Wireless Mobile Communication and Healthcare

Early Warning Score (EWS) systems are a common practice in hospitals. Health-care professionals use them to measure and predict amelioration or deterioration of patients’ health status. However, it is desired to monitor EWS of many patients in everyday settings and outside the hospitals as well. For portable EWS devices, which monitor patients outside a hospital, it is important to have an acceptable level of reliability. In an earlier work, we presented a self-aware modified EWS system that adaptively corrects the EWS in the case of faulty or noisy input data. In this paper, we propose an enhancement of such data reliability validation through deploying a hierarchical agent-based system that classifies data reliability but using Fuzzy logic instead of conventional Boolean values. In our experiments, we demonstrate how our reliability enhancement method can offer a more accurate and more robust EWS monitoring system.

Smartphone-based assessments have been considered a potential solution for continuously monitoring gait and mobility in mild to moderate Parkinson’s disease (PD) patients. Forty-four PD patients from cohorts 4 to 6 of the Multiple Ascending Dose (MAD) study of PRX002/RG7935 and thirty-five age- and gender-matched healthy individuals (i.e. healthy controls - HC) in a separate study performed smartphone-based assessments for up to 24 weeks and up to 6 weeks, respectively. The assessments included “active gait tests”, where all participants were asked to walk for 30 s with at least one 180\(^\circ \) turn, and “passive monitoring”, in which subjects carried the smartphone in a pocket or fanny pack as part of their daily routine. In total, over 6,600 active gait tests and over 30,000 h of passive monitoring data were collected. A mobility analysis indicates that patients with PD are less mobile than HCs, as manifested in time spent in gait-related activities, number of turns and sit-to-stand transitions, and power per step. It supports the potential use of smartphones for continuous mobility monitoring in future clinical practice and drug development.

Rehabilitation from cardiovascular disease (CVD) usually requires lifestyle changes, especially an increase in exercise and physical activity. However, uptake and adherence to exercise is low for community-based programmes. We propose a mobile application that allows users to choose the type of exercise and compete it at a convenient time in the comfort of their own home. Grounded in a behaviour change framework, the application provides feedback and encouragement to continue exercising and to improve on previous results. The application also utilizes wearable wireless technologies in order to provide highly personalized feedback. The application can accurately detect if a specific exercise is being done, and count the associated number of repetitions utilizing accelerometer or gyroscope signals Machine learning models are employed to recognize individual local muscular endurance (LME) exercises, achieving overall accuracy of more than 98%. This technology allows providing a near real-time personalized feedback which mimics the feedback that the user might expect from an instructor. This is provided to motivate users to continue the recovery process.

The purpose of this research is to explore the factors affecting intention to use a mobile application for mental health in South Korea. Based on the Health Belief Model and Extended Technology Acceptance Model, this research aims to advance our understanding of mobile app adoption for mental health. A total of 218 men and women participated in an online survey. Results showed that perceived usefulness and perceived ease of use had significant effects on all stages of behavioral intention: app subscription, information seeking, information sharing, and following recommendations. Subjective norm and output quality were also significant predictors for intention to use a mobile app. Results provide useful insights for utilization of mobile apps to address mental health issues in Korean society.

An 8-channel ultra low power programmable wireless ExG (ECG, EMG and EEG) system-on-chip (SoC) design for bio-signal processing applications is presented in this paper. The proposed design consists of a capacitive coupled programmable gain instrumentation amplifier (CC-PGIA) with an improved transconductance of amplifier. A 12-bit programmable hybrid SAR-Cyclic analog-to-digital converter (ADC) is introduced for improved performance and low power consumption that consists of a 6-bit SAR ADC (SADC) followed by a 6-bit cyclic ADC (CADC). The remaining blocks implemented in the SoC are programmable low pass filter (PLPF), programmable wireless transmitter (PWT), power management unit (PMU) and a digital block. The proposed programmable wireless ExG (PW-ExG) design is implemented in 180 nm standard CMOS process with a core area of 4 mm². The performance parameters are found to be, power consumption of 286 µW @ 0.6 V supply voltage, input referred noise voltage of 0.96 µV_rms over 0.5 Hz–1 kHz range, gain of 30–65 dB and signal-to-noise-and-distortion ratio (SNDR) of 69.2 dB.

Recently, it has been proposed, that nanodevices can be injected in the human body and perform non-invasive medical diagnostics. However, due to their small size, a plethora of such nanodevices need to be used in practical applications, thus, creating a nanonetwork, which collects the information and communicates with out-of-body nodes. For these networks, several models have been proposed for the THz channel in the in-vivo scenario. Most of them are based on well-defined theories and physical laws, while some of them are based on experiments. In this paper, we review the state-of-the-art of channel modeling of in-vivo communications in the THz band and discuss future trends and research challenges.

The sense of touch can be used for sensory substitution, i.e., to represent visual or auditory cues to impaired users. Sensory substitution often requires the extensive training of subjects, leading to exhaustion and frustration over time. The goal of this paper is to investigate the ability of the subjects to recognize alphanumeric letters on 3 × 3 vibration array, where the subjects can fully personalize the variables including spatial location, vibratory rhythm, burst duration and intensity. We present a vibrotactile device for delivering the spatiotemporal letter patterns while maintaining the high level of expressiveness. The results prove that this system is an effective solution with a low cognitive load for visually/auditory impaired people and for any context that would benefit from leaving the eyes/ears free for other tasks.

People in many professions suffer from low back pain (LBP) due to wrong movements. Although this is anticipated by occupational medicine, the quality of evidence is low, since little objective measurements about the spine position in daily-use exist. The paper presents an ultra-flat posture monitoring system based on low-cost acceleration sensors, which can be very efficiently be used to measure the posture of the spine. First experiments (lab-based and in daily-use) showed a deviation of approximately 1° with a low standard deviation. Innovation is the suitability for daily-use by sensors having a height of 2,5 mm that allow a seamless usage even during positions applying pressure to the back such a leaned sitting on a chair.

Blood glucose self-monitoring plays an essential role in the life of diabetic people. A regular control helps diabetic persons to avoid acute complications, e.g. hypoglycaemic coma, and can reduce the risk of long-term consequences of diabetes. The implementation and usage of wireless technologies, e.g. NFC, in smartphones are a big step forward for diabetes home monitoring. Near Field Communication (NFC) is a wireless technology which allows the transmission of data and energy over short distances. The transmitted energy can be used for energy harvesting and in conjunction with low power electronic smart sensor solution reduced in size, weight and costs can be realized. We developed a smart glucose meter based on an amperometric measurement. The prototype is powered by the NFC interface of a smartphone. A user friendly mobile app completes the smart sensor system. The measured blood glucose is visualized on the smartphone and is stored in a diary automatically.

In the fitness and health fields, wearable sensors generate massive amount of information in big data. The machine learning techniques use the data to assess individuals’ health in real time and identify trends that may lead to better diagnoses and treatments. Applying efficient algorithms to learn from data can aid physicians to evaluate the state of human actions and diagnose the illnesses. The process of discerning valuable information from wearable sensors is a non-trivial task and is an on-going research area. Many research areas have focused on machine learning-based approaches to sensor data for better understanding and meeting people’s needs. However, there are different challenges such as runtime complexity and the number of functions calls associated with these approaches limit us to reach an acceptable accuracy level. To reduce the computational costs of the feature extraction and classification, a novel algorithm is proposed to analyze the variations in the periodic signals. It reduces the learning efforts by detecting any significant changes in the signal. We used the idea of pheromone trail employed in the ant colony optimization algorithm to keep track of the signal updates. The findings of this paper enable the design of a highly effective real-time predictive model for wearable applications.

Health-related quality of life (HRQOL) is a useful indicator that rates a person’s activities in various physical, mental and social domains. Continuously measuring HRQOL can help detect the early signs of declines in these activities and lead to steps to prevent such declines. However, it is difficult to continuously measure HRQOL by conventional methods, since its measurement requires each user to answer burdensome questionnaires. In this paper, we propose a simplified HRQOL measurement method for a continuous HRQOL measurement which can reduce the burden of questionnaires. In our method, sensor data from smart devices and the questionnaire scores of HRQOL are collected and used to construct a machine-learning model that estimates the score for each HRQOL questionnaire item. Our experiment result showed our method’s potential and found effective features for some questions.

Analysis of human activity, e.g., by tracking and analyzing motion information or vital signs became lots of attention in medical as well as athletic appliances during the last years. Nonetheless, comprehensive and labeled datasets containing human motion information are only sparsely accessible to the public. Especially qualitatively labeled datasets are rare, although they are of great value for the development of concepts concerning qualitative motion assessment, e.g., to avoid injuries during athletic workouts or to optimize a training’s success.

Therefore, we provide an open and qualitative as well as quantitative labeled dataset containing acceleration and rotation data of 8 different body weight exercises, conducted by 26 study participants. It encompasses more than 11,000 exercise repetitions of which we extracted 8,576 into individual segments. We believe, that due to its structure and labeling our work is suitable to serve for development, benchmarking, and validation of new concepts for human activity recognition and qualitative motion assessment (Publication notes: The dataset will be published at http://​github.​com/​andrebert/​body-weight-exercises together with this paper’s presentation on the MobiHealth conference 2017, taking place in Vienna, 14–16 November.).

In this paper, we present Watchful-Eye, a 3D skeleton-based system to monitor a physically disabled person using a cane as a mobility aid. Watchful-Eye detects fall occurrences using skeleton tracking with a Microsoft Kinect camera. Compared to existing systems, it has the merit of detecting various types of fall under multiple scenarios and postures, while using a small set of features extracted from Kinect captured video streams. To achieve this merit, we followed the typical machine learning process: First, we collected a rich fall detection dataset. Second, we experimentally determined the most relevant features that best-distinguish fall from non-fall frames, and the best performing classifier. As we report in this paper, the offline evaluation results show that Watchful-Eye reached an accuracy between 87.2% and 94.5% with 5.5% to 12.8% error rate depending on the used classifier. Furthermore, the online evaluation shows that it can detect falls with an accuracy between 89.47% and 100%.

This work presents a physical and cognitive training program, based on virtual reality technologies, designed with the aim of preventing the occurrence of symptoms of dementia in elderly with Mild Cognitive Impairment (MCI). The system foresees a physical task to be performed on a cycle-ergometer and two virtual environments for cognitive stimulation. In this paper, results of different validation phases conducted on both healthy and MCI subjects are described. The presented validation path allowed to implement, in parallel, the two current versions of the setup: the former, optimized to assess the efficacy of the intervention in a randomized clinical trial, which will take place in the next future, and the latter, more experimental, which foresees the employment of immersive environments to increase subjects’ engagement and motivation.

The use of mobile health together with the Internet of Things (IoT) technology and wireless networks have the potential of reshaping the healthcare systems towards the patient-centred and preventative ones. Better empowered patients which are familiar with smart technology represent a viable way for raising the quality of the self-management of health. Usability is a key factor for a successful acceptance of mHealth solutions. This paper presents the results of the heuristic evaluation of two mHealth apps that support self-healthcare revealed several important usability problems which have to be fixed in the further versions.

Technology can play a key role in support of the needs of the ageing population. In this direction, the rapid development of the ICT, and in particular mobile technologies, offers an important opportunity to address the development of an integrated solution to support active and healthy ageing. Whilst technology can potentially have a significant impact on health and wellbeing, to date uptake of digital health technologies has been problematic in a number of wide-scale studies. Literature has cited confidence, the stigmatizing aesthetics of products, meaningfulness of technology in the broader context of the persons’ life, ease of use and integration into everyday routines as important factors of non-acceptance. With the aim of overcoming the above limitation, we have gathered a multi-disciplinary consortium to develop an integrated solution that, strongly leveraging user participation and co-design as well as state-of-the-art technologies, offers a virtual coach service to elderly people so that they can maintain wellbeing and independence. The solution, in addition to being multi-technology, has the ambition of addressing wellbeing in a holistic manner taking into consideration several dimensions. NESTORE has started in September 2017 and will last three years. NESTORE involves 16 partners from 7 European countries. The paper presents the approach to the research and the envisaged results.

Clinical assessment scales for specific medical subareas include domain knowledge that may not be of general awareness among practitioners, hindering the adoption of best practices. In this context, we propose a pocket guide for comprehensive geriatric assessment as a mobile application. The GeriatricHelper is an Android mHealth application developed under an iterative, User-Centered Design approach. Feedback from a broad set of users including domain experts has been obtained throughout and a functional prototype is currently being tested in a Portuguese hospital, allowing for any clinician to apply the otherwise experts-limited geriatric assessment.

Life expectancy for some Cystic Fibrosis (CF) patients is rising and new complications and procedures are predicted. Subsequently there is need for education and management interventions that can benefit CF adults. This paper proposes a CF patient passport to record basic medical information through a smartphone application (app), giving the patient access to their own data. It is anticipated that such an app will be beneficial to patients when travelling abroad and between CF centres. This app is designed by a CF multidisciplinary team to be a lightweight reflection of a current patient file. The passport app is created using PhoneGap so that is can be deployed for both Android and iOS devices. The app is introduced to seven participants as part of a stress test. The app is found to be usable and accessible. The app is now being prepared for a pilot study with adult CF patients.

Among others, location changes and activity level are indicators for state changes of patients suffering from affective disorders such as Bipolar disorder, Borderline personality disorder or depression. It is a common means to assess this information via self-report questionnaires. Usually, these are sent out either randomly throughout the day or at fixed points in time. However, this might lead to missing records of location changes. We propose to rely on event-triggers: send out self-report prompts when a location change is automatically detected. We enhanced the ESMAC application by a location change detection event. Then, we created three different study configurations for each trigger type: random, time-based, and event-based. In a three-week within-subject study we let subjects experience each trigger type in randomized order. We found statistically significant differences in favor of the event-triggers in terms of number of prompts, response rate, prompts after detected location changes, and prompts after detected activity changes. We conclude that event-triggers based on a location change detection shall be used as trigger type for experience sampling studies focussing on location or activity changes.

Biometrics refer to unique measurable characteristics and information regarding individual’s health, physical or mental condition and can be used to uniquely authenticate or verify a person’s identity. They can be sorted in physiological such as fingerprints, palm print, face recognition, iris recognition, retina and DNA and behavioral such as typing rhythm (i.e. signature) and voice and can be described based on the uniqueness, potential change with time (i.e. facial changes), the feasibility to be collected (i.e. fingerprints) and the purposes of usage. In this work we study the use of a biometric technology for eHealth. We present the SpeechXRays project initiative that aims to provide a solution combining the convenience and cost-effectiveness of face and voice biometrics, achieving better accuracies by combining it with video, and bringing superior anti-spoofing capabilities. We explain how a novel user interface biometric platform is designed and adapted, for an eHealth use case, to enable secure access for medical specialists, nurses and patients to a collaborative eHealth platform that provides access to clinical and health related data within and possible outside a hospital. This is the first study, in the field, that gathered all necessary requirements (for a voice/face biometric system) and provides a formative evaluation and implementation of the SpeechXrays system user interface, for both end users and administrators, following a user-centered design approach, based on the holistic consideration of the user experience and the technical implication and functional requirements of the platform.

Telemedical consultation systems are emerging as a viable medium for patient-doctor interaction in a number of medical specialties. Such systems are already prevalent in fields like cardio diagnosis and it is still very nascent in the field of ophthalmology. But with the emergence of affordable and high quality remote-control cameras, a host of new possibilities have opened up. In this paper, we have developed innovative gaze alignment techniques for ensuring Mutual Gaze, Gaze Awareness and Gaze following. The system is shown to work effectively even for interactions that are as complex as involving multiparty consultations involving remotely located patients through the use of a mobile telemedicine network and general physician/physician-assistant and specialist ophthalmologist.

The efficiency of a biometric system is identified by the detection error tradeoff (DET) curve, which is a visual characterization of the trade-off between the False Acceptance Rate (FAR) and the False Rejection Rate (FRR). A DET curve is a plot of FAR against FRR for various threshold values, t. FRR refers to the expected probability that two mate samples (samples of the same biometric trait obtained from the same user) will be falsely declared as a non-match whereas FAR is the expected probability that two non-mate samples will be incorrectly recognized as a match. The threshold t defines how much the biometric characteristics must be similar, in order to make a positive comparison, so it measures the correspondence between characteristic to check and template stored in the database. By elevating the threshold, the risk that not authorized users can fool the system diminishes, but, on the other hand, it is more probable that some authorized users can sometimes be refused. In this work, we present the results for SpeechXRays multi-modal biometric system that uses audio-visual characteristics for user authentication in an eHealth platform for osteoarthritis management. Using the privacy and security mechanism provided by SpeechXrays based on audio and video biometrics medical personnel is able to be verified and subsequently identified to the eHealth application for osteoarthritis.

We designed, developed, and evaluated a novel system, QuantifyMe, for novice self-experimenters to conduct proper-methodology single-case self-experiments in an automated and scientific manner using their smartphones. In this work we evaluate its use with four different kinds of personalized investigations, examining how variables such as sleep duration and regularity, activity, and leisure time affect personal happiness, stress, productivity, and sleep efficiency. We describe lessons learned developing the system, and recommendations for its improvement, as well as its potential for enabling personalized insights to be scientifically evaluated in many individuals.

Electromyographic (EMG) signal is playing an important role on hand function training as a neuromuscular rehabilitation tool. Various pattern recognition algorithms (PRAs) have been compared and evaluated in previous research, and Linear Discriminant Analysis (LDA) showed the higher offline accuracy for motion classification. However, it is rarely of comparison for different types of Discriminant Analysis (DA), and the surface electrodes are common methods for signal acquisition. This paper proposes to evaluate the offline performance of LDA and other types of DA, and using Myo armband for recording signals. The offline data was acquired by Myo armband, processing recognizing the data in BioPatRec, an open source platform for motion classification and hand prosthetics control. From the results of average offline accuracy, training time, and testing time of the five types, LDA and Quadratic Discriminant Analysis (QDA) have the better performance than others, and LDA is the fastest algorithm with simple computing.

Monitoring plantar load conditions becomes useful in many health care fields, e.g. podiatric and orthopedic applications, rehabilitation tools, sports and fitness training tools, and in-field diagnosis and prevention tools for posture, balance, loading and contact times monitoring. IEE target is to provide a single insole-solution for daily usage in order to acquire information on the plantar load distribution for health prophylaxis in a large range of different shoe configurations. In this paper, we introduce for the first time a new High-Dynamic (HD) multi-cell smart insole sensor enabling advanced real-time foot plantar pressure monitoring applications. The in-situ measurement of the dynamic plantar load distribution provides an important new source of information that can be combined with traditional monitoring systems often based on accelerometer and gyroscope sensors. In fact, the new smart insole as presented here, facilitates the discovery in an early phase of any biomechanical mismatch in the walking or running gait of its user. Specific datasets have been recorded from a representative healthy population with different monitoring tools, i.e. force plate, pressure matrix and our new smart insole. The aim was to study the similarity of measurements recorded by each system on a defined measurement protocol. It is shown that the new monitoring device provides a competitive methodology to measure static and dynamic foot plantar pressure distribution. The system flexibility and robustness enable the development of new real-time applications, such as high peak pressure detection for diabetics, activity tracking, etc. The paper is organized as follows: we provide in Sect. 1 an overview of challenges and opportunities around foot pressure monitoring and discuss the sensing capabilities. Then we give a description of the new smart insole designed by IEE in Sect. 2. Next we define in Sect. 3 the measurement protocol based on 3 different systems, followed in Sect. 4 by a comparison of their efficiency and reliability. Finally, Sect. 5 provides related works and Sect. 6 concludes the paper.

Haptic perception plays a major role when vision and audition are partially or fully impaired. Therefore, this paper tries to give a brief overview on humans’ sensitivity distribution in perceptual space. During our experiments, a wearable sleeve with 7 vibro-actuators was used to stimulate subjects arm to convey haptic feedback. The basic research questions in this study are: (1) whether humans’ perception linearly correlated with the actuation frequency, haptic feedback in our scenario (2) humans’ ability to generalise templates via the wearable haptic sleeve. Those findings would be useful to increase humans’ perception when humans have to work with fully or partially impaired perception in their day-to-day life.

The aim of the present work is to introduce SHOULPHY: a digital application, which includes a rehabilitation protocol for the treatment of Shoulder Impingement Syndrome (SIS). SHOULPHY, short for Shoulder Physiotherapy, represents a valid contribute for physicians allowing for the creation of a patient-centred physiotherapic program and remote monitoring patient’s adherence to it, both in clinics and daily life. The application permits quantitative and effective evaluation of the therapeutic activity and functional level, through the use of wearable devices. The final purpose is to facilitate the functional recovery and maintenance of the physical level gained through the rehabilitation program, allowing for a complete return to sport and ordinary activities.

Motor peculiarity is an integral part of the schizophrenia disorder, having various manifestations both throughout the phases of the disease, and as a response to treatment. The current subjective non-quantitative evaluation of these traits leads to multiple interpretations of phenomenology, which impairs the reliability and validity of psychiatric diagnosis. Our long-term objective is to quantitatively measure motor behavior in schizophrenia patients, and develop automatic tools and methods for patient monitoring and treatment adjustment. In the present study, wearable devices were distributed among 25 inpatients in the closed wards of a Mental Health Center. Motor activity was measured using embedded accelerometers, as well as light and temperature sensors. The devices were worn continuously by participants throughout the duration of the experiment, approximately one month. During this period participants were also clinically evaluated twice weekly, including patients’ mental, motor, and neurological symptom severity. Medication regimes and outstanding events were also recorded by hospital staff. Below we discuss the general framework for monitoring psychiatric patients with wearable devices. We then present results showing correlations between features of activity in various daily time-windows, and measures derived from the psychiatrist’s clinical assessment or abnormal events in the patients’ routine.

The spatio-temporal parameters of gait can reveal early signs of medical conditions affecting motor ability, including the frailty syndrome and neurodegenerative diseases. This has brought increasing interest into the development of wearable-based systems to automatically estimate the most relevant gait parameters, such as stride time and the duration of gait phases. The aim of this paper is to investigate the use of body-worn accelerometers at different positions as a means to continuously analyze gait. We relied on a smart shoe to provide the ground truth in terms of reliable gait phase measurements, so as to achieve a better understanding of the signal captured by body-worn sensors even during longer walks. A preliminary experiment shows that both trunk and thigh positions achieve accurate results, with a mean absolute error in the estimation of gait phases of \(\sim \)12 ms and \(\sim \)31 ms, respectively.