Biosignal Interpretation Research Articles

Early Eye Disengagement Is Regulated by Task Complexity and Task Repetition in Visual Tracking Task.

Understanding human actions often requires in-depth detection and interpretation of bio-signals. Early eye disengagement from the target (EEDT) represents a significant eye behavior that involves the proactive disengagement of the gazes from the target to gather information on the anticipated pathway, thereby enabling rapid reactions to the environment. It remains unknown how task difficulty and task repetition affect EEDT. We aim to provide direct evidence of how these factors influence EEDT. We developed a visual tracking task in which participants viewed arrow movement videos while their eye movements were tracked. The task complexity was increased by increasing movement steps. Every movement pattern was performed twice to assess the effect of repetition on eye movement. Participants were required to recall the movement patterns for recall accuracy evaluation and complete cognitive load assessment. EEDT was quantified by the fixation duration and frequency within the areas of eye before arrow. When task difficulty increased, we found the recall accuracy score decreased, the cognitive load increased, and EEDT decreased significantly. The EEDT was higher in the second trial, but significance only existed in tasks with lower complexity. EEDT was positively correlated with recall accuracy and negatively correlated with cognitive load. Performing EEDT was reduced by task complexity and increased by task repetition. EEDT may be a promising sensory measure for assessing task performance and cognitive load and can be used for the future development of eye-tracking-based sensors.

Auditory and Nociceptive Stimuli Responses in the Electroencephalogram. A Non-linear Measures and Time-frequency Representation Based Analysis.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". An efficient way to investigate the neural basis of nociceptive responses is the analysis of the event-related brain potentials (ERPs). The main objective of this work was to study how adaptation and fatigue affect the ERPs to stimuli of different modalities, by characterizing the responses to infrequent and frequent stimulation in different recording periods. In this work, series of averaged EEG epochs recorded after thermal, electrical and auditory stimulation were analyzed with time-frequency representation and non-linear measures as spectral entropy and auto-mutual information function. The study was performed by considering the traditional EEG frequency bands. The defined measures presented a statistical significance p-value < 0.01 and accuracy higher than 60% by differentiating windows of response to infrequent (I) and frequent (F) stimuli between the start and end of the EEG recording. These measures permitted to observe some aspects of the subject's adaptation and the nociceptive response.

Individual Thresholding of Voxel-based Functional Connectivity Maps. Estimation of Random Errors by Means of Surrogate Time Series.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". Voxel-based functional connectivity analysis is a common method for resting state fMRI data. However, correlations between the seed and other brain voxels are corrupted by random estimate errors yielding false connections within the functional connectivity map (FCmap). These errors must be taken into account for a correct interpretation of single-subject results. We estimated the statistical range of random errors and propose two methods for an individual setting of correlation threshold for FCmaps. We assessed the amount of random errors by means of surrogate time series and described its distribution within the brain. On the basis of these results, the FCmaps of the posterior cingulate cortex (PCC) from 15 healthy subjects were thresholded with two innovative methods: the first one consisted in the computation of a unique (global) threshold value to be applied to all brain voxels, while the second method is to set a different (local) threshold of each voxel of the FCmap. The distribution of random errors within the brain was observed to be homogeneous and, after thresholding with both methods, the default mode network areas were well identifiable. The two methods yielded similar results, however the application of a global threshold to all brain voxels requires a reduced computational load. The inter-subject variability of the global threshold was observed to be very low and not correlated with age. Global threshold values are also almost independent from the number of surrogates used for their computation, so the analyses can be optimized using a reduced number of surrogate time series. We demonstrated the efficacy of FCmaps thresholding based on random error estimation. This method can be used for a reliable single-subject analysis and could also be applied in clinical setting, to compute individual measures of disease progression or quantitative response to pharmacological or rehabilitation treatments.

Quadratic Phase Couplings in the EEG of Premature and Full-term Newborn during Quiet Sleep.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". The aim of this study was to compare rhythmicities in the quadratic phase coupling (QPC) in the tracé discontinue EEG patterns (TD) of premature newborns and the tracé alternant EEG patterns (TA) of full-term newborns by means of time-variant bispectral analysis. Both pattern occur during quiet sleep and are characterized by an ongoing sequence of interburst and burst patterns. The courses of time-variant bispectral measures during the EEG burst most likely indicate specific interrelations between cortical and thalamocortical brain structures. The EEG of a group of premature (n = 5) and of full-term (n = 5) newborns was analysed. Time-variant QPC was investigated by means of time-variant parametric bispectral analysis. The frequency plain [0.5 Hz, 1.5 Hz] x [3 Hz, 6 Hz] was used as the region-of-interest (ROI). QPC rhythms with a frequency of 0.1 Hz (8 - 11 s) were found in all full-term newborns at all electrodes. For the premature newborns the QPC rhythms were less stable and slower (< 0.1 Hz, 11 - 17 s) at all electrodes and showed a higher inter-individual variation than for the full-term newborns. Statistically, the adaptation of a linear mixed model revealed a difference of about 5 s between both groups of newborns. The comparison of the results of both groups of newborns indicates a development in the interaction between cortical, thalamocortical and neurovegetative structures in the neonatal brain.

An averaging technique for the P300 spatial distribution.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". The main objectives of the paper regard the analysis of amplitude spatial distribution of the P300 evoked potential over a scalp of a particular subject and finding an averaged spatial distribution template for that subject. This template, which may differ for two different subjects, can help in getting a more accurate P300 detection for all BCIs that inherently use spatial filtering to detect P300 signal. Finally, the proposed averaging technique for a particular subject obtains an averaged spatial distribution template through only several epochs, which makes the proposed averaging technique fast and possible to use without applying any prior training data as in case of data enhancement technique. The method used in the proposed framework for the averaging of spatial distribution of P300 evoked potentials is based on the statistical properties of independent components (ICs). These components are obtained by using independent component analysis (ICA) from different target epochs. This paper gives a novel averaging technique for the spatial distribution of P300 evoked potentials, which is based on the P300 signals obtained from different target epochs using the ICA algorithm. Such a technique provides a more reliable P300 spatial distribution for a subject of interest, which can be used either for an improved spatial selection of ICs, or more accurate P300 detection and extraction. In addition, the experiments demonstrate that the values of spatial intensity computed by the proposed technique for P300 signal converge after only several target epochs for each electrode allocation. Such a speed of convergence allows the proposed algorithm to easily adapt to a subject of interest without any additional artificial data preparation prior the algorithm execution such in case of data enhancement technique. The proposed technique averages the P300 spatial distribution for a particular subject over all electrode allocations. First, the technique combines P300-like components obtained by the ICA run within a target epoch in order to obtainan averaged P300 spatial distribution. Second, the technique averages spatial distributions of P300 signals obtained from different target epochs in order to get the final averaged template. Such an template can be useful for any BCI technique where spatial selection is used to detect evoked potentials.

Motor Unit TrackingUsing High Density Surface Electromyography (HDsEMG). Automated Correction of Electrode Displacement Errors.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Ad-vanced Methods for Neural Signals and Images". The study discusses a technique to automatically correct for effects of electrode grid displacement across serial surface EMG measurements with high-density electrode arrays (HDsEMG). The goal is to match motor unit signatures from subsequent measurements and by this, achieve automated motor unit tracking. Test recordings of voluntary muscle contractions using HDsEMG were performed on three healthy individuals. Electrode grid displacements were mimicked in repeated recordings while measuring the exact position of the grid. A concept of accounting for translational and rotational displacements by making the projection of the recorded motor unit action potentials is first introduced. Then, this concept was tested for the performed measurements attempting the automated matching of the similar motor unit action potentials across different trials. The ability to perform automated correction (projection) of the isolated motor unit action potentials was first shown using large angular displacements. Then, for accidental (small) displacements of the recording grid, the ability to automatically track motor units across different measurement trials was shown. It was possible to track 10 -15% of identified motor units. This proof of concept study demonstrates an automated correction allowing the identification of an increased number of same motor unit action potentials across different measurements. By this, great potential is demonstrated for assisting motor unit tracking studies, indicating that otherwise electrode displacements cannot always be precisely described.

Improving Bridging from Informatics Theory to Practice.

In 1962, Methods of Information in Medicine (MIM) began to publish papers on the methodology and scientific fundamentals of managing data, information, and knowledge in biomedicine and health care. Meeting an increasing demand for research about practical implementation of health information systems, the journal Applied Clinical Informatics (ACI) was launched in 2009. Both journals are official journals of the International Medical Informatics Association (IMIA). Based on prior analyses, we aimed to describe major topics published in MIM during 2014 and to explore whether theory of MIM influenced practice of ACI. Our objectives were further to describe lessons learned and to discuss possible editorial policies to improve bridging from theory to practice. We conducted a retrospective, observational study reviewing MIM articles published during 2014 (N=61) and analyzing reference lists of ACI articles from 2014 (N=70). Lessons learned and opinions about MIM editorial policies were developed in consensus by the two authors. These have been influenced by discussions with the journal's associate editors and editorial board members. The publication topics of MIM in 2014 were broad, covering biomedical and health informatics, medical biometry and epidemiology. Important topics discussed were biosignal interpretation, boosting methodologies, citation analysis, health-enabling and ambient assistive technologies, health record banking, safety, and standards. Nine ACI practice articles from 2014 cited eighteen MIM theory papers from any year. These nine ACI articles covered mainly the areas of clinical documentation and medication-related decision support. The methodological basis they cited from was almost exclusively related to evaluation. We could show some direct links where theory impacted practice. These links are however few in relation to the total amount of papers published. Editorial policies such as publishing systematic methodological reviews and clarification of possible practical impact of theory-focused articles may improve bridging.

Stochastic dynamic causal modelling of FMRI data with multiple-model Kalman filters.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". Dynamic Causal Modelling (DCM) is a generic formalism to study effective brain connectivity based on neuroimaging data, particularly functional Magnetic Resonance Imaging (fMRI). Recently, there have been attempts at modifying this model to allow for stochastic disturbances in the states of the model. This paper proposes the Multiple-Model Kalman Filtering (MMKF) technique as a stochastic identification model discriminating among different hypothetical connectivity structures in the DCM framework; moreover, the performance compared to a similar deterministic identification model is assessed. The integration of the stochastic DCM equations is first presented, and a MMKF algorithm is then developed to perform model selection based on these equations. Monte Carlo simulations are performed in order to investigate the ability of MMKF to distinguish between different connectivity structures and to estimate hidden states under both deterministic and stochastic DCM. The simulations show that the proposed MMKF algorithm was able to successfully select the correct connectivity model structure from a set of pre-specified plausible alternatives. Moreover, the stochastic approach by MMKF was more effective compared to its deterministic counterpart, both in the selection of the correct connectivity structure and in the estimation of the hidden states. These results demonstrate the applicability of a MMKF approach to the study of effective brain connectivity using DCM, particularly when a stochastic formulation is desirable.

Decision Making Concepts for the Remote, Personalized Evaluation of COPD Patients' Health Status.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Neural Signals and Images". This paper presents the main concepts of a decision making approach for the remote management of COPD patients based on the early detection of disease exacerbation episodes. An e-diary card is defined to evaluate a number of physiological variables and clinical parameters acquired remotely by means of wearable and environmental sensors deployed in patients' long-stay settings. The automatic evaluation of the card results in a so-called Chronic Status Index (CSI) whose computation is tailored to patients' specific manifestation of the disease (i.e., patient's phenotype). The decision support method relies on a parameterized analysis of CSI variations so as to early detect worsening changes, identify exacerbation severity and track the patterns of recovery. A preliminary study, carried out in real settings with 30 COPD patients monitored at home, has shown the validity and sensitivity of the method proposed, which was effectively able to timely and correctly identify patients' critical situation. The preliminary results showed that the proposed e-diary card, which presents several novel features with respect to other solutions presented in the literature, can be practically used to remotely monitor COPD patients.

Modeling and quantification of repolarization feature dependency on heart rate.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". This work aims at providing an efficient method to estimate the parameters of a non linear model including memory, previously proposed to characterize rate adaptation of repolarization indices. The physiological restrictions on the model parameters have been included in the cost function in such a way that unconstrained optimization techniques such as descent optimization methods can be used for parameter estimation. The proposed method has been evaluated on electrocardiogram (ECG) recordings of healthy subjects performing a tilt test, where rate adaptation of QT and Tpeak-to-Tend (Tpe) intervals has been characterized. The proposed strategy results in an efficient methodology to characterize rate adaptation of repolarization features, improving the convergence time with respect to previous strategies. Moreover, Tpe interval adapts faster to changes in heart rate than the QT interval. In this work an efficient estimation of the parameters of a model aimed at characterizing rate adaptation of repolarization features has been proposed. The Tpe interval has been shown to be rate related and with a shorter memory lag than the QT interval.

Coupling of heart rate and systolic blood pressure in hypertensive pregnancy.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". Hypertensive pregnancy disorders affect 6 - 8 percent of all pregnancies and can result in severe complications for both the mother and the fetus. The aim of this study was to improve risk stratification of pregnant women suffering from hypertension and pre-eclampsia (PE) by applying bivariate Segmented Poincaré plot analysis (BSPPA). From 35 pregnant women suffering from chronic hypertension, gestational hypertension and PE, 30 minutes of noninvasive systolic blood pressure and beat- to-beat intervals were continuously recorded and analyzed by applying BSPPA to quantify their couplings. We revealed significant different couplings between chronic hypertension (CH), gestational hypertension and PE, indicating that cardiovascular regulation can be considerably altered depending on the type of hypertensive disorder. The optimal multivariate set of two BSPPA indices was determined which distinguish best between CH and PE. It achieved a sensitivity of 100%, a specificity of 77.8% and an area under the receiver operator characteristic curve of 90.8%. The BSPPA method a) provides improved risk stratification for pregnant women suffering from hypertension and PE, b) increases the ability to diagnose pathological changes, and c) could contribute substantially to the differential diagnosis of hypertensive pregnancy disorders.

Slow adaptation of ventricular repolarization as a cause of arrhythmia?

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". Adaptation of the QT-interval to changes in heart rate reflects on the body-surface electrocardiogram the adaptation of action potential duration (APD) at the cellular level. The initial fast phase of APD adaptation has been shown to modulate the arrhythmia substrate. Whether the slow phase is potentially proarrhythmic remains unclear. To analyze in-vivo human data and use computer simulations to examine effects of the slow APD adaptation phase on dispersion of repolarization and reentry in the human ventricle. Electrograms were acquired from 10 left and 10 right ventricle (LV/RV) endocardial sites in 15 patients with normal ventricles during RV pacing. Activation-recovery intervals, as a surrogate for APD, were measured during a sustained increase in heart rate. Observed dynamics were studied using computer simulations of human tissue electrophysiology. Spatial heterogeneity of rate adaptation was observed in all patients. Inhomogeneity in slow APD adaptation time constants (Δτ(s)) was greater in LV than RV (Δτ(s)(LV) = 31.8 ± 13.2, Δτ(s)(RV) = 19.0 ± 12.8 s , P< 0.01). Simulations showed that altering local slow time constants of adaptation was sufficient to convert partial wavefront block to block with successful reentry. Using electrophysiological data acquired in-vivo in human and computer simulations, we identify heterogeneity in the slow phase of APD adaptation as an important component of arrhythmogenesis.

Computerized diagnosis of respiratory disorders. SVM based classification of VAR model parameters of respiratory sounds.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced METHODS for Studying Cardiovascular and Respiratory Systems". This work proposes an algorithm for diagnostic classification of multi-channel respiratory sounds. 14-channel respiratory sounds are modeled assuming a 250-point second order vector autoregressive (VAR) process, and the estimated model parameters are used to feed a support vector machine (SVM) classifier. Both a three-class classifier (healthy, bronchiectasis and interstitial pulmonary disease) and a binary classifier (healthy versus pathological) are considered. In the binary scheme, the sensitivity and specificity for both classes are 85% ± 8.2%. In the three-class classification scheme, the healthy recall (95% ± 5%) and the interstitial pulmonary disease recall and precision (100% ± 0% both) are rather high. However, bronchiectasis recall is very low (30% ± 15.3%), resulting in poor healthy and bronchiectasis precision rates (76% ± 8.7% and 75% ± 25%, respectively). The main reason behind these poor rates is that the bronchiectasis is confused with the healthy case. The proposed method is promising, nevertheless, it should be improved such that other mathematical models, additional features, and/or other classifiers are to be experimented in future studies.

Monitoring nocturnal heart rate with bed sensor.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". The aim of this study is to assess the reliability of the estimated Nocturnal Heart Rate (HR), recorded through a bed sensor, compared with the one obtained from standard electrocardiography (ECG). Twenty-eight sleep deprived patients were recorded for one night each through matrix of piezoelectric sensors, integrated into the mattress, through polysomnography (PSG) simultaneously. The two recording methods have been compared in terms of signal quality and differences in heart beat detection. On average, coverage of 92.7% of the total sleep time was obtained for the bed sensor, testifying the good quality of the recordings. The average beat-to-beat error of the inter-beat intervals was 1.06%. These results suggest a good overall signal quality, however, considering fast heart rates (HR > 100 bpm), performances were worse: in fact, the sensitivity in the heart beat detection was 28.4% while the false positive rate was 3.8% which means that a large amount of fast beats were not detected. The accuracy of the measurements made using the bed sensor has less than 10% of failure rate especially in periods with HR lower than 70 bpm. For fast heart beats the uncertainty increases. This can be explained by the change in morphology of the bed sensor signal in correspondence of a higher HR.

Point-process nonlinear autonomic assessment of depressive states in bipolar patients.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". The goal of this work is to apply a computational methodology able to characterize mood states in bipolar patients through instantaneous analysis of heartbeat dynamics. A Point-Process-based Nonlinear Autoregressive Integrative (NARI) model is applied to analyze data collected from five bipolar patients (two males and three females, age 42.4 ± 10.5 range 32 -56) undergoing a dedicated affective elicitation protocol using images from the International Affective Picture System (IAPS) and Thematic Apperception Test (TAT). The study was designed within the European project PSYCHE (Personalised monitoring SYstems for Care in mental HEalth). RESULTS demonstrate that the inclusion of instantaneous higher order spectral (HOS) features estimated from the NARI nonlinear assessment significantly improves the accuracy in successfully recognizing specific mood states such as euthymia and depression with respect to results using only linear indices. In particular, a specificity of 74.44% using the instantaneous linear features set, and 99.56% using also the nonlinear feature set were achieved. Moreover, IAPS emotional elicitation resulted in a more discriminant procedure with respect to the TAT elicitation protocol. A significant pattern of instantaneous heartbeat features was found in depressive and euthymic states despite the inter-subject variability. The presented point-process Heart Rate Variability (HRV) nonlinear methodology provides a promising application in the field of mood assessment in bipolar patients.

Surface and intramural reentrant patterns during atrial fibrillation in the sheep.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia in humans and is predicted to dramatically increase its prevalence in the future. High-resolution mapping data and Fourier power spectral analysis with its dominant frequency support the hypothesis that AF in the structurally normal sheep heart and in some patients often presents organized drivers in the form of periodic surface re-entries or breakthroughs. Nevertheless, the dynamics of those surface patterns of activity, as well as their intramural components are still poorly understood. To present data on AF waves from the surface of isolated sheep hearts and discuss the interpretation of their intramural patterns. We used a combination of endocardial-epicardial optical mapping with phase and spectral analysis as well as computer simulation of the re-entrant activity in the myocardial wall. Analysis of the surfaces' optical mapping data in the phase domain reveals that activation of the posterior left atrium (PLA) consisted of alternating patterns of breakthroughs and reentries. The patterns on the endocardial and epicardial PLA surface at any given moment of time of the AF could be either identical or not identical, and the activity in the thickness of the PLA wall is hypothesized to conform to either ectopic discharge or reentrant scroll waves, but a definite evidence for the presence of such mechanisms is currently lacking. A universal minimal-principle theory is shown in a computer model to result in a tendency of the axis of the scroll waves to align with the myocardial fibers inside the wall. The tendency of filaments of scroll waves to align with myocardial fibers may contribute to the variety and intermittency of surface rotors seen in AF.

Robust detection of sleep apnea from Holter ECGs. Joint assessment of modulations in QRS amplitude and respiratory myogram interference.

This article is part of the Focus Theme of Methods of Information in Medicine on "Biosignal Interpretation: Advanced Methods for Studying Cardiovascular and Respiratory Systems". Detect presence of sleep-related breathing disorders (SRBD) in epochs of 1 min by signal analysis of Holter ECG recordings. In 121 patients, 140 synchronized polysomnograms (PSGs) and 8-channel Holter ECGs were recorded. The only excluded condition was persistent arrhythmias. Respiratory events as scored from the PSGs were mapped to a 1 min grid and served as reference for ECG-based detection. Moreover, 69/70 recordings of the Physionet Sleep Apnea ECG Database (PADB) were included. We performed receiver operating characteristics analysis of a single, novel time-domain feature, the joint local similarity index (jLSI). Based on cross-correlation, the jLSI quantifies the time-locked occurrence of characteristic low-frequency (LF) modulations in ECG respiratory myogram interference (RMI), QRS amplitude (QRSA) and heart rate. Joint oscillations in QRSA, RMI and the envelope of RMI identified positive epochs with a sensitivity of 0.855 (PADB: 0.873) and a specificity of 0.86 (PADB: 0.88). Inclusion of heart rate did not improve detection accuracy. Joint occurrence of LF-modulations in QRSA and RMI is a characteristic feature of SRBD that is robustly quantified by the jLSI and permits reliable and reproducible detection of sleep apnea in very heterogeneous settings.

Pair-Wise Preference Comparisons Using Alpha-Peak Frequencies

Understanding of user needs and preferences, and incorporating them into product designs are crucial for new products to be successful in today's highly competitive marketplace. This paper introduces a unique methodology to capture user preferences from biological signals. The proposed method successfully utilizes one of the most complex phenomenons of the human body, bio-signals for preference extraction. Bio-signals are magnetic fields that are generated by the neurons as a response to a person's surroundings. Due to its complexity, interpretation of bio-signals in the form of natural communication channels is extremely difficult. On the other hand, our experiments with potential users of various types of products revealed that detectable shifts from steady state levels of brain signals in the positive or negative direction are strongly correlated with the individual's preferences on alternative designs. From experiments conducted on 14 different subjects we conclude that when the alpha-peak frequencies EEG signals at the 8--12 Hz band are captured during a user's interaction with two competing product design solutions, the lower alpha-peak value indicates a higher preference over the competing product for right-sided subjects. The opposite effect is observed for the left-sided subjects.

ADVANCED CLASSIFICATION AND RULES-BASED EVALUATION OF MOTION, VISUAL AND BIOSIGNAL DATA FOR PATIENT FALL INCIDENT DETECTION

The monitoring of human physiological data, in both normal and abnormal situations of activity, is interesting for the purpose of emergency event detection, especially in the case of elderly people living on their own. Several techniques have been proposed for identifying such distress situations using either motion, audio or video data from the monitored subject and the surrounding environment. This paper aims to present an integrated patient fall detection system that may be used for patient activity recognition and emergency treatment. Visual data captured from the user's environment, using overhead cameras among with motion and physiological data collected from the subject's body are utilized. Appropriate tracking techniques are applied to the aforementioned visual perceptual component enabling the trajectory tracking of the subjects, while acceleration data from the sensors can indicate a fall incident. Trajectory information and subject's visual location can verify fall and indicate an emergency event, whereas the interpretation of biosignals like electrocardiogram (ECG) and blood oxygen saturation (SPO2) can indicate the severity of the incident with the help of rules-based evaluation. The paper includes also the assessment of several classifiers and meta-classifiers in terms of accuracy in detecting falls and a user based evaluation.

Autoadaptivity and Optimization in Distributed ECG Interpretation

This paper addresses principal issues of the ECG interpretation adaptivity in a distributed surveillance network. In the age of pervasive access to wireless digital communication, distributed biosignal interpretation networks may not only optimally solve difficult medical cases, but also adapt the data acquisition, interpretation, and transmission to the variable patient's status and availability of technical resources. The background of such adaptivity is the innovative use of results from the automatic ECG analysis to the seamless remote modification of the interpreting software. Since the medical relevance of issued diagnostic data depends on the patient's status, the interpretation adaptivity implies the flexibility of report content and frequency. Proposed solutions are based on the research on human experts behavior, procedures reliability, and usage statistics. Despite the limited scale of our prototype client-server application, the tests yielded very promising results: the transmission channel occupation was reduced by 2.6 to 5.6 times comparing to the rigid reporting mode and the improvement of the remotely computed diagnostic outcome was achieved in case of over 80% of software adaptation attempts.