Search

This paper focuses on the use of wearable sensors to acquire and process motion data, which is essential for monitoring physiological movement and identifying gait disorders. It is particularly relevant in pediatrics, neurology, and rehabilitation. The research evaluates body motion symmetry in children using accelerometric data, taking into account factors such as age, diagnosis, and gender. Signals were recorded from 35 children (average age 10.8 years) using mobile sensors and were analyzed using digital signal processing techniques and classification methods. The proposed methodology includes data acquisition by smartphone sensors, wireless data export to a remote drive, and data processing through a graphical user interface. The highest classification accuracy of walking features, at 92.0%, was achieved with a two-layer neural network. The findings underscore the effectiveness of these tools in rehabilitation, fitness monitoring, and neurological studies.

Motion analysis using wearable sensors is an essential research topic with broad mathematical foundations and applications in various areas, including engineering, robotics, and neurology. This paper presents the use of the global navigation satellite system (GNSS) for detecting and recording the position of a moving body, along with signals from additional sensors, for monitoring of physical activity and analyzing heart rate dynamics during running on route segments of different slopes and speeds. This method provides an alternative to the heart monitoring on the treadmill ergometer in the cardiology laboratory. The proposed computational methodology involves digital data preprocessing, time synchronization, and data resampling to enable their correlation, feature extraction both in time and frequency domains, and classification. The datasets include signals acquired during ten experimental runs in the selected area. The motion patterns detection involves segmenting the signals by analysing the GNSS data, evaluating the patterns, and classifying the motion signals under different terrain conditions. This classification method compares neural networks, support vector machine, Bayesian, and $k$ -nearest neighbour methods. The highest accuracy of 93.3 % was achieved by using combined features and a two-layer neural network for classification into three classes with different slopes. The proposed method and graphical user interface demonstrate the efficiency of multi-channel and multi-dimensional signal processing with applications in rehabilitation, fitness movement monitoring, neurology, cardiology, engineering, and robotic systems.

Gait analysis and the assessment of rehabilitation exercises are important processes that occur during fitness level monitoring and the treatment of neurological disorders. This paper presents the possibility of using oximetric, heart rate (HR), accelerometric, and global navigation satellite systems (GNSSs) to analyse signals recorded during uphill and downhill walking without and with a face mask to find its influence on physiological functions during selected walking patterns. The experimental dataset includes 86 signal segments acquired under different conditions. The proposed methodology is based on signal analysis in both the time and frequency domains. The results indicate that face mask use has a minimal effect on blood oxygen concentration and heart rate, with the average mean changes of these parameters being less than 2%. The support vector machine, a Bayesian method, the ${k}$ -nearest neighbour method, and a two-layer neural network showed very good separation abilities and successfully classified different walking patterns only in the case when the effect of face mask wearing was not included in the classification process. Our methodology suggests that artificial intelligence and machine learning tools are efficient methods for the assessment of motion patterns in different motion conditions and that face masks have a negligible effect for short-duration experiments.

Anthropometric studies focusing on facial metrics and their proportions form an important research area devoted to observations of the appearance of the human skull. Many different applications include the use of craniometry for maxillofacial reconstruction and surgery. This paper explores the possibility of using selected craniometric points and associated metric to observe spatial changes during the maxillofacial surgery treatment. The experimental dataset includes observations of 27 individuals. The proposed method is associated with the processing of measurements by selected methods of signal processing and computational intelligence. The statistical results point to changes of facial measures before and after the maxillofacial surgery. The proposed method conclusively demonstrates that the area of the mean upper law triangle after surgical treatment is decreased by 8.5%, at the 5% significance level of the two-sample t-test. The classification of selected measurements by a neural network model reached an accuracy of 84.9%.

The study of physiological changes recorded by wearable devices during physical exercises belongs to very important research topics in neurology for the detection of motion disorders or monitoring of the fitness level during sports activities. This paper contributes to this area with studies of the effect of face masks and respirators on blood oxygen concentration, breathing frequency, and the heart rate changes. Experimental data sets include 296 segments of their total length of 60 hours, recorded on a home exercise bike under different motion conditions. Wearable instruments with oximetric, heart rate, accelerometric, and thermal camera sensors were used to fill the own database of signals recorded with selected sampling frequencies. The proposed methodology includes fundamental signal and image processing methods for signal analysis and machine learning tools for labeling image components and detecting facial temperature changes. Results show the minimal effect of mask wearing on blood oxygen concentration but its substantial influence on the breathing frequency and the heart rate. The use of a respirator substantially increased the respiratory rate for the given set of experiments under the load. This indicates how wearable sensors, computational intelligence, and machine learning can be used for motion monitoring and data analysis of signals recorded in different conditions.

Background. The QuantiFERON®-Monitor (QFM) is an assay that measures interferon-γ production and was developed to provide an objective marker of complex immune response. In this study, we evaluated the use of the QFM test in patients with two forms of multiple sclerosis (MS), relapsing–remitting form treated with fingolimod (fMS) and secondarily progressive form not treated pharmacologically (pMS), and in healthy controls (HC). We hypothesized that IFN-γ levels would be lower in those subjects who are relatively more immunosuppressed and higher in those with normal or activated immune function. Methods. This single-center observational study was conducted from November 2020 to October 2021 and compared results in three groups of patients: 86 healthy controls, 96 patients with pMS, and 78 fMS. Combination of lyophilized stimulants was added to 1 ml heparinized whole blood within 8 hr of collection. Plasmatic IFN-γ was measured using the ELISA kit for the QFM and data were obtained in IU/ml. Results. The results showed that controls had nearly 2-fold higher levels of IFN-γ (QFM score) in median (q25, q75) 228.00 (112.20, 358.67) than the MS patient groups: pMS 144.80 (31.23, 302.00); fMS 130.50 (39.95, 217.07) which is statistically significant difference P-value: HC vs. pMS = 0.0071; HC vs. fMS = 0.0468. This result was also confirmed by a validation analysis to exclude impact of variable factors, such as disease duration and Expanded Disability Status Scale scores. Conclusions. Results showed that controls had higher levels of IFN-γ production than the MS patient groups and suggest that MS patients included in this study have a lower ability of immune system activation than HC. Results confirm that fingolimod is able to suppress production of IFN-γ. The fact that the QFM score of MS patients is significantly lower than that of HC may indicate a dysfunctional state of the immune system in baseline conditions.

Motion pattern analysis uses a variety of methods to recognise physical activities recorded by wearable sensors, video-cameras, and global navigation satellite systems. This paper presents motion analysis during cycling, using data from a heart rate monitor, accelerometric signals recorded by a navigation system, and the sensors of a mobile phone. Real cycling experiments were recorded in a hilly area with routes of about 12 km long. Signals were analyzed with appropriate computational tools to find the relationships between geographical and physiological data, including the detection of heart rate recovery delay as an indicator of physical and nervous condition. The proposed algorithms utilized methods of signal analysis and extraction of body motion features, which were used to study the correspondence of heart rate, route profile, cycling speed, and cycling cadence, both in the time and frequency domains. Data processing included the use of Kohonen networks and supervised two-layer softmax computational models for the classification of motion patterns. The results obtained point to a mean time of 22.7 s for a 50 % decrease of the heart rate after a heavy load detected by a cadence sensor. Further results point to a close correspondence between the signals recorded by the body worn accelerometers and the speed evaluated from the GNSSs data. The classification of downhill and uphill cycling based upon accelerometric data achieved an accuracy of 93.9 % and 95.0 % for the training and testing data sets, respectively. The proposed methodology suggests that wearable sensors and artificial intelligence methods form efficient tools for motion monitoring in the assessment of the physiological condition during different sports activities including cycling, running, or skiing. These techniques may also be applied to wide ranging applications in rehabilitation and in the diagnostics of neurological disorders.

Memantine is a noncompetitive N-methyl-d-aspartate (NMDA) receptor antagonist utilized as a palliative cure for Alzheimer’s disease. This is the second study examining the memantine concentrations in cerebrospinal fluid. The previously published study enrolled six patients, and three of them were theoretically in a steady state. In our study, we enrolled 22 patients who regularly used a standard therapeutic dose of memantine (20 mg/day, oral administration) before the sample collection. Patients were divided into four groups, according to the time of plasma and cerebrospinal fluid collection: 6, 12, 18, and 24 h after memantine administration. The cerebrospinal fluid samples were also assessed for selected oxidative stress parameters (malondialdehyde, 3-nitrotyrosine, glutathione, non-protein thiols, and non-protein disulfides). The plasma/cerebrospinal fluid (CSF) ratio for all time intervals were within the range of 45.89% (6 h) to 55.60% (18 h), which corresponds with previously published findings in most patients. The other aim of our study was to deduce whether the achieved “real” memantine concentration in the central compartment was sufficient to block NMDA receptors. The IC50 value of memantine as an NMDA antagonist is in micromolar range; the lowest limit is 112 ng/ml (GluN2C), and this value was achieved only in three cases. The memantine cerebrospinal fluid concentration did not reach one quarter of the IC50 value in five cases (one patient was excluded for noncompliance); therefore, the potency of memantine as a therapeutic effect in patients may be questionable. However, it appears that memantine therapy positively affected the levels of some oxidative stress parameters, especially non-protein thiols and 3-nitrotyrosine.

Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem.

The fluctuation of an EEG signal is a useful symptom of EEG quasi-stationarity. Linear predictive models of three types and their prediction error are studied via traditional and robust measures. The resulting EEG characteristics are applied to the diagnosis of Alzehimer’s disease. Our aim is to decide among: forward, backward, and predictive models, EEG channels, and also robust and non-robust variability measures, and then to find statistically significant measures for use in the diagnosis of Alzheimer’s disease from EEG.

Background: In patients with vertebral artery origin (VAO) stenosis and concomitant stenoses of other cerebral feeding arteries, data on the risk of percutaneous transluminal angioplasty (PTA) alone and with stent placement (PTAS) for VAO stenosis are limited. We aimed to determine how the presence of polystenotic lesions in other cerebral feeding arteries and concomitant carotid artery stenting (CAS) affect the periprocedural risk and long-term effect of PTA/S for atherosclerotic VAO stenosis. Methods: In a retrospective descriptive study, consecutive patients treated with PTA/S for ≥70% VAO stenosis were divided into groups with isolated VAO stenosis and multiple stenoses. We investigated the rate of periprocedural complications in the first 72 h and the risk of restenosis and ischemic stroke (IS)/transient ischemic attack (TIA) during the follow-up period. Results: In a set of 66 patients aged 66.1 ± 9.1 years, polystenotic lesions were present in 56 (84.8%) patients. 21 (31.8%) patients underwent endovascular treatment for stenosis of one or more other arteries in addition to VAO stenosis (15 underwent CAS). During the periprocedural period, no patient suffered from an IS or died, and, in the polystenotic group with concomitant CAS, there was one case of TIA (1.6%). During a mean follow-up period of 36 months, we identified 8 cases (16.3%) of ≥50% asymptomatic VA restenosis, and, in the polystenotic group, 4 (8.9%) cases of IS. Conclusion: The presence of severe polystenotic lesions or concomitant CAS had no adverse effect on the overall low periprocedural risk of PTA/S of VAO stenosis or the risk of restenosis during the follow-up period.

The safety and efficacy of intravenous thrombolysis (IVT) are well established in anterior circulation stroke (ACS) but are much less clear for posterior circulation stroke (PCS). The aim of this study was to evaluate the occurrence of parenchymal hematoma (PH) and 3-month clinical outcomes after IVT in PCS and ACS. In an observational, cohort multicenter study, we analyzed data from ischemic stroke patients treated with IVT prospectively collected in the SITS (Safe Implementation of Treatments in Stroke) registry in the Czech Republic between 2004 and 2018. Out of 10,211 patients, 1166 (11.4%) had PCS, and 9045 (88.6%) ACS. PH was less frequent in PCS versus ACS patients: 3.6 vs. 5.9%, odds ratio (OR) = 0.594 in the whole set, 4.4 vs. 7.8%, OR = 0.543 in those with large vessel occlusion (LVO), and 2.2 vs. 4.7%, OR = 0.463 in those without LVO. At 3 months, PCS patients compared with ACS patients achieved more frequently excellent clinical outcomes (modified Rankin scale [mRS] 0–1: 55.5 vs. 47.6%, OR = 1.371 in the whole set and 49.2 vs. 37.6%, OR = 1.307 in those with LVO), good clinical outcomes (mRS 0–2: 69.9 vs. 62.8%, OR = 1.377 in the whole set and 64.5 vs. 50.5%, OR = 1.279 in those with LVO), and had lower mortality (12.4 vs. 16.6%, OR = 0.716 in the whole set and 18.4 vs. 25.5%, OR = 0.723 in those with LVO) (p < 0.05 in all cases). In PCS versus ACS patients, an extensive analysis showed a lower risk of PH both in patients with and without LVO, more frequent excellent and good clinical outcomes, and lower mortality 3 months after IVT in patients with LVO.

The aim of this study was to conduct QuantiFERON Monitor (QFM) testing in patients with multiple sclerosis (MS), which is used to monitor the state of the immune system through the non-specific stimulation of leukocytes followed by determining the level of interferon-gamma (IFN-γ) released from activated cells. Additionally, we tested the level of selected cytokines (IFN-α, IFN-γ, IL-1α, IL-1β, IL-1ra, IL-2, IL-3, IL-4, IL-6, IL-7, IL-10, IL-15, IL-33, VEGF) from stimulated blood samples to further understand the immune response. This study builds upon a previously published study, utilizing activated serum samples that were initially used for IFN-γ determination. However, our current focus shifts from IFN-γ to exploring other cytokines that could provide further insights into the immune response. A screening was conducted using Luminex technology, which yielded promising results. These results were then further elaborated upon using ELISA to provide a more detailed understanding of the cytokine profiles involved. This study, conducted from August 2019 to June 2023, included 280 participants: 98 RRMS patients treated with fingolimod (fMS), 96 untreated patients with progressive MS (pMS), and 86 healthy controls (HC). Our results include Violin plots showing elevated IL-1α in pMS and fMS. Statistical analysis indicated significant differences in the interleukin levels between groups, with IL-1ra and age as key predictors in differentiating HC from pMS and IL-1ra, IL-1α, age, and EDSS in distinguishing pMS from fMS. These findings suggest cytokines’ potential as biomarkers in MS progression and treatment response.

Abstract We aimed was to assess the factors influencing therapy choice and clinical outcome after 3–4 months in patients with cerebral venous sinus thrombosis (CVST). In a retrospective, bi-centric study, the set consisted of 82 consecutive CVST patients (61 females; mean age 33.5 ± 15.7 years). Following data were collected: baseline characteristics, presence of gender-specific risk factors (GSRF), location and extent of venous sinus impairment, clinical presentation, type of treatment, recanalization, presence of parenchymal lesions, and clinical outcome after 3–4 months (assessed using the modified Rankin Scale [mRS], with excellent outcome defined as mRS 0–1). Multivariate logistic regression analysis was used for statistical evaluation. After 3–4 months, complete recovery was achieved in 41 (50%) and excellent clinical outcome in 67 (81.7%) patients. Female sex (OR 0.11; p = 0.0189) and presence of focal neurologic deficit (OR 0.16; p = 0.0165) were identified as significant independent negative predictors and, the presence of GSRF (OR 15.63; p = 0.0011) as significant independent positive predictor of excellent clinical outcome. In conclusion, in our CVST patients, the presence of GSRF was associated with excellent clinical outcome, while the female sex itself was associated with poorer clinical outcome.

PURPOSE:We aimed to assess the safety and effectiveness of mechanical recanalization in patients with ischemic stroke in the anterior circulation within 8 h since symptoms onset and with unknown onset time. We compared time intervals

Real-world data report worse 3-month clinical outcomes in elderly patients with acute ischemic stroke (AIS) treated with mechanical thrombectomy (MT). The aim was to identify factors influencing clinical outcome in elderly patients with anterior circulation AIS treated with MT (±intravenous thrombolysis (IVT)). In a retrospective, monocentric study, analysis of prospectively collected data of 138 patients (≥80 years) was performed. IVT was an independent negative predictor (OR 0.356; 95% CI: 0.134–0.942) and female sex an independent positive predictor (OR 4.179, 95% CI: 1.300–13.438) of 3-month good clinical outcome (modified Rankin scale 0–2). Female sex was also an independent negative predictor of 3-month mortality (OR 0.244, 95% CI: 0.100–0.599). Other independent negative predictors of 3-month good clinical outcome were older age, lower pre-stroke self-sufficiency, more severe neurological deficit and longer procedural intervals. Mortality was also independently predicted by longer procedural interval and by the occurrence of symptomatic intracerebral hemorrhage (p < 0.05 in all cases). Our results demonstrated, that in patients aged ≥80 years with anterior circulation AIS undergoing MT (±IVT), IVT reduced the chance of 3-month good clinical outcome and female sex was associated with a greater likelihood of 3-month good clinical outcome and lower probability of 3-month mortality.

Gait disorders accompany a number of neurological and musculoskeletal disorders that significantly reduce the quality of life. Motion sensors enable high-quality modelling of gait stereotypes. However, they produce large volumes of data, the evaluation of which is a challenge. In this publication, we compare different data reduction methods and classification of reduced data for use in clinical practice. The best accuracy achieved between a group of healthy individuals and patients with ataxic gait extracted from the records of 43 participants (23 ataxic, 20 healthy), forming 418 segments of straight gait pattern, is 98% by random forest classifier preprocessed by t-distributed stochastic neighbour embedding.

This paper is devoted to proving two goals, to show that various depth sensors can be used to record breathing rate with the same accuracy as contact sensors used in polysomnography (PSG), in addition to proving that breathing signals from depth sensors have the same sensitivity to breathing changes as in PSG records. The breathing signal from depth sensors can be used for classification of sleep apnea events with the same success rate as with PSG data. The recent development of computational technologies has led to a big leap in the usability of range imaging sensors. New depth sensors are smaller, have a higher sampling rate, with better resolution, and have bigger precision. They are widely used for computer vision in robotics, but they can be used as non-contact and non-invasive systems for monitoring breathing and its features. The breathing rate can be easily represented as the frequency of a recorded signal. All tested depth sensors (MS Kinect v2, RealSense SR300, R200, D415 and D435) are capable of recording depth data with enough precision in depth sensing and sampling frequency in time (20−35 frames per second (FPS)) to capture breathing rate. The spectral analysis shows a breathing rate between 0.2 Hz and 0.33 Hz, which corresponds to the breathing rate of an adult person during sleep. To test the quality of breathing signal processed by the proposed workflow, a neural network classifier (simple competitive NN) was trained on a set of 57 whole night polysomnographic records with a classification of sleep apneas by a sleep specialist. The resulting classifier can mark all apnea events with 100% accuracy when compared to the classification of a sleep specialist, which is useful to estimate the number of events per hour. When compared to the classification of polysomnographic breathing signal segments by a sleep specialist, which is used for calculating length of the event, the classifier has an F 1 score of 92.2% Accuracy of 96.8% (sensitivity 89.1% and specificity 98.8%). The classifier also proves successful when tested on breathing signals from MS Kinect v2 and RealSense R200 with simulated sleep apnea events. The whole process can be fully automatic after implementation of automatic chest area segmentation of depth data.

Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, k-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands 〈 3 , 8 〉 and 〈 8 , 15 〉 Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.

Introduction: The issue of resistance to antiplatelet therapy has raised many questions in the area of neurovascular diseases. The first objective of this work was to determine the prevalence of aspirin resistance in neurovascular patients with clinical non-responsiveness to aspirin treatment and a high-risk of atherothrombotic complications using two interpretable and independent methods (aggregation and PFA 100). The second objective was to find the correlation between both assays and to evaluate the results in groups at risk for various cerebrovascular diseases. Material and methods: Laboratory tests of aspirin resistance were performed in 79 patients with clinical non-responsiveness to aspirin treatment suffering from neurovascular diseases. Patients were divided into the two groups: expected low risk for aspirin resistance due to the first manifestation of a neurovascular disease (n = 34) and expected high risk due to the second clinical manifestation of a neurovascular disease (n = 45). Results: The prevalence of aspirin resistance in both groups combined as determined by the PFA-100 and CPG techniques were 50.6% and 17.7%, respectively. No correlation was found between the two techniques. Conclusions: No significant prevalence of aspirin resistance was demonstrated by either method despite the heterogeneous pathophysiological mechanisms. However, we are presently unable to provide an accurate opinion on the value of laboratory test result or routine monitoring in clinical neurology.

Augmented reality has a wide range of applications in many areas that can extend the study of real objects into the digital world, including stomatology. Real dental objects that were previously examined using their plaster casts are often replaced by their digital models or three-dimensional (3D) prints in the cyber-physical world. This paper reviews a selection of digital methods that have been applied in dentistry, including the use of intra-oral scanning technology for data acquisition and evaluation of fundamental features of dental arches. The methodology includes the use of digital filters and morphological operations for spatial objects analysis, their registration, and evaluation of changes during the treatment of specific disorders. The results include 3D models of selected dental arch objects, which allow a comparison of their shape and position during repeated observations. The proposed methods present digital alternatives to the use of plaster casts for semiautomatic evaluation of dental arch measures. This paper describes some of the advantages of 3D digital technology replacing real world elements and plaster cast dental models in many areas of classical stomatology.

Analysis of motion symmetry constitutes an important area with many applications in engineering, robotics, neurology and biomedicine. This paper presents the use of microelectromechanical sensors (MEMS), including accelerometers and gyrometers, to acquire data via mobile devices so as to monitor physical activities and their irregularities. Special attention is devoted to the analysis of the symmetry of the motion of the body when the same exercises are performed by the right and the left limb. The analyzed data include the motion of the legs on a home exercise bike under different levels of load. The method is based on signal analysis using the discrete wavelet transform and the evaluation of signal segment features such as the relative energy at selected decomposition levels. The subsequent classification of the evaluated features is performed by k-nearest neighbours, a Bayesian approach, a support vector machine, and neural networks. The highest average classification accuracy attained is 91.0% and the lowest mean cross-validation error is 0.091, resulting from the use of a neural network. This paper presents the advantages of the use of simple sensors, their combination and intelligent data processing for the numerical evaluation of motion features in the rehabilitation and monitoring of physical activities.

Background: Glatiramer acetate (GA) is an effective treatment for the earliest stages of multiple sclerosis (MS)—clinically isolated syndrome (CIS) or clinically definite MS (CDMS). Objective: This study aims to determine the differences in the lymphocyte population (at baseline and the course of five years) between confirmed sustained progression (CSP) and non-CSP groups and to identify potential biomarkers among these parameters that can predict a positive response to the treatment. Methods: Twelve male and 60 female patients were included in the study. Peripheral blood samples were collected before and five years after treatment with GA. The authors compared lymphocyte parameters between the CSP and non-CSP groups by statistical analyses. Univariate and penalized logistic regression models were fitted to identify the best lymphocyte parameters at baseline and their combination for potential biomarkers. Subsequently, the ROC analysis was used to identify cut-offs for selected parameters. Results: The parameter CD4+/CD45RO+ was identified as the best single potential biomarker, demonstrating the ability to identify patients with CSP. Moreover, a combination of four lymphocyte parameters at baseline, relative lymphocyte counts, CD3+/CD69+, CD4+/CD45RO+, and CD4+/CD45RA+ab, was identified as a potential composite biomarker. This combination explains 23% of the variability in CSP, which is better than the best univariate parameter when compared to CD4+/CD45RO+ at baseline. Conclusions: The results suggest that other biomarkers can help monitor the conditions of patients and predict a favourable outcome.

Multimodal signal analysis based on sophisticated sensors, efficient communicationsystems and fast parallel processing methods has a rapidly increasing range of multidisciplinaryapplications. The present paper is devoted to pattern recognition, machine learning, and the analysisof sleep stages in the detection of sleep disorders using polysomnography (PSG) data, includingelectroencephalography (EEG), breathing (Flow), and electro-oculogram (EOG) signals. The proposedmethod is based on the classification of selected features by a neural network system with sigmoidaland softmax transfer functions using Bayesian methods for the evaluation of the probabilities of theseparate classes. The application is devoted to the analysis of the sleep stages of 184 individualswith different diagnoses, using EEG and further PSG signals. Data analysis points to an averageincrease of the length of the Wake stage by 2.7% per 10 years and a decrease of the length of theRapid Eye Movement (REM) stages by 0.8% per 10 years. The mean classification accuracy for givensets of records and single EEG and multimodal features is 88.7% ( standard deviation, STD: 2.1) and89.6% (STD:1.9), respectively. The proposed methods enable the use of adaptive learning processesfor the detection and classification of health disorders based on prior specialist experience andman–machine interaction.

This paper presents methodology for the processing of GPS and heart rate signals acquired during long-term physical activities. The data analysed include geo-positioning and heart rate multichannel signals recorded for 272.2 h of cycling across the Andes mountains over a 5694-km long expedition. The proposed computational methods include multimodal data de-noising, visualization, and analysis in order to determine specific biomedical features. The results include the correspondence between the heart rate and slope for downhill and uphill cycling and the mean heart rate evolution on flat segments: a regression coefficient of - 0 . 014 bpm/h related to time and 6 . 3 bpm/km related to altitude. The classification accuracy of selected cycling features by neural networks, support vector machine, and k-nearest neighbours methods is between 91.3% and 98.6%. The proposed methods allow the analysis of data during physical activities, enabling an efficient human–machine interaction.

This paper is devoted to a new method of using Microsoft (MS) Kinect sensors for non-contact monitoring of breathing and heart rate estimation to detect possible medical and neurological disorders. Video sequences of facial features and thorax movements are recorded by MS Kinect image, depth and infrared sensors to enable their time analysis in selected regions of interest. The proposed methodology includes the use of computational methods and functional transforms for data selection, as well as their denoising, spectral analysis and visualization, in order to determine specific biomedical features. The results that were obtained verify the correspondence between the evaluation of the breathing frequency that was obtained from the image and infrared data of the mouth area and from the thorax movement that was recorded by the depth sensor. Spectral analysis of the time evolution of the mouth area video frames was also used for heart rate estimation. Results estimated from the image and infrared data of the mouth area were compared with those obtained by contact measurements by Garmin sensors (www.garmin.com). The study proves that simple image and depth sensors can be used to efficiently record biomedical multidimensional data with sufficient accuracy to detect selected biomedical features using specific methods of computational intelligence. The achieved accuracy for non-contact detection of breathing rate was 0.26% and the accuracy of heart rate estimation was 1.47% for the infrared sensor. The following results show how video frames with depth data can be used to differentiate different kinds of breathing. The proposed method enables us to obtain and analyse data for diagnostic purposes in the home environment or during physical activities, enabling efficient human–machine interaction.