilting. There was strong inverse correlation between the heart rate increase induced by tilting and age (r=--0.63; P<.001), but the increase (16.8 [9.3] bpm in patients with syncope versus 14.9 [11.3] bpm in those without; P=.3) did not predict the result of the test. The heart rate increase induced by nitroglycerin was also similar for patients with and without syncope during the pharmacologic phase of the test (27.3 [12.6] bpm and 26.7 (13.4) bpm, respectively; P=.8). CONCLUSIONS: The magnitude of the heart rate increase during the first few minutes of tilt-testing and after nitroglycerin administration is inversely related to age but does not predict the result of the head-up tilt test with nitroglycerin.

El incremento temprano de la frecuencia cardíaca no predice el resultado de la prueba de basculación potenciada con nitroglicerina / Early heart rate increase does not predict the result of the head-up tilt test potentiated with nitroglycerin

Introducción y objetivos. El incremento acentuado de la frecuencia cardíaca en los primeros minutos de la prueba de basculación ha sido utilizado como predictor del resultado final de ésta, en protocolos sin potenciación farmacológica o con isoproterenol. El objetivo del estudio es evaluar si este incremento se relaciona con la aparición de síncope durante la prueba de basculación potenciada con nitroglicerina. Pacientes y método. Análisis retrospectivo de 158 pacientes consecutivos sometidos a prueba de basculación potenciada con nitroglicerina por síncope, sin cardiopatía y en ritmo sinusal. Se calculó el incremento de la frecuencia cardíaca secundario a la basculación y el debido a la nitroglicerina, relacionándolos con las variables clínicas y el resultado de la prueba. Resultados. La prueba de basculación fue positiva en117 pacientes (74%). La frecuencia cardíaca pasó de68,7 ± 11,3 lat/min en decúbito a 85,1 ± 15,4 lat/min en los primeros 6 min pos-basculación. El incremento de frecuencia presentó una fuerte correlación negativa con la edad (r = -0,63; p < 0,001), pero no se relacionó significativamente con el resultado (16,8 ± 9,3 lat/min en el grupo con prueba positiva frente a 14,9 ± 11,3 en el negativo; p = 0,3). El aumento de la frecuencia cardíaca inducido por la nitroglicerina (27,3 ± 12,6 y 26,7 ± 13,4lat/min, respectivamente; p = 0,8) tampoco predijo el resultado del test durante la fase farmacológica. Conclusiones. Los incrementos de frecuencia cardíaca en los primeros minutos después de la basculación y la administración del fármaco se relacionan fundamentalmente con la edad y no tienen utilidad para predecir el resultado de la prueba de basculación potenciada con nitroglicerina (AU)

Introduction and objectives. The magnitude of the change in heart rate during the first few minutes of the head-up tilt test has been used to predict the test’s result. The aim of this study was to investigate whether the heart rate increase during the head-up tilt test potentiated with nitroglycerin is related to the development of syncope. Patients and method. The study included 158 consecutive patients with syncope, with stable sinus rhythm, and without structural cardiac disease who were undergoing a head-up tilt test with nitroglycerin. The heart rate increment induced by the tilt maneuver and by nitroglycerin administration was calculated, and its relationship to clinical variables and to the test’s results was analyzed. Results. The head-up tilt test gave positive results in117 patients (74%). The heart rate was 68.7 (11.3) bpm in the decubitus position and 85.1 (15.4) bpm during the first 6 min of tilting. There was strong inverse correlation between the heart rate increase induced by tilting and age (r = -0.63; P<.001), but the increase (16.8 [9.3] bp min patients with syncope versus 14.9 [11.3] bpm in those without; P=.3) did not predict the result of the test. The heart rate increase induced by nitroglycerin was also similar for patients with and without syncope during the pharmacologic phase of the test (27.3 [12.6] bpm and 26.7(13.4) bpm, respectively; P=.8). Conclusions. The magnitude of the heart rate increase during the first few minutes of tilt-testing and after nitroglycerin administration is inversely related to age but does not predict the result of the head-up tilt test with nitroglycerin (AU)

[A probabilistic model of cardiac electrical activity based on a cellular automata system]. / Desarrollo de un modelo probabilístico de la actividad eléctrica cardíaca basado en un autómata celular.

INTRODUCTION AND OBJECTIVES: Mathematical models of cardiac electrical activity may help to elucidate the electrophysiological mechanisms involved in the genesis of arrhythmias. The most realistic simulations are based on reaction-diffusion models and involve a considerable computational burden. The aim of this study was to develop a computer model of cardiac electrical activity able to simulate complex electrophysiological phenomena but free of the large computational demands required by other commonly used models. MATERIAL AND METHOD: A cellular automata system was used to model the cardiac tissue. Each individual unit had several discrete states that changed according to simple rules as a function of the previous state and the state of the neighboring cells. Activation was considered as a probabilistic process and was adjusted using restitution curves. In contrast, repolarization was modeled as a deterministic phenomenon. Cell currents in the model were calculated with a prototypical action potential that allowed virtual monopolar and bipolar electrograms to be simulated at any point in space. RESULTS: Reproducible flat activation fronts, propagation from a focal stimulus, and reentry processes that were stable and unstable in two dimensions (with their corresponding electrograms) were obtained. The model was particularly suitable for the simulation of the effects observed in curvilinear activation fronts. Fibrillatory conduction and stable rotors in two- and three-dimensional substrates were also obtained. CONCLUSIONS: The probabilistic cellular automata model was simple to implement and was not associated with a high computational burden. It provided a realistic simulation of complex phenomena of interest in electrophysiology.

Desarrollo de un modelo probabilístico de la actividad eléctrica cardíaca basado en un autómata celular / A probabilistic model of cardiac electrical activity based on a cellular automata system

Introducción y objetivos. La utilización de modelos matemáticos de activación y propagación del impulso ha mejorado la comprensión de diversos mecanismos electrofisiológicos involucrados en la génesis de las arritmias. Las simulaciones más realistas se basan en los modelos de reacción-difusión e implican una carga computacional muy elevada. El objetivo del estudio es desarrollar un modelo de activación eléctrica cardíaca por ordenador que permita simular fenómenos electrofisiológicos complejos y que no requiera la carga computacional necesaria en otros modelos habitualmente empleados. Material y método. Se ha modelado el tejido cardíaco como un autómata celular, cada uno de cuyos elementos adopta estados discretos en función de su estado previo y del de las células vecinas siguiendo unas reglas sencillas. La activación se contempla como un proceso probabilístico y se ajusta mediante el fenómeno de restitución, mientras la repolarización se modela como un proceso determinista. Finalmente, las corrientes celulares se calculan utilizando un potencial de acción prototipo, lo que permite simular los electrogramas virtuales monopolares y bipolares en cualquier punto del espacio. Resultados. Se ha conseguido reproducir frentes planos de activación, propagación de un estímulo focal y reentradas estables e inestables en 2 dimensiones, con sus electrogramas correspondientes. El modelo es particularmente adecuado para simular los fenómenos asociados a la curvatura de los frentes, y permite reproducir la conducción fibrilatoria y los rotores estables en 2 y 3 dimensiones. Conclusiones. Aunque el modelo de autómata celular probabilístico desarrollado es sencillo y no requiere cargas computacionales elevadas, es capaz de simular de forma realista fenómenos complejos de gran interés en electrofisiología

Introduction and objectives. Mathematical models of cardiac electrical activity may help to elucidate the electrophysiological mechanisms involved in the genesis of arrhythmias. The most realistic simulations are based on reaction-diffusion models and involve a considerable computational burden. The aim of this study was to develop a computer model of cardiac electrical activity able to simulate complex electrophysiological phenomena but free of the large computational demands required by other commonly used models. Material and method. A cellular automata system was used to model the cardiac tissue. Each individual unit had several discrete states that changed according to simple rules as a function of the previous state and the state of the neighboring cells. Activation was considered as a probabilistic process and was adjusted using restitution curves. In contrast, repolarization was modeled as a deterministic phenomenon. Cell currents in the model were calculated with a prototypical action potential that allowed virtual monopolar and bipolar electrograms to be simulated at any point in space. Results. Reproducible flat activation fronts, propagation from a focal stimulus, and reentry processes that were stable and unstable in two dimensions (with their corresponding electrograms) were obtained. The model was particularly suitable for the simulation of the effects observed in curvilinear activation fronts. Fibrillatory conduction and stable rotors in two- and three-dimensional substrates were also obtained. Conclusions. The probabilistic cellular automata model was simple to implement and was not associated with a high computational burden. It provided a realistic simulation of complex phenomena of interest in electrophysiology