Ebook: dHealth 2024

In the ever-evolving healthcare landscape, the integration of technology has become paramount in improving patient outcomes, optimising clinical workflows, and expanding access to care. The rise of large language models (LLMs), such as ChatGPT in 2022, has changed the view of citizens as regards artificial intelligence (AI)-based applications. This has triggered the foundation of various research groups to explore the use of large language models in healthcare, for purposes including literature review, documentation, translation, coding, decision support, and digital assistants, among others. The coming years will show to what extent the huge expectations raised by LLMs will be met, and which classical health IT areas will survive this technological transformation.

Since 2007, the dHealth conference has been providing insight into the research and application of up-to-date health IT solutions. Each year, this event attracts around 300 participants from academia, industry, government, and healthcare organisations. In keeping with its interdisciplinary mission, the dHealth conference series provides a platform for researchers, practitioners, decision makers and vendors to discuss innovative health informatics and eHealth solutions aimed at improving the quality and efficiency of healthcare by means of digital technology.

This year’s proceedings of the 18th edition of dHealth represent an up-to-date mirror of ongoing research in health IT in Europe. Topics range from the adoption of emerging technologies like LLMs, telemedicine and cloud computing, to the ethical, legal, social, and economic implications of health IT. Each paper contributes to the rich tapestry of research aimed at advancing digital health and improving patient outcomes. As we navigate the complexities of modern healthcare, interdisciplinary collaboration, technological innovation, and ethical considerations will continue to shape the future of healthcare delivery, and ensure equitable access to quality care for all.

Graz, Hall in Tyrol, Vienna, May 2024

Dieter Hayn (AIT)

Bernhard Pfeifer (UMIT)

Günter Schreier (AIT)

Martin Baumgartner (AIT)

A Critical Incident Reporting System (CIRS) collects anecdotal reports from employees, which serve as a vital source of information about incidents that could potentially harm patients. Objectives: To demonstrate how natural language processing (NLP) methods can help in retrieving valuable information from such incident data. Methods: We analyzed frequently occurring terms and sentiments as well as topics in data from the Swiss National CIRRNET database from 2006 to 2023 using NLP and BERTopic modelling. Results: We grouped the topics into 10 major themes out of which 6 are related to medication. Overall, they reflect the global trends in adverse events in healthcare (surgical errors, venous thromboembolism, falls). Additionally, we identified errors related to blood testing, COVID-19, handling patients with diabetes and pediatrics. 40–50% of the messages are written in a neutral tone, 30–40% in a negative tone. Conclusion: The analysis of CIRS messages using text analysis tools helped in getting insights into common sources of critical incidents in Swiss healthcare institutions. In future work, we want to study more closely the relations, for example between sentiment and topics.

Knee injuries are a common concern in orthopedic and sports medicine, often requiring extensive rehabilitation to restore function and alleviate pain. The rehabilitation process can be long and challenging, necessitating innovative approaches to engage and motivate patients effectively. Serious games have emerged as a promising tool in rehabilitation, offering an interactive and enjoyable way to perform therapeutic exercises. In this context, a new serious game that leverages the Wii Fit Balance Board as an input device supported by a keyboard to aid knee rehabilitation was developed. To tailor the game to the specific needs of knee rehabilitation, qualitative content analysis and requirement extraction based on three interviews with therapists were conducted. These insights were then iteratively integrated into the game’s development, ensuring that the final game was both clinically relevant and engaging. A therapist subsequently re-evaluated the completed game, confirming its potential to enhance the rehabilitation process. It was also shown that further research is needed to detect squat movements on the Balance Board. But this initial approach, combining the Wii Fit Balance Board with squat exercises, uniquely addresses the challenges of knee rehabilitation, offering a novel video and game solution.

Background:

Dementia is becoming a significant public health concern, affecting approximately 130,000 individuals in Austria, whereby nearly 40% of the cases are attributed to modifiable risk factors. Multidomain lifestyle interventions have thereby demonstrated significant effects in reducing the risk of dementia.

Objectives:

The goal was to define an interoperability framework to conduct standardized monitoring in clinical trials for enhancing dementia risk mitigation. In addition, the identified standards should be integrated into the components of the project.

Methods:

A step-by-step approach was used, where initially data collection, aggregation and harmonization was carried out with retrospective data from various clinical centers. Afterwards, the interoperability framework was defined including the prospective data that is gathered during a clinical trial.

Results:

A guideline for integrating healthcare standards was developed and incorporated into the technical components for the clinical trial.

Conclusion:

The interoperability framework was designed in a scalable way and will be regularly updated for future needs.

Background:

Stroke as a cause of disability in adulthood causes an increasing demand for therapy and care services, including telecare and teletherapy.

Objectives:

Aim of the study is to analyse the acceptance of telepresence robotics and digital therapy applications.

Methods:

Longitudinal study with a before and after survey of patients, relatives and care and therapy staff.

Results:

Acceptance of the technology analysed is high in all three groups. Although acceptance among patients declined in parts of the cases in the second survey after having used telerobotics, all in all approval ratings remained high. With regard to patients no significant correlation was found between the general technology acceptance and the acceptance of use of telerobotics.

Conclusion:

Accepted new telecare and teletherapies can be offered with the help of telepresence robotics. This requires knowledge of and experience with the technology.

Background:

Healthcare systems are increasingly resource constrained, leaving less time for important patient-provider interactions. Conversational agents (CAs) could be used to support the provision of information and to answer patients’ questions. However, information must be accessible to a variety of patient populations, which requires understanding questions expressed at different language levels.

Methods:

This study describes the use of Large Language Models (LLMs) to evaluate predefined medical content in CAs across patient populations. These simulated populations are characterized by a range of health literacy. The evaluation framework includes both fully automated and semi-automated procedures to assess the performance of a CA.

Results:

A case study in the domain of mammography shows that LLMs can simulate questions from different patient populations. However, the accuracy of the answers provided varies depending on the level of health literacy.

Conclusions:

Our scalable evaluation framework enables the simulation of patient populations with different health literacy levels and helps to evaluate domain specific CAs, thus promoting their integration into clinical practice. Future research aims to extend the framework to CAs without predefined content and to apply LLMs to adapt medical information to the specific (health) literacy level of the user.

Background:

The Bulgaria Diabetes Register (BDR) contains more than 380 millions of pseudonymized outpatient records with proprietary data structures and format.

Objectives:

This paper presents the application results and experience acquired during the process of mapping such observational health data to OMOP CDM with the objective of publishing it in the European Health Data and Evidence Network (EHDEN) Portal.

Methods:

The data mapping follows the activities of the well-structured Extract-Transform-Load process. Unlike other publications, we focus on the need for preprocessing the data structures of raw data, cleaning data and procedures for assuring quality of data.

Results:

This paper provides quantitative and statistical measures for the records in the CDM database as published in the EHDEN Portal.

Conclusion:

The mapping of data from the BDR to OMOP CDM provides the EHDEN community with opportunities for including these data in large-scale project for evidence generation by applying standard analytical tools.

Supporting older adults’ health and well-being in the transition from work to retirement requires a holistic perspective and needs to address physical, mental, and social aspects of life. In a field study, applying a mixed-methods approach, we investigated to what extent the prototype of a digital coach can support older adults in this sensitive phase. We aim at answering the central research question: How can a digital coach support older adults in the transition from work to retirement to establish and maintain a healthy lifestyle? Overall, 32 participants from Austria and Belgium took part in an eight-week trial. App-based interventions in different domains (physical, mental, social) were provided and aimed at motivating the target group to become and/or stay active. The study shows that the digital coach has potential to support health and well-being on various levels. In particular, the mental activities proofed valuable and supported older adults’ well-being.

The present study aims to describe ethical and social requirements for technical and robotic systems for caregiving from the perspective of users. Users are interviewed in the ReduSys project during the development phase (prospective viewpoint) and after technology testing in the clinical setting (retrospective viewpoint). The preliminary results presented here refer to the prospective viewpoint.

Introduction:

The project “digiDEM Bayern” aims to set up a registry with long-term follow-up data on people with dementia and their family caregivers. For that purpose an Electronic Data Capture (EDC) system linked with a Participant Management (PM) system has been established. This study evaluates the acceptance and usability of the IT tools supporting all data management processes in order to further improve the system and associated processes.

Methods:

For this purpose we collected the key numbers of the registry, and used the System Usability Scale (SUS) to evaluate the interactions of the data management systems in a wide area.

Results:

Thirty-six research partners (RP) and six study team (ST) members completed the anonymous online survey. The EDC system overall reached an average SUS score of 73.42 and the PM system of 77.92.

Discussion:

The two systems fulfil their required task and, therefore, simplify the work of the RP in the data collection process and of the ST during the data quality checks.

Conclusion:

Integrating the used systems is therefore recommended for registry studies in other medical areas.

Background:

The Fast Healthcare Interoperability Resources (FHIR) and Clinical Document Architecture (CDA) are standards for the healthcare industry, designed to improve the exchange of health data by interoperability. Both standards are constrained through what are known as Implementation Guides (IG) for specific use.

Objectives:

Both of these two standards are widely in use and play an important role in the Austrian healthcare system. Concepts existing in CDA and FHIR must be aligned between both standards.

Methods:

Many existing approaches are presented and discussed, none are fully suited to the needs in Austria.

Results:

The IG Publisher has already been used for CDA IGs, beside of its intended FHIR support, but never for both in one IG. Even the International Patient Summary (IPS), existing as CDA and FHIR specification, does not solve the needed comparability between these two.

Conclusion:

As the IG Publisher is widely used and supports CDA, it should be used for Dual Implementation Guides. Further work and extension of IG Publisher is necessary to enhance the readability of the resulting IGs.

Background:

In 2019, the Digital Healthcare Act created the legal basis for prescribable mobile health applications, referred to as DiGA (in German: Digitale Gesundheitsanwendungen), as a novel healthcare delivery option in Germany [1, 2].

Objectives:

The aim of this study is to analyze the use of DiGA in primary care, focusing on the influence of socio-demographic characteristics of family doctors (FDs) and patient-related factors.

Methods:

Pen-and-paper survey among 97 FDs in the district of Giessen, Hesse, Germany.

Results:

59.4% of surveyed FDs have already prescribed DiGA. The age and digital affinity of FDs as well as the location of their practice are significantly correlated with the level of information and willingness to use DiGA. Male und younger FDs rate their digital affinity higher. When deciding whether to prescribe DiGA, 72.9% of surveyed physicians take patient-related factors such as digital affinity, motivation, age and health literacy into consideration.

Conclusion:

Socio-demographic characteristics of FDs and patient-related factors have an influence on the use of DiGA.

Background:

Telehealth uptake will remain sub-optimal without consumer trust. Safeguarding the security and privacy of health information plays an important role in building trust and acceptance of telehealth.

Objectives:

This study seeks to unpack the sociotechnical discourses on the use of telehealth with a focus on privacy and security in the context of United States health services.

Methods:

A search of the media outlets facilitated via the Factiva database was conducted. Using a qualitative method, thematic analysis was performed on the news texts to identify the key themes and provide contextual explanations.

Results:

The analysis led to the identification of three key themes: ‘data protection practice’, ‘clinical resilience’, and ‘digital health business value’ perspectives. These themes focus on various concepts of telehealth use including data privacy, security, public health emergency, compliance activities in the use of telehealth, meeting stakeholders’ needs, reducing costs of service delivery, the potential of telehealth for informed action, and improving users’ experience. Among these themes, ‘data protection practice’ was directly associated with privacy compliance and telehealth use. Other thematic discourses have provided an indirect reflection on the role of privacy compliance, with a greater emphasis placed on health service delivery and market dynamics rather than compliance in practice.

Conclusion:

Our study revealed the importance of the COVID-19 pandemic in telehealth use, highlighting the move towards ‘good faith’ and responsible use of telehealth.

Background:

Several studies have demonstrated the effectiveness of telerehabilitation. However, it remains unclear what proportion of people in need of rehabilitation can confidently use telecommunications networks and related devices.

Objectives:

The aim of this study is to estimate the proportion of patients who possess either the requisite digital literacy to perform telerehabilitation independently or have a family caregiver capable of providing effective support.

Methods:

Synthetic populations with a realistic kinship network (i.e. family trees) representative of European countries are built. Age, sex, and location-specific prevalence rates of rehabilitation needs and digital skills are combined to estimate the percentage of digitally literate patients and patients with digitally literate relatives.

Results:

In Europe, 86% of people in need of rehabilitation are potentially eligible for telerehabilitation. However, in four out of five cases, eligible patients over the age of 65 require caregiver support.

Conclusion:

Telerehabilitation has the potential to spread in Europe. Caregivers have an essential social role in ensuring sustainable access to telerehabilitation.

While adherence to clinical guidelines improves the quality and consistency of care, personalized healthcare also requires a deep understanding of individual disease models and treatment plans. The structured preparation of medical routine data in a certain clinical context, e.g. a treatment pathway outlined in a medical guideline, is currently a challenging task. Medical data is often stored in diverse formats and systems, and the relevant clinical knowledge defining the context is not available in machine-readable formats. We present an approach to extract information from medical free text documentation by using structured clinical knowledge to guide information extraction into a structured and encoded format, overcoming the known challenges for natural language processing algorithms. Preliminary results have been encouraging, as one of our methods managed to extract 100% of all data-points with 85% accuracy in details. These advancements show the potential of our approach to effectively use unstructured clinical data to elevate the quality of patient care and reduce the workload of medical personnel.

Background:

Telemedicine has emerged as a potential solution to mitigate the significant greenhouse gas emissions of the healthcare sector. A comprehensive evaluation is required to quantify the environmental benefits of its implementation.

Objectives:

The study aims to compare the environmental sustainability of in-person and virtual examinations for heart failure patients.

Methods:

A standard life cycle assessment has been applied to quantify the equivalent CO₂ of direct and indirect activities required to release a medical examination (virtual or physical) for a patient in an Italian hospital. Inputs of the analysis include electronic devices of hospital and patients, energy consumption, wastes, internet usage and patient travel. Depending on the type of visit (virtual or physical), inputs have been processed differently, considering actual consumption and utilization.

Results:

Televisit reduces emissions from 9.77 kgCO₂e to 0.41 kgCO₂e. Transport and internet data use are key inputs for in-person (i.e., 98%) and telemedicine visits (i.e., 72%), respectively.

Discussion:

Given the frequent car travels, telemedicine emerges as a tool to improve environmental benefits and reduce time for patients and caregivers.

Electronic Health Records (EHRs) are pivotal in prevention, therapy, and care. Their design necessitates the representation of users, activities, context, and technology. Among various participative and ethnographic design methods, user personas are an effective tool for encapsulating users in the design process.

Background:

Telehealth and mHealth apps become increasingly popular in health professions such as physiotherapy calling for increased awareness on functionality, privacy, and data security.

Objectives:

This work presents a functionality, privacy, and data-security evaluation of four telehealth services commonly used in physiotherapy.

Methods:

We examined functionality and features, data protection, privacy implementations and data-security with a questionnaire and performed an in-depth investigation of the services.

Results:

Privacy and security relevant findings such as use of outdated webservers, problems with certificate renewal as well as questionable GDPR compliance were reported.

Conclusion:

Due to the privacy and security relevant findings in this analysis it can be concluded that there is a need for improvement in design, development, operation as well as regulation of telehealth apps and services.

The integration of Artificial Intelligence (AI) into digital healthcare, particularly in the anonymisation and processing of health information, holds considerable potential.

Background:

Approximately 40% of all recorded deaths in Austria are due to behavioral risks. These risks could be avoided with appropriate measures.

Objectives:

Extension of the concept of EHR and EMR to an electronic prevention record, focusing on primary and secondary prevention.

Methods:

The concept of a structured prevention pathway, based on the principles of P4 Medicine, was developed for a multidisciplinary prevention network. An IT infrastructure based on HL7 FHIR and the OHDSI OMOP common data model was designed.

Results:

An IT solution supporting a structured and modular prevention pathway was conceptualized. It contained a personalized management of prevention, risk assessment, diagnostic and preventive measures supported by a modular, interoperable IT infrastructure including a health app, prevention record web-service, decision support modules and a smart prevention registry, separating primary and secondary use of data.

Conclusion:

A concept was created on how an electronic health prevention record based on HL7 FHIR and the OMOP common data model can be implemented.

Background:

There is an increased need for physical activity among children and adolescents. KIJANI, a mobile augmented reality game, is designed to increase physical activity through gamified exercises.

Objectives:

The primary aim of this study is to get feedback on the design and implementation of potentially physical activity-increasing features in KIJANI.

Methods:

A mixed-method study (n=13) evaluates newly implemented game design features quantitatively through measuring physical activity and qualitatively through participant feedback.

Results:

Preliminary results are limited and need further studies. Participants’ feedback shows a positive trend and highlights the game’s potential effectiveness.

Conclusion:

KIJANI shows potential for increasing physical activity among children and adolescents through gamified exercise. Future work will refine the game based on user feedback and findings presented in related work. The game’s long-term impact is to be explored.

Background:

Medical informatics programs cover a variety of topics.

Objectives:

To test the utility of the GMDS medical informatics competency catalog in comparing programs by developing study profiles.

Methods:

Coverage of 234 competencies is recorded and visualized in a spider diagram.

Results:

Spider diagrams allow visualizing various study profiles.

Conclusion:

The GMDS catalog seems useful for comparing medical informatics study programs, e.g., for interested students, employers, or accreditation reviewers.

Background:

Electronic health records (EHR) emerged as a digital record of the data that is generated in the healthcare.

Objectives:

In this paper the transfer times of EHRs using the Hypertext Transfer Protocol and WebSocket in both local network and wide area network (WAN) are compared.

Methods:

A python web application to serve Fast Health Interoperability Resources (FHIR) records is created and the transfer times of the EHRs over both HTTP and WebSocket connection are measured. 45000 test Patient resources in 20, 50, 100 and 200 resources per Bundle transfers are used.

Results:

WebSocket showed much better transfer times of large amount of data. These were 18 s shorter in the local network and 342 s shorter in WAN for the 20 resource per Bundle transfer.

Conclusion:

RESTful APIs are a convenient way to implement EHR servers; on the other hand, HTTP becomes a bottleneck when transferring large amount of data. WebSocket shows better transfer times and thus its superiority in such situations. The problem can be addressed by developing a new communication protocol or by using network tunneling to handle large data transfer of EHRs.

Background:

Elevating systolic blood pressure (SBP) and diastolic blood pressure (DBP) independently influences clinical outcomes and adverse cardiovascular events. Blood pressure can be affected by modifiable (such as diets and physical activities) and non-modifiable factors (such as age and gender). Elevated blood pressure (EBP or formerly prehypertension) during childhood is associated with hypertension incidence in later adulthood.

Objectives:

This cross- sectional study investigated modifiable risk factors for blood pressure among children (aged 3–12).

Methods:

We employed wearable devices to monitor the blood pressure of 45 preschool and primary school children and analyze this data with secondary blood pressure data of their parents from electronic medical records.

Results:

EBP phenotypes in children (offspring) were not related to their parent’s blood pressure phenotypes (P = 0.15 and 0.19 for SBP). Consumption of high saturated fat (P = 0.032), copper (P = 0.026), and vitamin B12 (P = 0.032) was associated with a significant increase in DBP. Daily sodium intakes between normal and DBP hypertensive groups were not significantly different (P = 0.75).

Conclusion:

This study indicates that dietary intakes of high saturated fat, copper, and vitamin B12, but not parental blood pressure statuses, determine high diastolic blood pressure among children regardless of daily sodium intake. Early dietary consumption behavioral adaptation should be considered to prevent further hypertension in adulthood.

Background:

CareNet is the IT-based tool for Case and Care Management (CCM) in Tyrol, which facilitates standardised documentation of CCM activities.

Objectives:

Analysing the pilot usage of CareNet Tyrol.

Methods:

Evaluation of the success and user experience of CareNet, expert interviews and a questionnaire-based assessment.

Results:

Feedback from users in both phases indicated that the CareNet platform provides general benefits, but falls short of fully supporting the daily work of CCM experts and avoiding the need for parallel use of different documentation tools.

Conclusion:

This paper provides an insight into the ongoing transition to digital documentation for CCM at LIV Tyrol. While user feedback highlights areas for improvement, digital documentation is proved to be beneficial for the CCM team.