Purpose: Limited access to specialist expertise in point-of-care ultrasound (POCUS) in rural areas may adversely affect patient care and healthcare systems by increasing reliance on costly imaging modalities (e.g., computed tomography or magnetic resonance imaging [MRI] and unnecessary patient transfers to specialized centers. Telemedical support represents a promising strategy to address this gap. Methods: In this block-randomized controlled trial with allocation concealment, a total of 358 patients requiring ultrasound were assigned to two POCUS groups: 184 patients received standard POCUS without teleconsultation, and 174 received POCUS supported by remote experts via telemedicine. All examinations were performed by the most experienced available local providers. Standardized post-examination questionnaires were administered to assess perceptions of the diagnostic process. Results: No statistically significant differences were observed between telemedicine-assisted POCUS and standard POCUS. The study also provides insights into the feasibility and diagnostic performance of teleconsultation-supported ultrasound in real-world clinical settings. MRI utilization was significantly lower in the teleconsultation group (P=0.002). Conclusion: Telemedicine-assisted POCUS demonstrated acceptability and comparable care outcomes relative to standard practice. Its potential to reduce reliance on high-cost diagnostic modalities supports its relevance as a scalable and efficient care model.

Detection and prediction of the onset of seizures are among the most challenging problems in epilepsy diagnostics and treatment. Small electronic devices capable of doing that will improve the quality of life for epilepsy patients while also open new opportunities for pharmacological intervention. This paper presents a novel approach using machine learning techniques to detect seizures onset using intracranial electroencephalography (EEG) signals. The proposed approach was tested on intracranial EEG data recorded in rats with pilocarpine model of temporal lobe epilepsy. A principal component analysis was applied for feature selection before using a support vector machine for the detection of seizures. Hjorth's parameters and Daubechies discrete wavelet transform coefficients were found to be the most informative features of EEG data. We found that the support vector machine approach had a classification sensitivity of 90% and a specificity of 74% for detecting ictal episodes. Changing the epoch parameter from one to twenty-one seconds results in changing the redistribution of principal components' values to 10% but does not affect the classification result. Support vector machines are accessible and convenient methods for classification that have achieved promising classification quality, and are rather lightweight compared to other machine learning methods. So we suggest their future use in mobile devices for early epileptic seizure and preictal episode detection.

(1) Background: Unclear sonographic findings without adequate specialist expertise in abdominal ultrasound (AU) may harm patients in rural areas, due to overlooked diagnoses, unnecessary additional imaging (e.g., CT scan), and/or patient transport to referral expert centers. Appropriate telemedical sonography assistance could lead to corresponding savings. (2) Methods: The study was designed as a randomized trial. Selected study centers performed AU with the best local expertise. Patients were selected and monitored according to the indication that they required AU. The study depicted three basic scenarios. Group 1 corresponds to the telemedically assisted cohort, group 2 corresponds to the non-telemedically assisted cohort, and group 3 corresponds to a telemedically supported cohort for teaching purposes. The target case number of all three groups was 400 patients (20 calculated dropouts included). (3) Discussion: This study might help to clarify whether telemedicine-assisted ultrasound by a qualified expert is non-inferior to presence sonography concerning technical success and whether one of the interventions is superior in terms of efficacy and safety in one or more secondary endpoints. Randomization was provided, as every patient who needed an AU was included and then randomized to one of the groups. The third group consisted of a lower number of patients who were selected from group 1 or 2 for teaching purposes in case of rare diseases or findings. (4) Conclusions: The study investigates whether there are benefits of telemedical ultrasound for patients, medical staff, and the health care system.

Abstract Background The duration of stays in hospitals have decreased by almost 50% to an average of 7.2 days in 2021 compared to 1992 whilst reliance on internet-based health information has increased. This trend raises concerns about potential misinterpretations and the need for enhanced post-hospital support. Methods This proof-of-concept study established a chat-based recovery counseling service providing nursing expertise and digital counseling options to patients within 7 days after discharge from hospital. Therefore, real nursing professionals where available to respond to patient queries and questions. A chatbot assisted the counselor by suggesting potential responses based on the patient's questions. This chatbot was trained using the expertise of nursing professionals. The study aimed to assess patients' acceptance, nursing professionals' commitment, and patients' willingness to contribute chat interactions and chat content for further research and tool developments. Surveys and interviews were conducted with recovery counselors to explore their attitudes towards digitalization, self-assessed digital competencies, and potential changes to the service structure. Results Within one year, 247 patients across five stations (surgery, oncology, and orthopedics) were introduced to the digital recovery counseling service. Several patients declined to participate in the study, with the main reason for refusal voluntarily given by patients being the lack of a PC in the household (68.86%). Patients in the 51–70 age group showed the highest positive responses. Out of the consenting patients, all but one agreed to donate their chat history, and 21 of the participants registered on the platform. Neurosurgery patients exhibited the highest interest, while oncology patients had limited interest due to pre-existing information. Recovery counselors reported varying degrees of improved digital competencies. The chatbot presented challenges for uniform training across specialties due to its limited dataset, emphasizing the need for a broader question set for comprehensive training. Conclusions The study shows patients acceptance for digital counselling via chat, emphasizing also nursing staff's readiness for digital expansion. Integrating digital training is vital to overcome initial doubts. Patients willingly donate data with clear information, showcasing the chatbot's potential as a nursing expert system. Expanding chat-based nurse counselling may enhance post-inpatient advice, necessitating future considerations for broader deployment.

Background Transfer transports in the case of unclear sonographic findings without adequate specialist expertise in transcutaneous ultrasound (TUS) by a qualified colleague are associated with considerable and increasing costs for the healthcare system. Ambulance transport and the corresponding waiting times as well as the monitoring of patients, some of whom are severely impaired, are to be regarded as labor-, time- and cost-intensive in this context. Appropriate telemedical sonographic assistance could lead to corresponding savings here.

Many studies showed the feasibility of detecting Freezing of Gait (FOG) of Parkinson’s patients by using several numbers of inertial sensors worn on the body and in back-end computing power. This work uses machine learning approaches for analyzing the data of one single body-worn inertial sensor system to classify and detect FOG. Long-Short-Term-Memory (LSTM) is employed as the FOG detection algorithm and the Daphnet (FOG and normal gait) dataset provides the data for model training and testing in this paper. The model considers raw data from three channels of the acceleration sensor mounted on the patient’s shank and ignores all other data from other sensors. The model is patient dependent and uses sensitivity and specificity metrics to evaluate the model’s performance. In this paper, we propose a novel padding method that is applied to the windows of FOG and non-FOG with zero overlaps on the training set and adapts the padding to the individual regions. This method produces windows of only one type of data and label. The proposed padding method reduces the padding amount by two orders of magnitude compared to bigger batch sizes in the sequence splitting method offered by MATLAB 2019a. The padding amount is independent of the batch size. Raw data is fed to the model in the testing mode without any pre-processing or data transformation. The standard rolling window generates fixed-size windows for the test set without overlap and the higher amount of FOG or Normal walking data which defines the label of the individual window. The model for one-second long windows applied in this work outperformed the literature results with a sensitivity of 92.57% and a specificity of 95.62% compared to 82% and 94% reported by Masiala et al.

Robotic-assisted systems have been playing a key role in improving and speeding up motor recovery during stroke rehabilitation therapies. This paper presents an approach to determine velocity patterns based on the analysis of the EMG muscular condition of the hand. To this purpose, we conducted an experimental protocol with 18 subjects participating as volunteers, with the aim of acquiring EMG signals for three levels of the muscular condition: non-fatigue, transition-to-fatigue, and fatigue. Artificial Neural Networks (ANN) were trained to identify the aforementioned muscular condition levels, while a Sugeno-Type Fuzzy Inference system was used to determine the velocity based on the output of the ANN classifiers. Results indicate the proposed approach can be used for the accurate modulation of pinch-grip therapies according to the muscular condition. These are promising results towards the development of EMG-driven robotic-assistance rehabilitation therapies for stroke patients.

Stroke is the fourth most common cause of death and can lead complex and long-term disability. In this regard, robotic-based rehabilitation could be an alternative for motion recovery. In this research we study how myoelectric signals (EMG) could be used to identify the fingers/hand motion through pattern recognition techniques. To this purpose, we implemented an experimental protocol on three subject groups: (I) non-stroke without hand impairments, (II) stroke without hand impairments and (III) stroke with hand impairments. The subjects performed a set of hand therapies to improve the range of motion and dexterity. Several methods for feature extraction, ranking and classification from EMG signals were implemented and the performance in the motion identification was compared. Specifically, three ranking methods: Two-sample T-test with feature variances, Separability Index, and the Davies-Boulding Index were used to determine the relevance of the features. As a result, dimensionality reduction was achieved by selecting only 50 features out of 136 with a comparable performance. Also, we compared three different classifiers: LDA, KNN and SVM. On average, the KNN classifier obtained a performance of 0.87 followed by the SVM with 0.82 and LDA with 0.74. Experimental results showed that we are able to identify the hand movements from subjects with a stroke event (group III) with 0.85 of correct classification rate average, which seems a promising approach in robotic-based rehabilitation assistance. (C) 2019 Elsevier Ltd. All rights reserved.

Background: Mobile health (mHealth) could play an important role in assisting patients self-managing their asthma. Therefore we developed the myAirCoach mHealth system to aid self-management. We aimed to assess the effect of the myAirCoach system in addition to usual care on asthma control. Methods: In a randomized controlled trial in the Netherlands we included 30 patients with uncontrolled asthma using a staggered enrolment with 3-7 months follow-up. Patients received either ‘usual care’ or ‘usual care + self-management support via ‘myAirCoach’’. In addition, we performed a 3-month before-after study in 12 patients in the UK. Asthma control was measured with the Asthma Control Questionnaire (ACQ), with a minimal important difference (MID) of 0.5. Secondary outcomes were exacerbation rate and quality of life, measured by the mini Asthma Quality of Life Questionnaire (mAQLQ) with a MID of 0.5. The myAirCoach system consisted of an app, myAirCoach inhaler add-on, indoor air-quality monitor, physical activity tracker, home spirometer and FeNO device. Results: Asthma control improved in the Dutch intervention group compared to controls (ACQ-difference 0.70, p=0.006). A total of 4 severe exacerbations occurred in the intervention group compared to 12 in the control group (hazard ratio 0.22, 95%CI 0.07-0.71, p=0.011). Also quality of life improved significantly (mAQLQ difference 0.53, p= 0.04). In the UK patients, asthma control improved by 0.86 compared to baseline (p=0.007) and quality of life was 0.16 higher (p=0.64). Conclusion: The myAirCoach mHealth self-management system provides an improvement in asthma control and quality of life and a reduction in asthma exacerbation.

Millions of users voluntarily release private and business data at community platforms without considering potential impacts on their real lives that may come along with that. Being used for personalized advertisement or profiling, user data are of utmost importance for economic success of the platform. Hence, platform providers exploit all promising options to gather data while privacy seems partially to be a pain for them. Beside data voluntarily released by the user, there are techniques and methods to secretly gather more user data, e.g., by proper fusion of miscellaneous information such as analysis of websites visited or social games played. In this article we investigate obvious as well as concealed data gathering options of platform providers. By that we uncover the true detailedness of user data collected by social networks to document our key message, i.e., social networks know EVERYTHING about their users. Finally, we discuss why existing privacy protecting solutions cannot stand up with the threats and risks resulting from easygoing use of social networks.

We present a low-complexity framework for classifying elementary arm movements (reach retrieve, lift cup to mouth, and rotate arm) using wrist-worn inertial sensors. We propose that this methodology could be used as a clinical tool to assess rehabilitation progress in neurodegenerative pathologies tracking occurrence of specific movements performed by patients with their paretic arm. Movements performed in a controlled training phase are processed to form unique clusters in a multidimensional feature space. Subsequent movements performed in an uncontrolled testing phase are associated with the proximal cluster using a minimum distance classifier (MDC). The framework involves performing the compute-intensive clustering on the training data set offline (MATLAB), whereas the computation of selected features on the testing data set and the minimum distance (Euclidean) from precomputed cluster centroids are done in hardware with an aim of low-power execution on sensor nodes. The architecture for feature extraction and MDC are realized using coordinate rotation digital computer-based design that classifies a movement in (9n + 31) clock cycles, n being number of data samples. The design synthesized in STMicroelectronics 130-nm technology consumed 5.3 nW at 50 Hz, besides being functionally verified up to 20 MHz, making it applicable for real-time high-speed operations. Our experimental results show that the system can recognize all three arm movements with average accuracies of 86% and 72% for four healthy subjects using accelerometer and gyroscope data, respectively, whereas for stroke survivors, the average accuracies were 67% and 60%. The framework was further demonstrated as a field-programmable gate array-based real-time system, interfacing with a streaming sensor unit.

This paper reports an algorithm for the detection of three elementary upper limb movements, i.e., reach and retrieve, bend the arm at the elbow and rotation of the arm about the long axis. We employ two MARG sensors, attached at the elbow and wrist, from which the kinematic properties (joint angles, position) of the upper arm and forearm are calculated through data fusion using a quaternion-based gradient-descent method and a two-link model of the upper limb. By studying the kinematic patterns of the three movements on a small dataset, we derive discriminative features that are indicative of each movement; these are then used to formulate the proposed detection algorithm. Our novel approach of employing the joint angles and position to discriminate the three fundamental movements was evaluated in a series of experiments with 22 volunteers who participated in the study: 18 healthy subjects and four stroke survivors. In a controlled experiment, each volunteer was instructed to perform each movement a number of times. This was complimented by a seminaturalistic experiment where the volunteers performed the same movements as subtasks of an activity that emulated the preparation of a cup of tea. In the stroke survivors group, the overall detection accuracy for all three movements was 93.75% and 83.00%, for the controlled and seminaturalistic experiment, respectively. The performance was higher in the healthy group where 96.85% of the tasks in the controlled experiment and 89.69% in the seminaturalistic were detected correctly. Finally, the detection ratio remains close ( ±6%) to the average value, for different task durations further attesting to the algorithms robustness.

In this paper we present a methodology for recognizing three fundamental movements of the human forearm (extension, flexion and rotation) using pattern recognition applied to the data from a single wrist-worn, inertial sensor. We propose that this technique could be used as a clinical tool to assess rehabilitation progress in neurodegenerative pathologies such as stroke or cerebral palsy by tracking the number of times a patient performs specific arm movements (e.g. prescribed exercises) with their paretic arm throughout the day. We demonstrate this with healthy subjects and stroke patients in a simple proof of concept study in which these arm movements are detected during an archetypal activity of daily-living (ADL) - 'making-a-cup-of-tea'. Data is collected from a tri-axial accelerometer and a tri-axial gyroscope located proximal to the wrist. In a training phase, movements are initially performed in a controlled environment which are represented by a ranked set of 30 time-domain features. Using a sequential forward selection technique, for each set of feature combinations three clusters are formed using k-means clustering followed by 10 runs of 10-fold cross validation on the training data to determine the best feature combinations. For the testing phase, movements performed during the ADL are associated with each cluster label using a minimum distance classifier in a multi-dimensional feature space, comprised of the best ranked features, using Euclidean or Mahalanobis distance as the metric. Experiments were performed with four healthy subjects and four stroke survivors and our results show that the proposed methodology can detect the three movements performed during the ADL with an overall average accuracy of 88% using the accelerometer data and 83% using the gyroscope data across all healthy subjects and arm movement types. The average accuracy across all stroke survivors was 70% using accelerometer data and 66% using gyroscope data. We also use a Linear Discriminant Analysis (LDA) classifier and a Support Vector Machine (SVM) classifier in association with the same set of features to detect the three arm movements and compare the results to demonstrate the effectiveness of our proposed methodology. (C) 2014 Elsevier B.V. All rights reserved.

The authors present a user-centric design flow for ease of use for specifying Wireless Sensor Network applications even for heterogeneous hardware. The design flow provides very high abstraction and user guidance to refrain the user from implementation, deployment, and hardware details including heterogeneity of the available sensor nodes. Automatic event configuration is accomplished by using a flexible Event Specification Language (ESL) and Event Decision Trees (EDTs) for distributed detection and determination of real world phenomena. EDTs autonomously adapt to heterogeneous availability of sensing capabilities by pruning and subscription to other nodes for missing information. The authors analyze the approaches in theory and praxis. They present two of numerous simulated scenarios proving the robustness and energy efficiency of the approach while having learnt appropriate configuration properties that are required for correct sensing. They can deal with failing sensors despite performing pretty well in terms of accuracy and number of messages exchanged.