Ebook: pHealth 2019

pHealth 2019 is the 16th Conference in a series of scientific events bringing together expertise from medical, technological, political, administrative, and social domains, and even from philosophy or linguistics. It opens a new chapter in the success story of the series of international conferences on wearable or implantable micro and nano technologies for personalized medicine.

Starting in 2003 as a Dissemination Activity in the framework of a European Project on Wearable Micro and Nano Technologies for Personalized Health with personal health management systems, pHealth conferences have evolved to truly interdisciplinary and global events. Meanwhile, pHealth comprehensively represented in the conference series also covers technological and biomedical facilities, legal, ethical, social, and organizational requirements and impacts as well as necessary basic research for enabling the future proof care paradigms. Thereby, it combines medical services with public health, prevention, social and elderly care, wellness and personal fitness to establish participatory, predictive, personalized, preventive, and effective care settings. By this way, it has attracted scientists, developers, and practitioners from various technologies, medical and health disciplines, legal affairs, politics, and administration from all over the world. The conference brought together health services vendor and provider institutions, payer organizations, governmental departments, academic institutions, professional bodies, but also patients and citizens representatives.

Smart mobile systems such as microsystems, smart textiles, smart implants, sensor-controlled medical devices, and innovative sensor and actuator principles and techniques as well as related body, local and wide area networks up to cloud services have become important enablers for telemedicine and ubiquitous pervasive health as the next generation health services. Social media and gamification have added even further knowledge to pHealth as an eco-system.

OECD has defined four basic areas to be managed in the new care model: address the big data challenges; foster meaningful innovation; understand and address the potential new risks; and support concerted effort to un-silo communities for a virtual care future. The multilateral benefits of pHealth technologies for all stakeholder communities including patients, citizens, health professionals, politicians, healthcare establishments, and companies from the biomedical technology, pharmaceutical, and telecommunications domain gives enormous potential, not only for medical quality improvement and industrial competitiveness, but also for managing health care cost.

The pHealth 2019 conference thankfully benefits from the experience and the lessons learned from the organizing committees of previous pHealth events, particularly 2009 in Oslo, 2010 in Berlin, 2011 in Lyon, 2012 in Porto, 2013 in Tallinn, 2014 in Vienna, 2015 in Västerås, 2016 in Heraklion, 2017 in Eindhoven, and 2018 in Gjøvik. The 2009 conference brought up the interesting idea of having special sessions, focusing on a particular topic, and being organized by a mentor/moderator. The Berlin event in 2010 initiated workshops on particular topics prior to the official kick-off of the conference. Lyon in 2011 initiated the launch of so-called dynamic demonstrations allowing the participants to dynamically show software and hardware solutions on the fly without needing a booth. Implementing pre-conference events, the pHealth 2012 in Porto gave attendees a platform for presenting and discussing recent developments and provocative ideas that helped to animate the sessions. Highlight of pHealth 2013 in Tallinn was the special session on European projects' success stories, but also presentations on the newest paradigm changes and challenges coming up with Big Data, Analytics, Translational and Nano Medicine, etc. Vienna in 2014 focused on lessons learned from international and national R&D activities and practical solutions, and especially from the new EU Framework Program for Research and Innovation, Horizon 2020. Beside reports about technology transfer support and building ecosystems and value chains to ensure better time to market and higher impact of knowledge-based technologies, the acceptability of solutions, especially considering security and privacy aspects have been presented and deeply discussed. pHealth 2015 in Västerås addressed mobile technologies, knowledge-driven applications and computer-assisted decision support, but also apps designed to support elderly as well as chronic patients in their daily and possibly independent living. Furthermore, fundamental scientific and methodological challenges of adaptive, autonomous, and intelligent pHealth approaches, the new role of patients as consumers and active party with growing autonomy and related responsibilities, but also requirements and solutions for mHealth in low- and medium income countries have been considered. The pHealth2016 conference aimed at the integration of biology and medical data, the deployment mobile technologies through the development of micro-nano-bio smart systems, the emphasis on personalized health, virtual care, precision medicine, big bio-data management and analytics. The pHealth 2017 event in Eindhoven provided an inventory of the former conferences by summarizing requirements and solutions for pHealth systems, highlighting the importance of trust, and newly focuses on behavioral aspects in designing and using pHealth systems. A specific aspect addressed is the need for flexible, adaptive and knowledge-based systems as well as decision intelligence. pHealth 2018 established national and European satellite workshops, so completing the more theoretical consideration of the majority of the papers by organizational and practical experiences. Borrowing from good experiences of former events, pHealth 2018 responds to the national and regional needs for advancing the healthcare systems and its services to citizens and health professionals as well. In that context, communication and cooperation with national and regional health authorities, but also with the Gruppo Nazionale di Bioingegneria play a special role in the 2019 conference. Furthermore, and following an international trend, a special focus was dedicated to artificial intelligence (AI) and machine learning (ML) and their deployment for decision support.

Being organized under the patronage of the City of Genoa and the Linguria Regional Authority, the University of Genoa and especially the Department of Informatics, Bioengineering, Robotics and System Engineering (DIBRIS), Healthtrophy srl as a University of Genoa's Spin-Off, but – following a long-term tradition – also the Working Groups “Electronic Health Records (EHR)”, “Personal Portable Devices (PPD)” and “Security, Safety and Ethics (SSE)” of the European Federation for Medical Informatics (EFMI) have been actively involved in the preparation and realization of the pHealth 2019 Conference.

This proceedings volume covers 1 keynote, 2 of 4 invited talks presented to the conference, 36 oral presentations, and 7 short poster presentations from 141 authors, coming from 15 countries from all around the world. All submissions have been carefully and critically reviewed by at least two independent experts from other than the authors' home countries, and additionally by at least one member of the Scientific Program Committee. The performed highly selective review process resulted in a full papers rejection rate of more than 30% despite of the specific dedication of the addressed community in comparison with multi-topic conferences. This process guarantees a high scientific level of the accepted and finally published papers. The editors are indebted to the internationally acknowledged and highly experienced reviewers for having essentially contributed to the quality of the conference and the book at hand.

Both the pHealth 2019 Conference and the publication of the pHealth 2019 Proceedings at IOS Press would not have been possible without the aforementioned pecuniary and spiritual supporters and sponsors. This also includes the Italian Scientific Society of Biomedical Informatics, the IEEE Engineering in Medicine and Biology Society (EMBS), the Camber of Engineers Genoa, or the European Federation for Medical Informatics (EFMI) and standards developing organizations such as HL7 International, ISO/TC215 or CEN/TC251.

The editors are also grateful to the Members of the international Scientific Program Committee, but especially the dedicated efforts of the Local Organizing Committee members and their supporters for carefully and smoothly preparing and operating of the conference.

Bernd Blobel, Mauro Giacomini

(Editors)

The paper introduces a structured approach to transforming healthcare towards personalized, preventive, predictive, participative precision (P5) medicine. It highlights the promising methodological paradigm changes, accompanied by related organizational and technological ones. In the latter context, the deployment of artificial intelligence and autonomous systems is crucial beside miniaturization and mobility. Beside their opportunities, those advanced technologies also bear risks to be managed. Beside the relationships between technology and human actors, the behavior of intelligent and autonomous systems from a humanistic and ethical perspective is in the center of considerations. The different existing approaches for guaranteeing the intended properties are presented and compared for deriving a common set of necessary principles to be met for P5 medicine.

Development in the area of sensor technologies and subsequently applications within the Internet of Things allows the implementation of systems for continuous monitoring of human's vital parameters and daily activities. This development is welcomed since the population aged 65 and over is constantly increasing. Moreover, the number of seniors living alone is also increasing. The monitoring systems can contribute to the safety and security of elderly people and allow them to stay at home where they are used to live as long as possible. Application of various sensor types raises questions on the most suitable sensor data representation, not losing useful information, and also on the design of detection and evaluation algorithms. In the paper, we briefly present several existing approaches and explain why we decided to use the basic ideas coming from the area of behaviour informatics.

The penetration of digital platforms and ecosystem based business-model together with the use algorithm and machine leaning are changing the environment where pHealth takes place. Traditional pHealth is changing to Digital pHealth. This development brings new ethical, privacy and trust problems which have to solve to make Digital pHealth successful. In this paper ethical, privacy and trust problems in Digital pHealth are studied at conceptual level. Concerns caused by the use novel ICT-technology and regulatory environment are also discussed. The starting point is that the Digital pHealth as a system and its applications and algorithms should be ethically acceptable, trustworthy and enable the service user to set own context-aware privacy policies. Mutual trust is needed between application and all stakeholders. Solution proposed for trustworthy Digital pHealth include ethical design, policy based privacy management and on-line calculation of privacy and trust levels using proven mathematical methods. In the future, novel solutions such as algorithm based access control and data sharing, and algorithm based privacy prediction together with cryptography based blockchain seems to have potential to change the way privacy is managed in Digital pHealth. Technology alone cannot solve current privacy and trust problems. New regulations which not only give users of the Digital pHealth right to set personal privacy polies but also force pHealth service providers and platform owners to prove regulatory compliance of their services are needed.

Prevention and control of hospital and community acquired infections caused by multi drug resistant organisms (MDROs) are one major priority nowadays for health care systems worldwide. To improve actions and plans to tackle this problem, the creation of automated regional, national and international MDRO surveillance networks is a mandatory path for international health Institutions and Ministries. In this paper, the authors report on the surveillance system designed for the Abruzzo Region (Central Italy) to monitor the prevalence of MDROs in both infected and colonized patients, to verify appropriateness of antibiotic prescription in hospitalized patients and to interact with other national and sovra-national networks. Service Oriented Architecture (SOA) approach, different Healthcare Service Specification Project (HSSP) standards, local, national and international terminology and Clinical Document Architecture Release 2 (CDA R2) were adopted to design the overall architecture of this regional surveillance system. The Authors discuss the state of implementation of the project, itemizing specific design and implementation choices adopted so far and sketching next steps and reasons of some design and implementation choices, and indicate the next steps.

The constraints that physical rehabilitation exergames (PREGs) may impose on Player Experience (PX) evaluation should be identified from a physiotherapists' perspective. In this paper, we present the results of a qualitative study to identify the characteristics and constraints that are relevant to evaluate PX in PREGs. The study included semi-structured interviews conducted during two sessions with three physiotherapists from a local hospital. The collected data was analysed using the thematic content analysis method. The findings indicate that the PX evaluation constraints are related to (a) the rehabilitation context in which PREGs are employed; (b) the pursued rehabilitation goal (i.e., the capability of a PREG to assist the achievement of a rehabilitation goal); and (c) the characteristics of target patients, which may affect their experience and willingness to play. The findings of the study contribute to a comprehensive understanding of PX in PREGs. We concluded that the three groups of constraints may impact the three constructs of PX; i.e., context (rehabilitation context), player (patient) and game system (PREG system). Confirming the need to propose or extend PX models of entertaining games for the case of PREGs.

Despite using electronic medical records, free narrative text is still widely used for medical records. Such text cannot be analyzed by statistical tools and be proceed by decision support systems. To make data from texts available for such tasks a supervised machine learning algorithms might be successfully applied. In this work, we develop and compare a prototype of a medical data extraction system based on different artificial neuron networks architectures to process free medical texts in Russian language. The best F-score (0.9763) achieved on a combination of CNN prediction model and large pre-trained word2vec model. The very close result (0.9741) has shown by the MLP model with the same embedding.

Introduction: Cardiac rehabilitation (CR) is a multidisciplinary intervention that improves quality of life and reduces the risk of recurrent heart attack. Unlike all known benefits for CR, the patient participation in CR is low. Telerehabilitation has the potential to improve lifestyle and helps patients having long-term compliance with clinician advice. The objective of this study was the development of a web-based cardiac telerehabilitation platform to engage the post-myocardial infarction (MI) patients in self-management of disease.

Method: Development process of creating and evaluating a telerehabilitation platform included four phases: (1) need assessment, (2) design the prototype, (3) implement the cardiac telerehabilitation platform, (4) usability evaluation.

Result: Cardiac telerehabilitation platform consists of an Android–based application for patients and web-based dashboard for rehabilitation mentors. The modules of the application are daily self-assessment, weekly self-assessment, educational content, stress and sleep improvement skills, medication reminder, online chat, prescribed diet, prescribed physical activity and rehabilitation records. The self-assessment modules allow users to enter the data such as physical activity, diet, blood pressure, heart rate, and body weight. The patient data entries are interpreted in the system knowledge base and colored symbol feedbacks display for patients and mentors. In the dashboard, the mentors review the patient data entries and set the rehabilitation plan for next week. In a beta test of usability evaluation, the mean of SUS score for patients was 75.16, for clinicians was 73.33 and for medical informatics specialist was 72.33. These results showed that the usability of our system was at an acceptable level.

Conclusion: The cardiac telerehabilitation platform is a convenient tool for post-MI patients who cannot attend at outpatient cardiac rehabilitation centers for any reason.

During the last decade, we have experienced fast development of virtual reality technology combined with various sensors and applications in different fields. The devices and applications are more easily accessible for the broader public. In this article, we describe a feasibility study of an affordable personalized, immersive VR motor rehabilitation system with full body tracking. While virtual reality rehabilitation is a relatively new field, several applications were already proven more effective than traditional rehabilitation programs. The applied methods utilize VR headset HTC Vive and HTC trackers together witch inverse kinematics algorithms to provide full body tracking. For that, we provide a framework for individual body calibration. The main result of the study is a developed virtual environment with guided rehabilitation scenarios based on personalized body calibration. We have proven that this approach can be used in personalized rehabilitation programs.

The lowering costs of DNA sequencing and the diffusion of numerous Direct to Consumer Genetic Testing (DTC-GT) services have made genetic testing easily available to the general public who can buy them without any medical prescription or consultation. Nevertheless, the knowledge required to understand the provided results and their implications is still scarce in the general public. Starting from these considerations, we developed two mini-games and one serious game to increase people genetic literacy through experiential learning. The three games were tested for usability on a sample of 30 participants, 10 for each game, who were asked to report any positive or negative issue related to the games and to fulfill the Game Experience Questionnaire in order to evaluate their playing experience. Results from the three games show that players experienced moderate levels of immersion and flow, low levels of negative sensations, and a prevalence of positive emotions. In general, these encouraging results suggest that the proposed games are suitable to transmit genetic notions to the general public.

There is a worldwide increase in the rate of obesity and its related long-term conditions, emphasizing an immediate need to address this modern-age global epidemic of healthy living. Moreover, healthcare spending on long-term or chronic care conditions such as obesity is increasing to the point that requires effective interventions and advancements to reduce the burden of the healthcare. This research focuses on the early risk assessment of overweight/obesity using wearable technology. We establish an individualised health profile that identifies the level of activity and current health status of an individual using real-time activity and vital signs. We developed an algorithm to assess the risk of obesity using the individual's current activity and calorie expenditure. The algorithm was deployed on a smartphone application to collect wearable device data, and user reported data. Based on the collected data, the proposed application assesses the risk of obesity/overweight, measures the current activity level and recommends an optimized calorie plan.

The monitoring of vital signs in a dynamic environment is challenging. This work demonstrates an approach to estimate the respiratory rate (RR) under real-driving conditions by using two accelerometers for signal recording and de-noising. One accelerometer was attached to the seatbelt for recording respiratory movements; another one was attached to the left side of the car seat for recording noise. The frequency components of the noise were used to suppress the noise hidden in the signal. The performance of the proposed approach is evaluated for three testers under three driving conditions, i.e., engine on, flat road and uneven road. The estimated RRs for three testers are 11.54 ± 2.28 breaths per minute (bpm), 15.57 ± 5.77 bpm, and 9.63 ± 4.58 bpm. The median estimated RR for three testers are 12.08 bpm, 18.26 bpm, and 7.76 bpm, where the manually counted reference RRs are 12 bpm, 18 bpm, and 7 bpm respectively. The average difference between estimated RRs and reference RRs is 0.71 bpm for the condition engine on, 3.36 bpm for flat road, and 4.58 bpm for uneven road. The results exhibit the ability of the proposed approach to estimate RR under real-driving conditions.

Measuring the kinematics of human body movements is important for several biomedical and non-biomedical uses, such as rehabilitation, sports medicine, control of virtual reality systems, etc. This is typically performed employing accelerometers, electrogoniometers, electromagnetic sensors or cameras, which however are usually bulky, or can cause discomfort to the user, or are insufficiently accurate, or require expensive instrumentation. As an alternative to those state-of-the-art systems, stretchable piezocapacitive sensors based on dielectric elastomers (DE) represent a recently described competitive technology, which might enable wearable, lightweight and cost-effective devices. DE sensors consist of stretchable capacitors whose mechanical deformation causes a change of capacitance, which can be measured and related to linear or angular motions, depending on the sensors' arrangement. Here, we present a wearable wireless system able to monitor the flexion and torsion of the lumbar region of the back. The system consists of two DE sensors arranged on shoulder straps, and a custom-made wireless electronics designed to measure the capacitance of the sensors and calibrate them when the user wears them for the first time. We describe preliminary results related to the characterisation of the sensors and the electronics.

The hospitalisation of patients with Heart Failure (HF) represents an increasing problem for the healthcare system with more than 26 million worldwide suffering from this disease. Predictions demonstrate that the total health expenditure will increase by 127% in 2030. In Portugal, demographic changes caused by an ageing population are associated with an increase in HF incidence rate, forecasting 479.921 Heart Failure patients by 2035. In this paper, we present the smartBEAT solution that was developed to monitor Heart Failure patients so that physicians can early detect HF decompensation and prevent HF hospitalisations. SmartBEAT collects data from several sensors: weigh scale, blood pressures, physical activity bracelet – and transmits to the cloud where a decision support algorithm helps to detect acute episodes early. The system was evaluated during a pilot phase for two weeks with nine seniors, and later for 1-3 months with 38 seniors HF patients. Adherence to the evaluation protocol was high, and perceptions on wellbeing and control over the disease were considered positive. Moreover, healthcare professionals were overwhelmed with the patients' high adherence and found the usability of the portal high, and providing interesting information about patients' health status.

Obesity is a chronic disease characterized by the accumulation of body fat. School-age children obesity is one of the most serious public health challenges since it progressively becomes a risk factor in adulthood. Recent studies and technological innovations have demonstrated the feasibility of game-based interventions for promoting physical activity among children. Nevertheless, there is a gap in fitting the system specifications to specific user profiles. This paper aims to present the development of an adaptation component for a particular exergame based on wearable technology that measures heart rate to support a personalized tracking system of the physical activity. The employed methodology was the General Adaptivity Model (GAM) that provides guidelines for the designing process of adaptivity models, incorporating user modeling and personalization in existing or new interactive systems. For validation purposes, an experiment was conducted at a primary school with thirty subjects aged between five to seven years to test the effectiveness of a user adaptive system against a conventional interactive system for the promotion of physical activity. Results indicate that the developed system was able to change its behavior according to the variations of the heart rate and therefore encouraging users to perform higher/lower physical activity levels.

Melanoma is the deadliest form of skin cancer. Early detection of melanoma is vital, as it helps in decreasing the death rate as well as treatment costs. Dermatologists are using image-based diagnostic tools to assist them in decision-making and detecting melanoma at an early stage. We aim to develop a novel handheld medical scanning device dedicated to early detection of melanoma at the primary healthcare with low cost and high performance. However, developing this particular device is very challenging due to the complicated computations required by the embedded diagnosis system. In this paper, we propose a hardware-friendly design for implementing an embedded system by exploiting the recent hardware advances in reconfigurable computing. The developed embedded system achieved optimized implementation results for the hardware resource utilization, power consumption, detection speed and processing time with high classification accuracy rate using real data for melanoma detection. Consequently, the proposed embedded diagnosis system meets the critical embedded systems constraints, which is capable for integration towards a cost- and energy-efficient medical device for early detection of melanoma.

Heart Rate Variability (HRV) derived from standard one-lead electrocardiography (ECG) was compared with HRV computed by a commercial ECG shirt and with the inter-beat-intervals (IBI) measured by a research-grade photoplethysmographic (PPG) wristband. Signals from 8 subjects were recorded in three experimental phases: during sit; in upright position (“stand”); during controlled respiration. HRV and IBI from both the wearables were computed online (i.e. during the experiment) and stored for subsequent analyses, while the standard ECG was processed offline with state-of-the-art methods to obtain a clean reference HRV. Shirt and wristband signals accuracies were assessed, with respect to the reference HRV, through a between-phase and a beat-to-beat analyses. The former considered several time and frequency domain parameters; the latter was carried out through the Bland-Altman method. Time and frequency domain parameters computed from shirt HRV resulted very similar to the ones extracted from the reference HRV and generally more accurate than the parameters computed from wristband IBI. The Bland-Altman analysis showed that wristband IBI is significantly different from ECG-derived HRV, especially during “stand”. Therefore, our results support the idea that some care should be paid in the interpretation of online PPG-derived IBI, while HRV measures online-derived from ECG-shirts seem to be more reliable in the analyzed conditions. The high number of missing beats also suggest that the design of wristband devices should be taken into account to reduce the rate of incorrect measurements, by maximizing sensor adhesion to the skin.

This article describes the study results of echocardiographic (ECHO) test data for 4P medicine applied to cardiovascular patients. Data from more than 145,000 echocardiographic tests were analyzed. One of the objectives of the study is the possibility to identify patterns and relationships in patient characteristics for more accurate appointment procedures based on the history of the disease and the individual characteristics of the patient. This is achieved by using classifications models based on machine learning methods. Early detection of disease risks and “accurate” appointment of diagnostic procedures makes a significant contribution to value-based medicine. Moreover, it was also possible to identify the classes and characteristics of patients for whom repeated diagnostic procedures are well founded. Calculation of personal risks from empirical retrospective data helps to detect the disease in early stages. Identifying patients with high risk of disease complications allow physicians to make right decisions about timely treatment, which can significantly improve the quality of treatment, and help to avoid diseases complications, optimize costs and improve the quality of medical care.

Continuous blood pressure (BP) monitoring can produce a significant amount of digital data, which increases the chance of early diagnosis and improve the rate of survival for people diagnosed with hypertension and Cardiovascular diseases (CVDs). However, mining and processing this vast amount of data are challenging. This research is aimed to address this challenge by proposing a deep learning technique, convolutional neural network (CNN), to estimate the systolic blood pressure (SBP) using electrocardiogram (ECG) and photoplethysmography (PPG) signals. Two different methods are investigated and compared in this research. In the first method, continuous wavelet transform (CWT) and CNN have been employed to estimate the SBP. For the second method, we used random sampling within the stochastic gradient descent (SGD) optimization of CNN and the raw ECG and PPG signals for training the network. The Medical Information Mart for Intensive Care (MIMIC III) database is used for both methods, which split to two parts, 70% for training our network and the remaining used for testing the performance of the network. Both methods are capable of learning how to extract relevant features from the signals. Therefore, there is no need for engineered feature extraction compared to previous works. Our experimental results show high accuracy for both CNN-based methods which make them promising and reliable architectures for SBP estimation.

This study proposes a graph-based method for representing the dynamics of chronic diabetes as a complex process with different characteristics. The study was based on the case histories of 6864 patients with diabetes mellitus, 90% of whom suffer from type 2 diabetes. Our method allows to predict the sequence of events during the development of type 2 diabetes for each patient. Typical developmental trajectories of the disease were investigated, their clustering was carried out, the trajectory patterns were identified and studied. Based on the constructed directed graph reflecting transitions between different conditions of the patients, the clustering of diabetic statuses was carried out using the Modularity Class method; 8 clusters were selected, each of them was interpreted and studied. The method of the disease developmental trajectories creation by means of machine learning methods was described. Unlike static models of a disease course, this method considers complete past information on the patient and his or her previous events, using each event of the course of disease to predict the next event.