Classification of Parkinson's disease severity using gait stance signals in a spatiotemporal deep learning classifier.

Parkinson's disease (PD) is a degenerative nervous system disorder involving motor disturbances. Motor alterations affect the gait according to the progression of PD and can be used by experts in movement disorders to rate the severity of the disease. However, this rating depends on the expertise of the clinical specialist. Therefore, the diagnosis may be inaccurate, particularly in the early stages of PD where abnormal gait patterns can result from normal aging or other medical conditions. Consequently, several classification systems have been developed to enhance PD diagnosis. In this paper, a PD gait severity classification algorithm was developed using vertical ground reaction force (VGRF) signals. The VGRF records used are from a public database that includes 93 PD patients and 72 healthy controls adults. The work presented here focuses on modeling each foot's gait stance phase signals using a modified convolutional long deep neural network (CLDNN) architecture. Subsequently, the results of each model are combined to predict PD severity. The classifier performance was evaluated using ten-fold cross-validation. The best-weighted accuracies obtained were 99.296(0.128)% and 99.343(0.182)%, with the Hoehn-Yahr and UPDRS scales, respectively, outperforming previous results presented in the literature. The classifier proposed here can effectively differentiate gait patterns of different PD severity levels based on gait signals of the stance phase.

Assessing cardiovascular stress based on heart rate variability in female shift workers: a multiscale-multifractal analysis approach.

Introduction: Sleep-wake cycle disruption caused by shift work may lead to cardiovascular stress, which is observed as an alteration in the behavior of heart rate variability (HRV). In particular, HRV exhibits complex patterns over different time scales that help to understand the regulatory mechanisms of the autonomic nervous system, and changes in the fractality of HRV may be associated with pathological conditions, including cardiovascular disease, diabetes, or even psychological stress. The main purpose of this study is to evaluate the multifractal-multiscale structure of HRV during sleep in healthy shift and non-shift workers to identify conditions of cardiovascular stress that may be associated with shift work. Methods: The whole-sleep HRV signal was analyzed from female participants: eleven healthy shift workers and seven non-shift workers. The HRV signal was decomposed into intrinsic mode functions (IMFs) using the empirical mode decomposition method, and then the IMFs were analyzed using the multiscale-multifractal detrended fluctuation analysis (MMF-DFA) method. The MMF-DFA was applied to estimate the self-similarity coefficients, α(q, τ), considering moment orders (q) between -5 and +5 and scales (τ) between 8 and 2,048 s. Additionally, to describe the multifractality at each τ in a simple way, a multifractal index, MFI(τ), was computed. Results: Compared to non-shift workers, shift workers presented an increase in the scaling exponent, α(q, τ), at short scales (τ < 64 s) with q < 0 in the high-frequency component (IMF1, 0.15-0.4 Hz) and low-frequency components (IMF2-IMF3, 0.04-0.15 Hz), and with q> 0 in the very low frequencies (IMF4, < 0.04 Hz). In addition, at large scales (τ> 1,024 s), a decrease in α(q, τ) was observed in IMF3, suggesting an alteration in the multifractal dynamic. MFI(τ) showed an increase at small scales and a decrease at large scales in IMFs of shift workers. Conclusion: This study helps to recognize the multifractality of HRV during sleep, beyond simply looking at indices based on means and variances. This analysis helps to identify that shift workers show alterations in fractal properties, mainly on short scales. These findings suggest a disturbance in the autonomic nervous system induced by the cardiovascular stress of shift work.

Analysis of Heart Rate Variability to Detect Changes Associated with Stress Using Cardiac Information Obtained via a Smartphone.

In this study, the contact image photoplethysmography (iPPG) technique was used through a smartphone video camera, and its usefulness was explored under baseline conditions, stress induced by Stroop test and recovery, taking as reference the heart rate variability (HRV) extracted from the electrocardiography (ECG) in two conditions: 1) spontaneous breathing, and 2) controlled breathing at a fixed rate of 6 breaths per minute. Thanks to the use of smartphones, the measurements were made in the homes of the volunteers, who were provided with the measurement systems. Linear temporal and spectral, as well as nonlinear indexes (Poincaré plot and binary symbolic dynamics) were explored for HRV and pulse rate variability (PRV). Similar results were found for ECG-based HRV and iPPG-based PRV, corroborating the usefulness of iPPG via smartphones in HRV studies, providing an interesting alternative to perform HRV analysis outside research and clinical settings.Clinical Relevance- This study shows the use of a smartphone to extract iPPG-based PRV time series and their linear and nonlinear indexes as a surrogate for ECG-based HRV during stress and a controlled breathing maneuver.

Characterization of systolic and diastolic pressure time series in pregnant women with preeclampsia through symbolic dynamics.

Preeclampsia (PE) is one of the leading causes of maternal mortality worldwide. Although clinical strategies to prevent the early onset of PE have been proposed, the ultimate solution is to end the pregnancy. Therefore, patients' identification with major PE risk is important towards the prevention and better management of a severe manifestation of the illness. This study aims to analyze the systolic blood pressure (SBP) and diastolic blood pressure (DBP) time series through a nonlinear perspective using symbolic dynamics and to incorporate a multi-scale assessment in the first trimester of pregnancy, previous to the clinical manifestation of PE. The study group of normotensive women who developed and were diagnosed with PE included 14 pregnant women, a normotensive throughout pregnancy control group (N) consisting of 14 participants, and a group of 14 normotensive women during pregnancy without comorbidities (S) were matched with PE by age, body mass index, gestational age and comorbidities. The preliminary results of this study showed a decreased complexity of SBP, assessed by multiscale symbolic entropy in the first trimester in PE patients, in comparison with normotensive pregnant women.Clinical relevance- This work shows how nonlinear analysis of systolic and diastolic blood pressure time series are useful to detect preeclampsia in the first trimester of pregnancy.

Triaxial Accelerometry Wireless System for Characterization of Parkinsonian Tremor.

Parkinsonian Tremor (PT) is the most common symptom of Parkinson's disease. Its early detection plays an important role in the diagnosis of the disease as it is often mistaken for another type of tremor, called Essential Tremor (ET). Accelerometry analysis has proven to be a trustworthy method for determining the frequency, amplitude, and occurrence of tremor. In addition, the use of portable and wearable sensors has increased due to the rapid growth of Internet of Things (IoT) technology, allowing data to be collected, processed, stored, and transmitted. In this paper, a wearable system consisting of a digital 3-axis accelerometer ADXL345 and micro-controller unit ESP32 was implemented to transmit accelerometry (ACC) signals from each upper limb simultaneously to a Graphical User Interface (GUI), that was developed in Python as an MQTT client, allowing the user to visualize both real-time and offline signals as well as to add markers to indicate events during the acquisition. Furthermore, this GUI is capable of performing an offline analysis consisting of the computing of Power Spectral Density (PSD) using Welch's method and a Spectrogram to visualize a time-frequency distribution of the ACC signals.

Perspectives of the Biomedical Engineering Program at UASLP after ten years - analysis and criticism.

The Biomedical Engineering (BME) bachelor pro-gram of the Faculty of Sciences in Universidad Autónoma de San Luis Potosí (UASLP) was created in June of 2010, with the aim of training professionals with an integral perspective in the engineering field by considering a multidisciplinary approach to develop and apply technology in the areas of medicine and biology. After 10 years, our BME program has achieved national recognition. Despite of being an emerging program, this achievement has been obtained by the consolidation of our academic staff, the outstanding participation of our students in national and international academic events, and the historical graduation results. In our comprehensive evaluation, we report an overall terminal efficiency (completion rate) of 67% and a graduation rate of 47.2%, where these values are above the average for an engineering program in our institution. Additionally, the BME program provides students with solid skills and background to carry out research activities, which has resulted in a considerable number of alumni pursuing graduate studies or have already completed one. Our results show that 90% of our former students are working after graduation, but only 44% work in the field of biomedical engineering, since the regional labor market starts to saturate given the fact that, at present, students from six generations have completed our BME bachelor program. In this way, few graduates visualize the wide spectrum of job options where a biomedical engineer can impact, by their distinctive comprehensive and multidisciplinary training. Therefore, it is necessary to propose new curricular design strategies to provide our students with an academic training that allows them to enter a globalized world, where there is an even greater spectrum of engineering possibilities related to the fields of medicine and biology, in line with current trends.

Detection of Respiratory Crackle Sounds via an Android Smartphone-based System.

Pulmonary auscultation with traditional stethoscope, although useful, has limitations for detecting discontinuous adventitious respiratory sounds (crackles) that commonly occur in respiratory diseases. In this work, we present the development of a mobile health system for the automated detection of crackle sounds, comprised by an acoustical sensor, a smart phone device, and a mobile application (app) implemented in Android. The app allows the physician to record, store, reproduce, and analyze respiratory sounds directly on the smart phone. The algorithm for crackle detection was based on a time-varying autoregressive modeling. Performance of the automated detector was analyzed using synthetic fine and coarse crackle sounds randomly added to the basal respiratory sounds acquired from healthy subjects with different signal to noise ratios. Accuracy and sensitivity were found to range from 90.7% to 94.0% and from 91.2% to 94.2%, respectively. Application of the proposed mobile system to real acquired data from a patient with pulmonary fibrosis is also exemplified.

Fluorescence background removal method for biological Raman spectroscopy based on empirical mode decomposition.

Raman spectroscopy of biological tissue presents fluorescence background, an undesirable effect that generates false Raman intensities. This paper proposes the application of the Empirical Mode Decomposition (EMD) method to baseline correction. EMD is a suitable approach since it is an adaptive signal processing method for nonlinear and non-stationary signal analysis that does not require parameters selection such as polynomial methods. EMD performance was assessed through synthetic Raman spectra with different signal to noise ratio (SNR). The correlation coefficient between synthetic Raman spectra and the recovered one after EMD denoising was higher than 0.92. Additionally, twenty Raman spectra from skin were used to evaluate EMD performance and the results were compared with Vancouver Raman algorithm (VRA). The comparison resulted in a mean square error (MSE) of 0.001554. High correlation coefficient using synthetic spectra and low MSE in the comparison between EMD and VRA suggest that EMD could be an effective method to remove fluorescence background in biological Raman spectra.

Non-linear analysis of EEG and HRV signals during sleep.

The sleep phenomenon is a complex process that involves fluctuations of autonomic functions such as the blood pressure, temperature and brain function. These fluctuations change their properties through the different sleep stages with specific relations among the different systems. In order to understand the relation between the cardiovascular and central nervous system at the different sleep stages, we applied different non-linear methods to the energy of electroencephalographic signal (EEG) and the heart rate fluctuations. The EEG was divided in the Delta, Theta, Alpha and Beta frequency bands and the mean energy of these bands was computed at each heart rate interval. Thus, the non-linear relation was evaluated between the energy of the EEG bands and the heart rate fluctuations using Cross-Correlation, Cross-Sample Entropy and Recurrence Quantification Analysis in segments of 5 minutes grouped by sleep stage. The results showed that a relation exists between the changes of the energy in the Delta band and the Heart rate fluctuations.

Baroreflex sensitivity variations in response to propofol anesthesia: comparison between normotensive and hypertensive patients.

The aim of this paper is to compare baroreflex sensitivity (BRS) following anesthesia induction via propofol to pre-induction baseline values through a systematic and mathematically robust analysis. Several mathematical methods for BRS quantification were applied to pre-operative and intra-operative data collected from patients undergoing major surgery, in order to track the trend in BRS variations following anesthesia induction, as well as following the onset of mechanical ventilation. Finally, a comparison of BRS trends in chronic hypertensive patients (CH) with respect to non hypertensive (NH) patients was performed. 10 NH and 7 CH patients undergoing major surgery with American Society of Anesthesiologists classification score 2.5 ± 0.5 and 2.6 ± 0.5 respectively, were enrolled in the study. A Granger causality test was carried out to verify the causal relationship between RR interval duration and systolic blood pressure (SBP), and four different mathematical methods were used to estimate the BRS: (1) ratio between autospectra of RR and SBP, (2) transfer function, (3) sequence method and (4) bivariate closed loop model. Three different surgical epochs were considered: baseline, anesthetic procedure and post-intubation. In NH patients, propofol administration caused a decrease in arterial blood pressure (ABP), due to its vasodilatory effects, and a reduction of BRS, while heart rate (HR) remained unaltered with respect to baseline values before induction. A larger decrease in ABP was observed in CH patients when compared to NH patients, whereas HR remained unaltered and BRS was found to be lower than in the NH group at baseline, with no significant changes in the following epochs when compared to baseline. To our knowledge, this is the first study in which the autonomic response to propofol induction in CH and NH patients was compared. The analysis of BRS through a mathematically rigorous procedure in the perioperative period could result in the availability of additional information to guide therapy and anesthesia in uncontrolled hypertensive patients, which are prone to a higher rate of hypotension events occurring during general anesthesia induction.

Effects of propofol anesthesia induction on the relationship between arterial blood pressure and heart rate.

This paper presents the analysis of autonomic nervous system (ANS) control of heart rate (HR) and of cardiac baroreflex sensitivity (BRS) in patients undergoing general anesthesia for major surgery through spectral analysis techniques and with the Granger causality approach that take into account the causal relationships between HR and arterial blood pressure (ABP) variability. Propofol produced a general decrease in ABP due to its vasodilatory effects, a reduction in BRS, while HR remained unaltered with respect to baseline values before induction of anesthesia. The bivariate model suggests that the feedback pathway of cardiac baroreflex could be blunted by propofol induced anesthesia and that the feedforward pathway could be unaffected by anesthesia.

Acoustic thoracic image of crackle sounds using linear and nonlinear processing techniques.

In this study, a novel approach is proposed, the imaging of crackle sounds distribution on the thorax based on processing techniques that could contend with the detection and count of crackles; hence, the normalized fractal dimension (NFD), the univariate AR modeling combined with a supervised neural network (UAR-SNN), and the time-variant autoregressive (TVAR) model were assessed. The proposed processing schemes were tested inserting simulated crackles in normal lung sounds acquired by a multichannel system on the posterior thoracic surface. In order to evaluate the robustness of the processing schemes, different scenarios were created by manipulating the number of crackles, the type of crackles, the spatial distribution, and the signal to noise ratio (SNR) at different pulmonary regions. The results indicate that TVAR scheme showed the best performance, compared with NFD and UAR-SNN schemes, for detecting and counting simulated crackles with an average specificity very close to 100%, and average sensitivity of 98 ± 7.5% even with overlapped crackles and with SNR corresponding to a scaling factor as low as 1.5. Finally, the performance of the TVAR scheme was tested against a human expert using simulated and real acoustic information. We conclude that a confident image of crackle sounds distribution by crackles counting using TVAR on the thoracic surface is thoroughly possible. The crackles imaging might represent an aid to the clinical evaluation of pulmonary diseases that produce this sort of adventitious discontinuous lung sounds.