Bioinformatics and Biomedical Engineering

Due to its robustness and built-in feature selection capability, random forest is frequently employed in omics studies for biomarker discovery and predictive modeling. However, random forest assumes equal importance of all features, while in reality domain knowledge may justify the prioritization of more relevant features. Furthermore, it has been shown that an antecedent feature selection step can improve the performance of random forest by reducing noises and search space. In this paper, we present a novel Know-guided regularized random forest (Know-GRRF) method that incorporates domain knowledge in a random forest framework for feature selection. Via rigorous simulations, we show that Know-GRRF outperforms existing methods by correctly identifying informative features and improving the accuracy of subsequent predictive models. Know-GRRF is responsive to a wide range of tuning parameters that help to better differentiate candidate features. Know-GRRF is also stable from run to run, making it robust to noises. We further proved that Know-GRRF is a generalized form of existing methods, RRF and GRRF. We applied Known-GRRF to a real world radiation biodosimetry study that uses non-human primate data to discover biomarkers for human applications. By using cross-species correlation as domain knowledge, Know-GRRF was able to identify three gene markers that significantly improved the cross-species prediction accuracy. We implemented Know-GRRF as an R package that is available through the CRAN archive.

In this paper, we introduce the Fisher’s ratio sampler that serves to unravel the defective pathways in highly underdetermined phenotype prediction problems. This sampling algorithm first selects the most discriminatory genes, that are at the same time differentially expressed, and samples the high discriminatory genetic networks with a prior probability that it is proportional to their individual Fisher’s ratio. The number of genes of the different networks is randomly established taking into account the length of the minimum-scale signature of the phenotype prediction problem which is the one that contains the most discriminatory genes with the maximum predictive power. The likelihood of the different networks is established via leave-one-out-cross-validation. Finally, the posterior analysis of the most frequently sampled genes serves to establish the defective biological pathways. This novel sampling algorithm is much faster and simpler than Bayesian Networks. We show its application to a microarray dataset concerning a type of breast cancers with very bad prognosis (TNBC). In these kind of cancers, the breast cancer cells have tested negative for hormone epidermal growth factor receptor 2 (HER-2), estrogen receptors (ER), and progesterone receptors (PR). This lack causes that common treatments like hormone therapy and drugs that target estrogen, progesterone, and HER-2 are ineffective. We believe that the genetic pathways that are identified via the Fisher’s ratio sampler, which are mainly related to signaling pathways, provide new insights about the molecular mechanisms that are involved in this complex disease. The Fisher’s ratio sampler can be also applied to the genetic analysis of other complex diseases.

In this paper, we introduce the holdout sampler to find the defective pathways in high underdetermined phenotype prediction problems. This sampling algorithm is inspired by the bootstrapping procedure used in regression analysis to established confidence bounds. We show that working with partial information (data bags) serves to sample the linear uncertainty region in a simple regression problem, mainly along the axis of greatest uncertainty that corresponds to the smallest singular value of the system matrix. This procedure applied to a phenotype prediction problem, considered as a generalized prediction problem between the set of genetic signatures and the set of classes in which the phenotype is divided, serves to unravel the ensemble of altered pathways in the transcriptome that are involved in the disease development. The algorithm looks for the minimum-scale genetic signature in each random holdout and the likelihood (predictive accuracy) is established using the validation dataset via a nearest-neighbor classifier. The posterior analysis serves to identify the header genes that most-frequently appear in the different hold-outs and are therefore robust to a partial lack of samples. These genes are used to establish the genetic pathways and the biological processes involved in the disease progression. This algorithm is much faster, robust and simpler than Bayesian Networks. We show its application to a microarray dataset concerning a type of breast cancers with poor prognoses (TNBC).

In this paper, we compare different sampling algorithms used for identifying the defective pathways in highly underdetermined phenotype prediction problems. The first algorithm (Fisher’s ratio sampler) selects the most discriminatory genes and samples the high discriminatory genetic networks according to a prior probability that it is proportional to their individual Fisher’s ratio. The second one (holdout sampler) is inspired by the bootstrapping procedure used in regression analysis and uses the minimum-scale signatures found in different random hold outs to establish the most frequently sampled genes. The third one is a pure random sampler which randomly builds networks of differentially expressed genes. In all these algorithms, the likelihood of the different networks is established via leave one out cross-validation (LOOCV), and the posterior analysis of the most frequently sampled genes serves to establish the altered biological pathways. These algorithms are compared to the results obtained via Bayesian Networks (BNs). We show the application of these algorithms to a microarray dataset concerning Triple Negative Breast Cancers. This comparison shows that the Random, Fisher’s ratio and Holdout samplers are most effective than BNs, and all provide similar insights about the genetic mechanisms that are involved in this disease. Therefore, it can be concluded that all these samplers are good alternatives to Bayesian Networks which much lower computational demands. Besides this analysis confirms the insight that the altered pathways should be independent of the sampling methodology and the classifier that is used to infer them.

‘Lab-on-a-chip’ is integrated micro-analytical system, which could perform sample pre-treatment, chemical reactions, analytical separation, detection and data handling. These platforms are able to convert biological, chemical or mechanical responses into electrical signals using the piezoelectric or piezoresistive materials. This paper discusses a piezoelectric composite material displaying its mechanical properties such as resonant frequencies, Young’s modulus and density. Nano composite polymer highlights the property of piezo effect and is suitable for formation of periodic micro scale patterns on it. These micro patterns are intended to be used as innovative functional elements in biomedical micro hydro mechanical systems such as micro channels. Thus by controlling surface configuration and the shape of active deformable polymer, pressure in microfluidic vessels can be changed and mobility of the transported bioparticles can be ensured.

The aim of this study was to compare Trabecular Bone Score (TBS) in overweight and normal-weight young women. This study included 14 overweight (BMI > 25 kg/m2) and 42 normal-weight (BMI < 25 kg/m2) young Lebanese women whose ages range from 18 to 32 years. Body composition, Bone Mineral Content (BMC), Bone Mineral Density (BMD), and lumbar spine (L1–L4) TBS were assessed by dual-energy X-ray asborptiometry (DXA). The DXA measurements were completed for the whole body (WB), the lumbar spine (L1–L4), the total hip (TH) and the femoral neck (FN). Physical activity, daily calcium intake, daily protein intake and sleep quality index were evaluated using validated questionnaires. Maximal oxygen consumption (VO₂ max in l/mn) was measured whilst exercising on a bicycle ergometer using a specialized device. Weight, height, BMI, lean mass, fat mass, WB BMC, WB BMD, TH BMD and FN BMD were significantly higher in overweight women compared to normal-weight women. Trabecular Bone Score (TBS) was not significantly different between the two groups (overweight and normal-weight). In the whole population (n = 56), weight, height, BMI, lean mass and fat mass were positively correlated to BMC and BMD values but not to TBS values. VO₂ max (l/mn) was positively correlated to BMC, BMD and TBS (p < 0.05). This study suggests that being overweight is not associated with higher trabecular bone score values in young women.

The aim of the present study was to compare hip structural analysis variables in postmenopausal women with sarcopenia and postmenopausal women with normal skeletal muscle mass index. This study included 8 postmenopausal women (aged between 65 and 84 years) with sarcopenia and 60 age-matched controls (with normal skeletal muscle mass index (SMI)). Body composition and bone mineral density (BMD) were assessed by dual-energy X-ray absorptiometry (DXA). Weight, lean mass, Body mass index, femoral neck cross-sectional area (FN CSA), FN section modulus (Z), FN cross sectional moment of inertia (CSMI), intertrochanteric (IT) CSA, IT Z, IT CSMI, IT cortical thickness (CT), femoral shaft (FS) CSA, FS Z and FS CSMI were significantly higher (p < 0.05) in women with normal SMI compared to women with sarcopenia. In the whole population, SMI was positively correlated to IT CSA, IT Z, IT CSMI, IT CT, FS CSA, FS Z, FS CSMI, FS CT but negatively correlated to IT buckling ratio (BR) and FS BR. The present suggests that sarcopenia negatively affects hip bone strength indices in postmenopausal women.

Detection of fidgeting activities is a field which has not been much explored as of now. Studies have shown that fidgeting has a beneficial impact on people’s healthiness as it burns a significant amount of energy. Being able to detect when someone is fidgeting would allow to study more closely the health impact of fidgeting. The purpose of this work is to propose an algorithm being able to detect feet fidgeting period of subjects while sitting using 3-D accelerometers on both shoes. Initial results on data from 5 subjects collected during this work shows an accuracy of 95% for a classification between sitting with fidgeting and sitting without fidgeting.

Structural aberrations (SAs), gains or losses in large segments of genomes, are associated with several genetic disorders. The SAs are commonly called the copy number alterations (CNAs) and their identification/classification is required to identify diseases. Many methods have been proposed to estimate the breakpoints and segmental constants in the CNAs with highest precision using the most powerful technologies of hybridization. However, locations and lengths of CNAs estimated using well-elaborated methods are often contradictory due to extensive variability of measurements and performance of the algorithms. Still much less attention is given to the estimation accuracy and it is difficult to select the best estimator. In this work, we propose to modify the confidence masks replacing the skew Laplace distribution with the asymmetric exponential power distribution (AEP) to approximate the jitter distribution in CNAs. Next, the estimates obtained using different algorithms are matched with the annotations made by experts employing the improved masks. Finally, we specify the match confidence probability of each CNAs detector algorithm respect the experts estimates.

Contralaterally controlled functional electrical stimulation (CCFES) is a recent therapy aimed at improving the recovery of impaired limbs after stroke. For hemiplegic patients, CCFES uses a control signal from the non-impaired side of the body to regulate the intensity of electrical stimulation delivered to the affected muscles of the homologous limb on the opposite side of the body. CCFES permits an artificial muscular contraction synchronized with the patient’s intentionality to carry out functional tasks, which is a way to enhance neuroplasticity and to promote motor learning. This work presents an upper extremity motor rehabilitation system based on CCFES, using orientation sensors for control. Thus, the stimulation intensity (current amplitude) delivered to the paretic extremity is proportional to the degree of joint amplitude of the unaffected extremity. The implemented controller uses a control strategy that allows the delivered electrical stimulation intensity, to be comparable to the magnitude of movement. It was carried out a set of experiments to validate the overall system, for executing five bilateral mirror movements that include human wrist and elbow joints. Obtained results showed that movements voluntary signals acquired from right upper-limb were replicated successfully on left upper-limb using the FES system.

Despite multiple advances with myoelectric control, currently there is still an important need to develop more effective methods for controlling prosthesis and exoskeletons in a natural way. This work describes the design and development of a research tool for the design, development and evaluation of algorithms of myoelectric control which base on intention detection from neuromuscular activation patterns. This platform provides integrated hardware and software tools for real-time acquisition, preprocessing, visualization, storage and analysis of biological signals. It is composed of a bio-instrumentation system controlled by a real-time software created in Simulink and executed on the xPC-target platform and, a Java based software application that allows to manage the acquisition and storage processes by a system operator. System evaluation was performed by the comparison with reference signals provided by a function generator and, as an example of the application of the developed acquisition platform, it was carried out a set of experiments to decode movements at the upper-limb level.

The actual trend in surgery is the transition from open procedures to minimally invasive interventions and revolutionary changes in computer-aided surgery have been obtained thanks to the introduction of the augmented reality technology that can support the doctor during the surgery. A realistic three-dimensional visualization of the patient’s organs can be obtained by means of specific algorithms of segmentation and classification of medical images and advanced modalities of touchless interaction and innovative gesture-control devices permit surgeon to have a natural and simple way of fruition of the patient’s data preserving the surgical environment from the danger of contamination.

The aim of the current study was to compare compression strength index (CSI), bending strength index (BSI) and impact strength index (ISI) among obese, overweight and normal-weight young women. 117 young women (20 obese, 36 overweight and 61 normal-weight) whose ages range from 18 to 35 years participated in this study. Body composition and BMD were evaluated by dual-energy X-ray absorptiometry (DXA). CSI, BSI and ISI values were significantly lower in obese and overweight women compared to normal-weight women (p < 0.001). In the whole population (n = 117), body mass index (BMI) was negatively correlated to CSI (r = −0.66; p < 0.001), BSI (r = −0.56; p < 0.001) and ISI (r = −0.54; p < 0.001). This study suggests that obesity is associated with lower CSI, BSI and ISI values in young women.

Diabetes mellitus (DM) and essential hypertension (EH) are chronic diseases more prevalent every year, both independently and jointly. To gain insights about the particularities of these chronic conditions, we study the use of decision trees as a tool for selecting discriminative features and making predictive analyses of the health status of this kind of chronic patients. We considered gender, age, ICD9 codes for diagnosis and ATC codes for drugs associated with the diabetic and/or hypertensive population linked to the University Hospital of Fuenlabrada (Madrid, Spain) during 2012. Results show a relationship among DM/EH and diseases/drugs related to the respiratory system, mental disorders, or the musculoskeletal system. We conclude that drugs are quite informative, collecting information about the disease when the diagnosis code is not registered. Regarding predictive analyses, when discriminating patients with EH-DM and just one of these chronic conditions, better accuracy is obtained for EH (85.4%) versus DM (80.1%).

Proliferative activity of cells is one of the most critical factors in breast cancer diagnosis. It is used to evaluate tumor cell progression and to predict treatment responses in chemotherapy. Ki-67 is a nuclear biomarker commonly used to measure cellular proliferation rate. The ratio between the number of Ki-67 positive tumor nuclei and all tumor nuclei defines Ki-67 index. However, manual cell counting is tedious and time consuming because hundreds of nuclei must be labeled. To speed up the analysis process, nuclei can be segmented automatically and then classified based on staining color. Unfortunately, segmentation of individual nuclei is a big challenge because they often create complex clusters comprised of many touching and overlapping nuclei. To deal with complexities and ambiguities of cytological material we propose a generative model which approximates nuclei using ellipses. We assume that the process of generating a cytological sample has stochastic nature. Therefore it is possible to reconstruct this process using marked point process tuned according to observed cytological sample. To verify the potential of the proposed method, we applied it to determine Ki-67 index in breast cancer immunochemistry samples. The results of experiments have shown that Ki-67 indices determined by proposed approach correlate well with those computed manually.

The article deals with selected methods of automated detection of microscopic objects in video sequences obtained by high-speed cinematography and light microscopy. The objects of interest are represented by cilia of airways and also artefact generating objects (gas bubbles and erythrocytes). The main idea of this work is to create complex diagnostic tool for evaluation of ciliated epithelium in airways, where the ratio between moving and static cilia helps to search proper diagnosis (confirmation of PCD – primary ciliary dyskinesia). Methods for automated segmentation of static cilia creates a big challenge for image analysis against the dynamic ones due to character and parameters of obtained images. This work is supported by medical specialists from Jessenius Faculty of Medicine in Martin (Slovakia) and proposed tools would fill the gap in the diagnostics in the field of respirology in Slovakia.

Parkinson’s Disease is one of the leading movement disorder diseases. It is the fourth most common neurological disease, after migraine, stroke and epilepsy. The motor symptoms of the disease significantly impair daily living and quality of life and exact a high burden on both patients and their caregivers. Deep Brain Stimulation is a proven therapy for this disease, getting positive outcomes while reducing medication. In this paper, stereotactic system used for Deep Brain Stimulation (DBS) procedures will be described. Different planning methods will be observed and compared to the gold standard normally used, neurophysiological coordinates recorded intra-operatively. MRI, CT scan and direct calculation of stereotactic coordinates will be compared and group in three different groups, according to DBS therapy outcomes: “very good DBS therapy”, “good DBS therapy” and “not major improvement”.Database of 72 DBS electrodes implanted in Parkinson’s Disease patients will be studied. Most potentially beneficial ranges of deviation within planning and neurophysiological coordinates from the operating room will be assessed, in order to provide neurosurgeons with more landmarks in order to achieve the best outcomes within a millimetric technique.We could confirm three main highlights out of this study: the neurophysiological length of the Subthalamic Nucleus does not play a major role in outcomes while being within normal range; CT scan calculations were the most accurate; direct calculations should not be used as major deviations were observed.

Breast cancer is one of the leading causes of cancer-related death in female patients. The quantitative ultrasound techniques being developed recently provide useful information facilitating the classification of tumors as malignant or benign. Quantitative parameters are typically determined on the basis of signals scattered within the tumor. The present paper demonstrates the utility of quantitative data estimated based on signal backscatter in the tissue surrounding the tumor. Two quantitative parameters, weighted entropy and Nakagami shape parameter were calculated from the backscatter signal envelope. The ROC curves and the AUC parameter values were used to assess their ability to classify neoplastic lesions. Results indicate that data from tissue surrounding the tumor may characterize it better than data from within the tumor. AUC values were on average 18% higher for parameters calculated from data collected from the tissue surrounding the lesion than from the data from the lesion itself.

This paper presents a learning based approach for the classification of pathological vertebrae. The proposed method is applied to spine metastasis, a malignant tumor that develops inside bones and requires a rapid diagnosis for an effective treatment monitoring. We used multiple texture analysis techniques to extract useful features from two co-registered MR images sequences (T1, T2). These MRIs are part of a diagnostic protocol for vertebral metastases follow up. We adopted a slice by slice MRI analysis of 153 vertebra region of interest. Our method achieved a classification accuracy of $$90.17\% \pm 5.49$$, using only a subset of 67 relevant selected features from the initial 142.

Near infrared (NIR) imaging is one of the promising methods for identification of superficial veins and widely researched and used in clinical medicine and biomedical studies. However, just like imaging in visible spectrum, NIR imaging is not adequate for exact recognition of the vein system as it is, therefore nearly every research starts with preprocessing to prepare the images for identification. Two major filtering methods are anisotropic diffusion and Gaussian high-pass filter which both consist of mandatory parametric adjustments for better visualization of the images and for revealing the vein system. Therefore in this paper we deal with parametric variations of these two methods on a NIR image to give ideas for choosing proper preprocessing techniques and parameters, excluding edge detection and vein detection methodologies.

This article aims to compare the results of two different infrared cameras through revealing the irregular temperature distribution on an injured toe. Since the inhomogeneous body temperature is the key indicator of severe injuries, wounds, and illnesses, infrared thermography is the strongest method among other conventional methods to map the skin temperature variations. The current utility of infrared cameras in biomedical applications is also presented to comprehend the relationship between the nature of thermal radiation and human body temperature. In the article, the presented biomedical applications include skin cancer screening, wound detection in a diabetic foot, muscle activation assessment during an exercise, or thermal mapping of healthy human bodies. Along with the developments in infrared thermography, this article focuses on analyzing temperature distribution on the injured toe of a subject with two different smartphone-based infrared camera models namely FLIR One and SEEK Compact Pro. In addition, the results obtained from the presented infrared camera models are compared regarding to the thermal images of the injured toe.

This work explores novel alternatives to conventional linear homotopy to enhance the quality of resulting transitions from object deformation applications. Studied/introduced approaches extend the linear mapping to other representations that provides smooth transitions when deforming objects while homotopy conditions are fulfilled. Such homotopy approaches are based on transcendental functions (TFH) in both simple and parametric versions. As well, we propose a variant of an existing quality indicator based on the ratio between the coefficients curve of resultant homotopy and that of a less-realistic, reference homotopy. Experimental results depict the effect of proposed TFH approaches regarding its usability and benefit for interpolating images formed by homotopic objects with smooth changes.

The anterior forearm recognition systems are very popular identify the subcutaneous veins, mostly by devices operating real-time. Real time projection systems are carried out by handheld devices with a near infrared (NIR) camera and a laser projector to choose venipuncture sites; however what we propose in this paper is an easier and more reliable way using infrared thermal (IR-T) camera. At the forearm some veins like Cephalic vein are mostly so concealed to detect by NIR cameras, therefore we propose an alternative method for localization of the whole vein system without preprocessing. Briefly in the thermograms, the forearm is segmented from the surrounding by crisp 2- means and the vein system is reconstructed on blank images by directional curvature method. All directional curvatures are combined by addition for merging the layers and highlighting mutual veins. The preliminary results are promising since all the vein system is revealed with invisible veins without any preprocessing.

From numbness to acral necrosis, vasospasms confining to the fingers are stimulating a wide variety of symptoms. Induced by several reasons, the constriction of small arteries is a severe disorder and should be diagnosed as early as possible. The major indicator of a mild vasospasm is reduced blood flow creating a nonhomogeneous radiation patterns in hand thermography before a total discoloration of the fingers. Therefore, in this paper, an identification methodology of the vasospasms is discussed, through the fuzzy c-means. Since the pseudocolored thermograms give crucial information of radiation variety, we segmented the hands from the images by hard k-means for subsequent analysis of low-radiated regions determined by fuzzy c-means. The isolated low-radiated regions in red-channel converted images also reveals ischemia as well as thermoregulation even in very milder cases.

Accurate diagnosis and early detection of various disease conditions are key to improving living conditions in any community. The existing framework for medical image classification depends largely on advanced digital image processing and machine (deep) learning techniques for significant improvement. In this paper, the performance of traditional hand-designed texture descriptors within the image-based learning paradigm is evaluated in comparison with machine-designed descriptors (extracted from pre-trained Convolution Neural Networks). Performance is evaluated, with respect to speed, accuracy and storage requirements, based on four popular medical image datasets. The experiments reveal an increased accuracy with machine-designed descriptors in most cases, though at a higher computational cost. It is therefore necessary to consider other parameters for tradeoff depending on the application being considered.

Breast cancer (BC) is a public health problem of first importance, being the second most common cancer worldwide. BC represents 30.4% of all new cancer cases in the European female population. The diagnosis and differential diagnosis of BC is based on the clinical presentations, physical examinations combined with imaging studies, and confirmed by histopathologic findings. Pathologists’ examination is a time-consuming analysis, susceptible to an interpretation bias mainly caused by the experience of the pathologist and the decrease of attention due to fatigue. Currently, computer-aided detection and diagnosis techniques applied to digital images are assisting the specialists.In this work, the performance of a pattern recognition system based on KAZE features in combination with Bag-of-Features (BOF) to discriminate between benign and malignant tumours is evaluated on the BreakHis database (7909 images). During the training stage, KAZE keypoints are extracted for every image in the training set. Keypoints are mapped into a histogram vector using K-means clustering. This histogram represents the input to build a binary SVM classifier. In the testing stage, the KAZE keypoints are extracted for every image in the test set, and fed into the cluster model to map them into a histogram vector. This vector is finally fed into the binary SVM training classifier to classify the image.The experimental evaluation shows the feasibility and effectiveness, in terms of classification accuracy, of the proposed scheme for the binary classification of breast cancer histopathological images with a low magnification factor.

The evaluation of the data/information fusion systems does not have standard quality criteria making the reuse and optimization of these systems a complex task. In this work, we propose a complete low data fusion (DF) framework based on the Joint Director of Laboratories (JDL) model, which considers contextual information alongside information quality (IQ) and performance evaluation system to optimize the DF process according to the user requirements. A set of IQ criteria was proposed by level. The model was tested with a brain-computer interface (BCI) system multi-environment to prove its functionality. The first level makes the selection and preprocessing of electroencephalographic signals. In level one feature extraction is carried out using discrete wavelet transform (DWT), nonlinear and linear statistical measures, and Fuzzy Rough Set – FRS algorithm for selecting the relevant features; finally, in the same level a classification process was conducted using support vector machine – SVM. A Fuzzy Inference system is used for controlling different processes based on the results given by an IQ evaluation system, which applies quality measures that can be weighted by the users of the system according to their requirements. Besides, the system is optimized based on the results given by the cuckoo search algorithm, which uses the IQ traceability for maximizing the IQ criteria according to user requirements. The test was carried out with different type and levels of noise applied to the signals. The results showed the capability and functionality of the model.

Continuous and non-invasive measurement of blood pressure (BP) is of great importance. To achieve continuous and cuffless BP monitoring, pulse transit time (PTT) has been reported as a potential parameter. Nevertheless, this approach remains very sensitive, cumbersome and disagreeable for patients. This study proposes a new parameter available in phonocardiogram (PCG) to measure blood pressure. The PCG is processed and analyzed in order to measure the systolic and diastolic durations in order to study their correlation with an estimated PTT. The proposed approach evaluated on a developed data base of 37 subjects shows linear regression of two classes in distribution of diastolic duration with PTT estimated. Where, a good correlation coefficient is found for each class (class1: R = 0.87, class2: R = 0.85. This technic has significant potential to develop a new approach to measure blood pressure using PCG signal.

In this paper, we used the fractal dimensions in ECG signals to identify the wave’s detections failure. We check for the sensitivities and the importance of QRS and ST detection because different false wave’s detections caused by the various types of interference and artefact are detected for some ECG signals presenting pathologies.The fractal dimension is very sensitive to variations: if irregularities degree is great, the fractal dimension is high and vice versa. Different cases of pathologies decreased irregularities on the ECG signal so it causes a decrease in fractal dimension. However decreasing in irregularities is not necessarily pathological: a bad detection can also train it, because we have not the exact location of the beginning and the end of QRS complex or the end of the T wave, it causes a new variation in the dimension fractal which can skew the result.For that reason and in order to get good results from algorithm detection, the fractal dimensions are calculated for each QRS complex and ST segment, for some ECG signals, to check their sensitivities in heart rate irregularities and false wave’s detections so that make ECG interpretation system more effective.

We consider the problem of increasing the informative value of electrocardiographic (ECG) surveys using data from multichannel electrocardiographic leads, that include both recorded electrocardiosignals and the coordinates of the electrodes placed on the surface of the human torso. In this area, we were interested in reconstruction of the surface distribution of the equivalent sources during the cardiac cycle at relatively low hardware cost. In our work, we propose to reconstruct the equivalent electrical sources by numerical methods, based on integral connection between the density of electrical sources and potential in a conductive medium. We consider maps of distributions of equivalent electric sources on the heart surface (HSSM), presenting source distributions in the form of a simple or double electrical layer. We indicate the dynamics of the heart electrical activity by the space-time mapping of equivalent electrical sources in HSSM.

Rapid Prototyping Platforms reduce development time by allowing quick prototyping of a prototype idea and achieve more time for actual application development with user interfaces. This approach has long been followed in technical platforms, such as the Arduino. To transfer this form of prototyping to wearables, WearIT is presented in this paper. WearIT consists of four components as a wearable prototyping platform: (1) a vest, (2) sensor and actuator shields, (3) its own library and (4) a motherboard consisting of Arduino, Raspberry Pi, a board and a GPS module. As a result, a wearable prototype can be quickly developed by attaching sensor and actuator shields to the WearIT vest. These sensor and actuator shields can then be programmed through the WearIT library. Via Virtual Network Computing (VNC) with a remote computer, the screen contents of the Raspberry Pi can be accessed and the Arduino be programmed.

How technology can answer the challenge that currently population ageing is facing to the healthcare system? In this work, systems and devices related to “smart” bed and cushion, that are commercially available or matter of research works, are reviewed.

Being able to monitor the heart activity of patients during their daily life in a reliable, comfortable and affordable way is one main goal of the personalized medicine. Current wearable solutions lack either on the wearing comfort, the quality and type of the data provided or the price of the device. This paper shows the development of a Textile Sensor Platform (TSP) in the form of an electrocardiogram (ECG)-measuring T-shirt that is able to transmit the ECG signal to a smartphone. The development process includes the selection of the materials, the design of the textile electrodes taking into consideration their electrical characteristics and ergonomy, the integration of the electrodes on the garment and their connection with the embedded electronic part. The TSP is able to transmit a real-time streaming of the ECG-signal to an Android smartphone through Bluetooth Low Energy (BLE). Initial results show a good electrical quality in the textile electrodes and promising results in the capture and transmission of the ECG-signal. This is still a work-in-progress and it is the result of an interdisciplinary master project between the School of Informatics and the School of Textiles & Design of the Reutlingen University.

The process of restoring our body and brain from fatigue is directly depending on the quality of sleep. It can be determined from the report of the sleep study results. Classification of sleep stages is the first step of this study and this includes the measurement of biovital data and its further processing.In this work, the sleep analysis system is based on a hardware sensor net, namely a grid of 24 pressure sensors, supporting sleep phase recognition. In comparison to the leading standard, which is polysomnography, the proposed approach is a non-invasive system. It recognises respiration and body movement with only one type of low-cost pressure sensors forming a mesh architecture. The nodes implement as a series of pressure sensors connected to a low-power and performant microcontroller. All nodes are connected via a system wide bus with address arbitration. The embedded processor is the mesh network endpoint that enables network configuration, storing and pre-processing of the data, external data access and visualization.The system was tested by executing experiments recording the sleep of different healthy young subjects. The results obtained have indicated the potential to detect breathing rate and body movement. A major difference of this system in comparison to other approaches is the innovative way to place the sensors under the mattress. This characteristic facilitates the continuous using of the system without any influence on the common sleep process.

The paper discusses a new type of active sensors for continuous non-invasive monitoring of arterial blood pressure based on the local pressure compensation. Practical implementation of this sensor became possible due to the effective use of modern radio-electronic element base, focused on low power consumption, miniaturization of sizes and built-in computing and communication components (microcontrollers). These characteristics are inherent in modern wearable medical devices, so the sensor proposed can be reliably attributed to this category of appliances. The use of miniature measuring unit, its arrangement close to the working area and the possibility of processing digitized data in real time directly in the microcontroller of the sensor made it possible to carry out a unique method of pressure compensation at very small (1 mm$$^{2}$$ or less) areas of elastic surfaces, such as the surface tissues of the human body. The technical implementation of the principle of local pressure compensation in the form of a pneumatic sensor, features of blood pressure measurement regimes, the results obtained and some theoretical recommendations are considered in the paper. The problem of stability of measurement modes is discussed in detail. Experimentally discovered causes of stability disturbance are considered and their theoretical analysis is carried out. The conclusion summarizes the results and outlines the ways of further research.

Logical interaction between every pair of genes in a gene interaction network affects the observable behavior of any organism. This genetic interaction helps us to identify pathways of associated genes for various diseases and also finds the level of interaction between the genes in the network. In this paper, at first we have used three correlation measures, like Pearson, Spearman and Kendall-Tau to find the interaction level in a gene interaction network. Rough set can also be used to find the level of interaction, as well as direction of interaction between every pair of genes. That’s why in the second phase of the experiment, entropy measure & Rough set theory are also used to determine the level of interaction between every pair of genes as well as finds the direction of interaction that indicates which gene regulates which other genes. Experiments are done on normal & diseased samples of Colorectal Cancer dataset (GDS4382) separately. At the end we try to find out those interactions responsible for this cancer disease to take place. To validate the experimental results biologically we compare it with interactions given in NCBI database.

This paper presents an algorithm for decision support over two complementary clinical conditions given a large features data base. The algorithm is mainly divided in two parts, the first one aims at identifying relevant features from a large dimension data base using a heuristic method based on a discriminating power. The second part is a tool based on the Transferable Belief Model (TBM) which combines information extracted from the selected features to provide decision results with probabilities along with a result’s consistency measure so that decision could be made carefully. The proposed algorithm is tested on a downloaded feature data base. The TBM based decision support tool showed consistent results w.r.t provided outcomes by combining data from two relevant features identified after using the heuristic feature ranking method.

This paper presents a web viewer of Fetal Heart Rate (FHR) signals developed on HTML5/JavaScript. It provides an easy solution to remotely consult an FHR signal on a web browser without installing any specific software and it can be used either on a computer or on mobile device. There are three major applications of this tool. First, it is used to build up our FHR database used for research on signal processing and analysis. Secondly, it is used on our E-learning website e.RCF in order to train midwives and obstetricians to interpret FHR signals. At last, it could be used on telemedicine either on tele-monitoring to remotely check the fetal welfare, or on tele-expertise to enable practitioners to ask for specialists’ opinion. This viewer is designed to correspond to practitioners’ habits while including tools to ease the interpretation the FHR signal.

During the 2009 H1N1 influenza pandemic, there was rising concern about the potential contribution of international travel and global mass gatherings on the dynamic of the virus. The travel patterns after global mass gatherings can cause a rapid spread of infections. Studying the impact of travel patterns, high population density, and social mixing on disease transmission in these events could help public health authorities assess the risk of global epidemics and evaluate various prevention measures. There have been many studies on computational modeling of epidemic spread in various settings, but few of them address global mass gatherings. In this paper, we develop a stochastic susceptible-exposed-infected-recovered agent-based model to predict early stage of a disease epidemic among international participants in the annual Hajj or pilgrimage to Makkah (also called Mecca). The epidemic model is used to explore several scenarios with initial reproduction number R0 range from 1.3 to 1.7, and various initial proportions of infections range from 0.5% to 1% of total arriving pilgrims. Following an epidemic with one infectious per flight, the model results predict an average of 30% infectious and 20% exposed individuals in Makkah by the end of the arrival period. The proposed model can be used to assess various intervention measures during the arrival of international participants to control potential epidemics in different global mass gatherings.

When developing serious games for health, the main goal is to use game mechanisms in a way that the users decide to extend their playing time, complete all levels within the game, and thereby gain progression and intended learning with regard to disease management. One major concern when developing games for health is, therefore, the possibility of users who withdraw from the game before completed. A game, with a rapid descending popularity and users quitting gameplay early, fails to provide medical education to patients and is thus useless. For that reason, motivational game elements, such as in-game rewards, have been heavily used when designing serious games. This paper identifies and suggests several reinforcement mechanisms within serious games and explores how they can be applied in diabetes. The game called Diaquarium, a serious game for children with Type 1 diabetes, provides knowledge regarding how nutrition, blood glucose levels, and insulin interplay for this patient group. A prototype has been developed to demonstrate its concept and some game mechanisms with help of Unity 3D game engine and the C# programming language. Game design, requirements and suggestions for the project, were gathered through literature review, attending workshops, meetings and discussions with experts, as well as feedback from a related user group through a questionnaire. The questionnaire was distributed to an elementary school class, involving nine 9-year-old children. The questionnaire examined and collected feedback regarding the game outline, usability, and preferred reward mechanisms in the Diaquarium game. Despite a short period of testing and a limited test group with non-diabetic children, the game was recognized as attractive and moderately difficult within the potential user group. The analysis suggests that rewards are highly a matter of preference. Simultaneously, there were indications that some of the rewards were more favorable than others. It appears that rewards serving a purpose within the game, e.g., potentially effect progression in the gameplay, are more favorable than the opposite rewards serving no purpose. The findings were highly valued and taken into consideration during the design process of exploring the in-game rewards of the Diaquarium.

The notion of cross-boundary decision support has the potential to transform the design of future work environments for e-health through a connected system that allows for harnessing of healthcare information and expert knowledge across geographical boundaries for more effective decision-making. The trouble, however, is that the use of healthcare information in decision-making usually occurs within the context of a complex structure of clinical work practices that is often shaped by a wide range of factors, including organisational culture, local work contexts, socially constructed traditions of actions, experiences and patients’ circumstances. They vary across geographical and organisational boundaries, and have remained to date largely unaccounted for in the design of e-health systems. As a result, achieving the e-health vision of ‘open’ clinical decision support requires a rethinking of key clinical and organisational processes in a manner that accommodates clinical work practice as a fundamental part of how clinicians work and make decisions in real-world settings. Drawing on the theories of human activity system and situation awareness as well as the belief-desire-intention architecture in AI, this paper presents the design of an awareness environment for cross-boundary clinical decision support in e-health that takes account of the concept of work practice as a design requirement. The proposed system shows that incorporating practice information into the design of e-health systems enhances their usefulness for ‘open’ clinical decision support.