Ebook: eHealth2015 – Health Informatics Meets eHealth

Innovative Health Perspectives – Personalized Health

Traditional medicine was characterized by therapies that were chosen depending on the respective disease of the patient – according to clinical guidelines. These guidelines were derived from clinical trials which pooled patients into specific patient groups. According to clinical guidelines, all patients within such a specific group should be treated in exactly the same way.

This paradigm is recently being shifted toward personalized medicine. In the future, individual treatment plans will depend on the very specific settings of each single patient, including genomic information. Searching for “personalised medicine” OR “personalized medicine” in PubMed currently yields 5944 results, almost exclusively published since 2000 with a strong rising trend.

One of the first fields of application for personalized medicine is oncology. While traditional oncological risk factors focused on populations at risk, current diagnostic tools include molecular risk factors, biomarkers, and individual cancer genome alterations. These additional data can be used to calculate a patient's individual risk profile. Additionally, they can be used to select individual therapies which effectively target on the present cancer cells.

As a next step, personalized medicine will need to be extended to a more general approach – i.e. personalized health: Although personalized medicine has a high potential in improving the therapy of many diseases, treatment is usually only the final, expensive step in a long-term process. Individual risk assessment and – subsequently – individual preventive strategies may provide even stronger impacts on our healthcare systems, if planned and performed in a suitable way. While for oncology personalized medicine is associated with genomic data, vital signs and activities of daily living may be an additional basis of personalized health systems for chronic diseases. Future decision support systems might not only propose to consult physicians with particularly important skills to select the optimal (guideline based) treatment but also propose suitable apps to support the treatment process. Personal apps could recommend, e.g. which fitness program best fits our personal preferences and risk profiles. Individual nutrition guides could help us to live on food that perfectly fits with our intolerances, genotypes and phenotypes. Such innovative tools, which address healthy citizens instead of patients, could lead us from personalized medicine to personalized health settings.

Along this path, interoperability of wellness and health services with electronic health records, quality management and integrated care will become more and more important. Active and assisted living as well as telemonitoring services can contribute data and they can build a link to patients and citizens. The present proceedings summarize interesting and novel approaches concerning these and related topics.

The 9th scientific eHealth conference (http://www.ehealth2015.at), which took place in the context of the eHealth Summit Austria (http://www.ehealthsummit.at) from the 18th to the 19th of June 2015 in Vienna, combined innovative research with state of the art applications of eHealth and health informatics within 25 sessions, including scientific tracks, workshops, round tables and demonstrations in accordance with the conference theme “from science to application and back”.

Dr. Dieter Hayn

Univ.-Doz. Dr. Günter Schreier

Univ.-Prof. Dr. Elske Ammenwerth

Univ.-Doz. Dr. Alexander Hörbst

Graz and Hall in Tyrol, 7th of May 2015

Today, connecting medical devices to the hospital network becomes a priority for many hospitals. User and operator requirements for communication must be considered in order to develop an adequate interoperable integration approach. This paper conducts a requirement study using questionnaires and working groups investigating 16 clinical communication requirements for connecting medical devices with each other and with clinical IT systems. Six German Hospitals order the communication requirements by their clinical relevance and categorize those into four main clusters. Communication requirements regarding accurate data transfer and processing for patients and devices have top priority, while communication requirements regarding remote manipulation of medical devices have low rank. Connecting medical devices to clinical IT systems improves clinical documentation and with it patient care processes.

Patients with chronic diseases undergo numerous in- and outpatient treatment periods, and therefore many documents accumulate in their electronic records. We report on an on-going project focussing on the semantic enrichment of medical texts, in order to support recall-oriented navigation across a patient's complete documentation. A document pool of 1,696 de-identified discharge summaries was used for prototyping. A natural language processing toolset for document annotation (based on the text-mining framework UIMA) and indexing (Solr) was used to support a browser-based platform for document import, search and navigation. The integrated search engine combines free text and concept-based querying, supported by dynamically generated facets (diagnoses, procedures, medications, lab values, and body parts). The prototype demonstrates the feasibility of semantic document enrichment within document collections of a single patient. Originally conceived as an add-on for the clinical workplace, this technology could also be adapted to support personalised health record platforms, as well as cross-patient search for cohort building and other secondary use scenarios.

Quality assurance (QA) is a key factor to evaluate success of organ transplantations. In Germany QA documentation is progressively developed and enforced by law. Our objective is to share QA models from Germany in a standardized format within a form repository for world-wide reuse and exchange. Original QA forms were converted into standardized study forms according to the Operational Data Model (ODM) and shared for open access in an international forms repository. Form elements were translated into English and semantically enriched with Concept Unique Identifiers from the Unified Medical Language System (UMLS) based on medical expert decision. All forms are available on the web as multilingual ODM documents. UMLS concept coverage analysis indicates 92% coverage with few but critically important definition gaps. New content and infrastructure for harmonized documentation forms is provided in the domain of organ transplantations enabling world-wide reuse and exchange.

Background: Automatic coding of medical terms is an important, but highly complicated and laborious task.

Objectives: To compare and evaluate different strategies a framework with a standardized web-interface was created. Two UMLS mapping strategies are compared to demonstrate the interface.

Methods: The framework is a Java Spring application running on a Tomcat application server. It accepts different parameters and returns results in JSON format. To demonstrate the framework, a list of medical data items was mapped by two different methods: similarity search in a large table of terminology codes versus search in a manually curated repository. These mappings were reviewed by a specialist.

Results: The evaluation shows that the framework is flexible (due to standardized interfaces like HTTP and JSON), performant and reliable. Accuracy of automatically assigned codes is limited (up to 40%).

Conclusion: Combining different semantic mappers into a standardized Web-API is feasible. This framework can be easily enhanced due to its modular design.

Data that has been collected in the course of clinical trials are potentially valuable for additional scientific research questions in so called secondary use scenarios. This is of particular importance in rare disease areas like paediatric oncology. If data from several research projects need to be connected, so called Core Datasets can be used to define which information needs to be extracted from every involved source system. In this work, the utility of the Clinical Data Interchange Standards Consortium (CDISC) Operational Data Model (ODM) as a format for Core Datasets was evaluated and a web tool was developed which received Source ODM XML files and – via Extensible Stylesheet Language Transformation (XSLT) – generated standardized Core Dataset ODM XML files. Using this tool, data from different source systems were extracted and pooled for joined analysis in a proof-of-concept study, facilitating both, basic syntactic and semantic interoperability.

Chronic diseases like Heart Failure are widespread in the ageing population. Affected patients can be treated with the aid of a disease management program, including a telemedical collaborative network. Evaluation of a currently used system has shown that the information of the textual communication is of pivotal importance for the collaboration in the network. Thus, the challenge is to make this unstructured information useable, potentially leading to a better understanding of the collaboration so as to optimize the processes. This paper presents the setup of an analysis pipeline for processing textual information automatically, and, how this pipeline can be utilized to train a model that is able to automatically classify the written messages into a set of meaningful task and status categories.

People aged 65 years and older are the fastest growing section of the population in many countries. Great hopes are projected on technology to support solutions for many of the challenges arising from this trend, thus making our lives more independent, more efficient and safer with a higher quality of life. But, as research and innovation ventures are often closely linked to the market, their focus may lead to biased planning in research and development as well as in policy-making with severe social and economic consequences. Thus the main research question concerned desirable settings of ageing in the future from different perspectives. The participatory foresight study CIVISTI-AAL cross-linked knowledge of lay persons, experts and stakeholders to include a wide variety of perspectives and values into productive long-term planning of research and development. Results include citizens' visions for autonomous living in 2050, implicitly and explicitly containing basic needs towards technological, social and organizational development as well as recommendations for implementation. Conclusions suggest that personalized health and living environments play an important part in the lay persons' view of aging in the future, but only if technologies support social and organizational innovations and yet do not neglect the importance of social affiliation and inclusion.

Cardiovascular diseases belong to the most common causes of death. Telehealth applications can help to improve therapy and support behavior change. It was the objective of the present work to construct and evaluate within a trial (25 patients) an automated feedback system for a telehealth application to support behavior change. We used a rule-based approach and constructed 26 rules in 9 categories. Rule design and implementation followed the principles of the Austrian Medical Product Law, resulting in an automated rule-based feedback system. Evaluations show high user satisfaction with 80% of all users perceiving the system as useful.

Management of heart failure is usually multidisciplinary and collaboration between stakeholders in a dedicated HI network like the HerzMobil Tirol can be supported by a mHealth-based telemedicine approach. The aim is to gain insights through textual analysis of collaboration notes that might trigger further developments and improvements of the HI network. A reusable pipeline for textual analysis of unstructured textual notes was implemented using the open source analytics software KNIME. After preprocessing, a keyword analysis was performed resulting in a classification of all notes in predefined categories.

Results: Medical and organizational issues dominate the communication with health status and therapy aspects as well as clinical treatment, discharge letter and home visits. Beside aspects of data transmission and mobile phone, technological issues are minor topics during the collaboration. It is possible to gain new insights with respect to technology like additional control Apps for mobile phone settings and to the HI network like clinical experts and technical help desk involvement.

Background: Biosample collections and biobank information systems have become a key enabler for medical research. Therefore it is important to identify potentially relevant ontologies to semantically enrich information related to the biobanking domain.

Objectives: We present a three-stage semi-automated evaluation approach which allows identifying relevant ontologies for the biobanking domain based on competency questions.

Methods: After identifying candidate biobanking ontologies (Stage 1) and competency questions (Stage 2), a six-step lexical evaluation approach, which assesses the coverage of concepts, properties or instances defined by competency questions is suggested and described (Stage 3).

Results: We were able to perform a proof-of-concept evaluation of the OMIABIS ontology using our proposed three-stage approach together with a sample competency question.

Conclusion: Our evaluation approach allows a swift evaluation of candidate ontology entities based on a search for higher hierarchy key terms that exist in comprehensive medical vocabularies in order to state the usability of specific ontologies for the biobanking domain.

Background: A Nursing Minimum Data Set (NMDS) aims at systematically describing nursing care in terms of patient problems, nursing activities, and patient outcomes. In an earlier Delphi study, 56 data elements were proposed to be included in an Austrian Nursing Minimum Data Set (NMDS-AT).

Objectives: To identify the most important data elements of this list, and to identify appropriate coding systems.

Methods: Online Delphi-based survey with 88 experts.

Results: 43 data elements were rated as relevant for an NMDS-AT (strong agreement of more than half of the experts): nine data elements concerning the institution, patient demographics, and medical condition; 18 data elements concerning patient problems by using nursing diagnosis; seven data elements concerning nursing outcomes, and nine data elements concerning nursing interventions. As classification systems, national classification systems were proposed besides ICNP, NNN, and nursing-sensitive indicators.

Conclusion: The resulting proposal for an NMDS-AT will now be tested with routine data.

Decision-support based medication adjustment in heart failure management. Prospective analysis of clinical decision support in fifteen patients that collected vital parameters and medication intake up to one year within a clinical trial. Correlation of event episodes and medication adjustments with respect to applied rule-sets and medication classes. 713 events were grouped to 195 event episodes. Physicians performed 86 medication adjustments. 30 of them were triggered by event episodes. 35% of all performed medication adjustments occurred between event episodes. 20% of all episodes triggered a medication adjustment. 15% of all episodes triggered the expected medication adjustment. Correlation between episodes and medication adjustment was low. Further analysis needs to be done, to evaluate reasons for low correlation and how the rule-set should be adapted to increase reliability.

The design of clinical trial (CT) study protocols, currently supported by clinicians, is often a slow and cumbersome process. The Electronic Health Records for Clinical Research (EHR4CR) project supports the design of study protocols through a multi-site patient count cohort system. However, there is still a need to improve the process step in which the clinicians are involved. This research aims to enhance the EHR4CR platform with a tool to support the contact of CT sponsors with clinical investigators to obtain their input regarding feasibility data for the CT protocol design. From a list of requirements, a technical architecture that responds to the needs of feasibility assessments was modelled. With this architecture as a basis, a system that allows users to generate, send, fill out and visualise results of feasibility questionnaires across clinical sites was developed and integrated within the EHR4CR platform. The resulting system improves the current methods by providing direct contact to clinical investigators, facilitating the creation and answer of feasibility questionnaires for CTs.

Background: Professional biobanks become increasingly important for fostering personalized medicine. While setting up and operating a high-quality collection of biomaterial specimens, biobank managers must face several challenges concerning quality management.

Objectives: Designing and implementing a data management, which ensures patient's privacy and simultaneously provides researchers with all relevant patient information, is particularly demanding. The requirements of all involved stakeholders must be considered without impairing the biobank's efficiency.

Methods: To link biomaterial samples to medical data documented in different contexts, an asymmetric encryption scheme with pseudonymization for existing clinical identifiers was implemented.

Results: The presented pseudonymization scheme allows establishing a comprehensive flow for pseudonymized data for biomaterial samples.

Conclusion: Most of the content stored in clinical databases, except for personally identifying data, can be evaluated, combined with individually documented medical data and associated this to a biomaterial sample without revealing personally identifying data.

In recent years an ongoing development in educational offers for professionals working in the field of eHealth has been observed. This education is increasingly offered in the form of eLearning courses. Furthermore, it can be seen that simulations are a valuable part to support the knowledge transfer. Based on the knowledge profiles defined for eHealth courses a virtual lab should be developed. For this purpose, a subset of skills and a use case is determined. After searching and evaluating appropriate simulating and testing tools six tools were chosen to implement the use case practically. Within an UML use case diagram the interaction between the tools and the user is represented. Initially tests have shown good results of the tools' feasibility. After an extensive testing phase the tools should be integrated in the eHealth eLearning courses.

Health care systems in Austria and Slovenia are currently facing challenges due to scarce resources and demographic change which can be seen especially along the supply chains. The main objective of this paper is to present an option to improve the use of assistive technologies. An extensive literature research for the theoretic part as well as a qualitative survey for the empiric part focusing on short-term care were carried out. Results show that there is a lack of information and training on assistive technologies. As a consequence, their full potential cannot be exploited. Therefore a guideline for nursing consultations was developed. To conclude, both the literature research and the qualitative survey show that assistive technologies have high potentials to improve the supply chains in the health care and social services sector, but there is a lot of information and training on them needed.

The field of “AAL Robotics”, combining AAL and robotics as disciplines, has not yet been precisely defined and does not present accepted structures and concepts that would allow to communicate unequivocally its methods, projects, and approaches. The paper presents a method of defining and categorizing AAL robots and presents the resulting classes of robots with regard to the activities they assist. The classification is useful in that it is able to cover the breadth of the field, but a more fine-grained description of functionalities will be needed in further research to establish the potential of robots to assist independent living of older adults.

The Ambient Assisted Living (AAL) market is still in an early stage of development. Previous approaches of comprehensive AAL services are mostly supply-side driven and focused on hardware and software. Usually this type of AAL solutions does not lead to a sustainable success on the market. Research and development increasingly focuses on demand and customer requirements in addition to the social and legal framework. The question is: How can a systematic performance measurement strategy along a service development process support the market-ready design of a concrete business model for AAL service? Within the EU funded research project DALIA (Assistant for Daily Life Activities at Home) an iterative service development process uses an adapted Osterwalder business model canvas. The application of a performance measurement index (PMI) to support the process has been developed and tested. Development of an iterative service development model using a supporting PMI. The PMI framework is developed throughout the engineering of a virtual assistant (AVATAR) as a modular interface to connect informal carers with necessary and useful services. Future research should seek to ensure that the PMI enables meaningful transparency regarding targeting (e.g. innovative AAL service), design (e.g. functional hybrid AAL service) and implementation (e.g. marketable AAL support services). To this end, a further reference to further testing practices is required. The aim must be to develop a weighted PMI in the context of further research, which supports both the service engineering and the subsequent service management process.

Due to demographic changes, the number of elderly people who are in need of care is increasing. Assistive technologies make it possible for many elderly people to remain home despite their health conditions, which many prefer. Quality is an essential element of nursing care, and the elderly are becoming increasingly aware of this and are beginning to make high demands. The aims of this paper, which is based on a master's thesis, were to identify quality criteria in the field of assistive technologies and to present indicators for measuring quality. An extensive literature research was conducted for the theoretical part, and the empirical part employed a qualitative survey. The results show that the elderly's contentment and quality of life are the decisive factors for quality. A catalogue of quality indicators was developed by merging the results from literature with those from the expert consultation. To conclude, further research in this context, based on the results of this paper, is needed, in order to support the increasing use of assistive technologies.

Experts refer to innovative telemonitoring technologies to deal with chronic respiratory diseases, especially the chronic obstructive pulmonary disease – COPD. In chronic respiratory diseases, sudden acute exacerbations may occur that can be life-threatening in some cases. Telemonitoring solutions help to detect the beginning of an impaired medical condition and can induce an adequate countermeasure in time. As soon as individually determined parameters are passed, appropriate warning signs can be transmitted. As part of a project, a new monitoring device for the detection of COPD-typical parameters has been utilized and optimized. Furthermore, an innovative 3D-Video-System was used to enable the implementation of physical exercises in the domestic environment. The systems assists the patient during the entire training unit and creates a feedback based on the quality of his or her exercises.

The demographic change, the social structure and the development of new and complex therapies for diseases are responsible for a permanent rise of health expenditure. To guarantee affordable health care, AAL (Ambient Assisted Living) is one possibility. Our objective is to show that it is possible to create remote support for caregivers by physicians even with widely available and versatile hardware. A single board computer currently only equipped with 6 different sensors to measure blood pressure, glucose level, pulse, oxygen saturation, temperature and ECG is used as a showcase for patients with e.g. coronary artery disease. We created a user-friendly local application that collects and stores all data and transmits them to a remote server as soon as an Internet connection becomes available. Additionally, a web-application gives access to remote physicians and nurses to support caregivers and patients. Patients keep the overview of their vital signs, caregivers, nurses and physician can be alerted on demand or check the patient's data anytime to give advice. We conclude, that projects like this are showcases for the usage of technology that can foster AAL due to the focus on widely available and cheap, versatile equipment.

COPD (chronic obstructive pulmonary disease) is the most frequent form of chronic respiratory disease. During the progress of this disease, phases of aggravation of pulmonary function (exacerbations) can occur, which reduce the quality of life. Clinical experience shows that single investigations are insufficient. Therefore a prolonged monitoring is required to recognize an exacerbation early. This home monitoring will involve a quick respiratory test and a related application for Android, iOS and Windows phones. This rapid test transmits the relevant pulmonary parameters, converted in an Extensible Markup Language file to the smartphone. The application will analyze the incoming data to evaluate the current health status of the patient. Additionally the data will be transferred to the virtual control point (server) and stored in a database. If critical values are detected, the server will send a notification to prior defined relatives and doctors. A connection to a Hospital Information System will be possible through an included Health Level 7 interface. This offers an improved site-independent patient care. The project is planned to be in development until 2016.

Diabetes is a serious world-wide medical challenge and there is a recognised need for improved diabetes care outcomes. This paper describes results of the EMPOWER project, to foster the self-management of diabetes patients by integration of existing and new services offered to patients after having been diagnosed with diabetes. The Self-Management Pathway described in this paper helps patients in the specification of personalized activities based on medical recommendations and personal goals, as well as self-monitoring of the results. The whole process is supported by innovative ICT services that motivate patients to change their lifestyle and adhere to defined medication and activity plans. We describe the approach and present the findings of the validation phase in Germany and Turkey.

Today, progress in biomedical research often depends on large, interdisciplinary research projects and tailored information and communication technology (ICT) support. In the context of the European Network for Cancer Research in Children and Adolescents (ENCCA) project the exchange of data between data source (Source Domain) and data consumer (Consumer Domain) systems in a distributed computing environment needs to be facilitated. This work presents the requirements and the corresponding solution architecture of the Advanced Biomedical Collaboration Domain for Europe (ABCD-4-E). The proposed concept utilises public as well as private cloud systems, the Integrating the Healthcare Enterprise (IHE) framework and web-based applications to provide the core capabilities in accordance with privacy and security needs. The utility of crucial parts of the concept was evaluated by prototypic implementation. A discussion of the design indicates that the requirements of ENCCA are fully met. A whole system demonstration is currently being prepared to verify that ABCD-4-E has the potential to evolve into a domain-bridging collaboration platform in the future.