Ebook: dHealth 2020 – Biomedical Informatics for Health and Care

This eBook was intended to be the Proceedings of the dHealth 2020 annual conference event on the general topic of “Health Informatics meets Digital Health”. As of this writing, however, we had to cancel the physical event as a consequence of the COVID-19 crisis that had gained control of Austria and most other home countries of our international authors and visitors. Nevertheless, we decided to go ahead with publishing the proceedings. On the one hand side, to keep the momentum and to avoid an empty space in the rather long row of proceedings of this conference, which spans 14 years already. On the other hand, we think that this year’s special topic: “Biomedical Informatics for Health and Care” is also very timely. We chose it to indicate that, already today, but even more in the future, ICT systems in healthcare and biomedical systems and devices will increasingly be intertwined. Both scientific disciplines, i.e. biomedical engineering and health informatics, are obviously closely related to each other and it is often difficult to delineate where the one ends and the other begins.

Successful healthcare depends on the complete chain of flow of information from the sensor via multiple steps of processing to the actuator, which can be anything from a human healthcare professional to a robot. Along this pathway, methods for automating the information processing, like signal processing, machine learning, predictive analytics and decision support, play an increasing role to provide actionable information and to support personalized and preventive healthcare concepts, in both biomedical and digital healthcare systems and applications.

Moreover, since 2007, this series of annual conferences has been organized by the joint working group for “Medical Informatics and eHealth” of the Austrian Society for Biomedical Engineering (OEGBMT).

http://www.oegbmt.at/arbeitsgruppen/medizinische-informatik-und-ehealth

and the Austrian Computer Society (OCG).

https://www.ocg.at/medizinische-informatik-und-ehealth

This unique group was founded in 1981 and, since then, has been a forum for the many scientists, experts and practitioners with a stake in both worlds, the world of Biomedical Engineering and Medical Informatics. As such, this year’s subtitle was also motivated by making this long-lasting partnership more explicit.

In these times of the COVID-19 crisis, it becomes evident not just to the ones deeply involved in health technology and health care, but for the general public as well, that data collected from many individuals, collected from different sensors (lab tests, body temperature values, etc.) are essential to assess the situation and inform the process of developing strategies to get this crisis under control from the epidemiological point of view. However, we also need the actuators, in this case ventilators, to finally deliver life support to severely ill patients, and the data provided by these systems need to be collated and fed into systems that provide actionable information to the healthcare professionals at the front line. This is extremely important in such a crisis situation, where the number of affected patients exceeds any previously conceived dimension and, at the same time, a server shortage of knowledgeable healthcare professionals happens.

With a deadline for submission at the end of January, none of the papers deals with the pandemic directly. Nevertheless, many of the papers in the proceedings deal with important aspects in that respect. Now, the described innovations in the realms from telehealth to decision support systems need to be focused on application fields like monitoring COVID-19 patients at home as long as possible or to analyze the EMR data from hospitalized patients in order to help healthcare professionals prioritize their limited resources.

In conclusion, we need to learn fast a lot of new things to navigate this situation. No matter what our specific discipline is, we need to devote our skills and energy to help managing this so far unprecedented situation.

Graz, April 2020

Günter Schreier

Dieter Hayn

Alphons Eggerth

Ultrasound imaging enables in-vivo investigations of muscle and tendon behaviour during human movement. Individual contributions of muscles and tendons to the behaviour of the whole muscle-tendon unit during locomotion are versatile. Therefore, movements of distinct landmarks, such as muscle tendon junctions are recorded and tracked in order to investigate internal dynamics of the muscle-tendon complex. In this study, we use a semi-automatic tracking method based on image segmentation and investigate how tracking accuracy can be improved using a sticks filter. We demonstrate that a speckle reduction decreases the root-mean-square error of the tracking result by up to 78.1%, depending on the chosen window size of the sticks filter.

Optoelectronic neurostimulation is a promising, minimally invasive treatment modality for neuronal damage, in particular for patients with traumatic brain injury. In this work, a newly developed optoelectronic device, a so-called photocap, based on light-activated organic semiconductor structures with high spatial and temporal resolution is investigated. To prove and verify the feasibility of this new technology, a mathematical model was developed, simulating the electrical response of excitable cells to photocap stimulation. In the first step, a comprehensive technical review of the device concept was performed, building the basis for setting up the simulation model. The simulations demonstrate that photocaps may serve as a stimulation device, triggering action potentials in neural or cardiac cells. Our first results show that the model serves as a perfect tool for evaluating and further developing this new technology, showing high potential for introducing new and innovative therapy methods in the field of optoelectronic cell stimulation.

Conduction of clinical trials may benefit from the reuse of EHR data. The upcoming EHR system eHDSI provides data exchange between European countries and thus represents an attractive data source for multinational trials. In this paper we analyze to what extent eHDSI could provide data relevant for trials with a focus on patient recruitment. Data elements identified in the EHR4CR project to be frequently used in trials were mapped to the HL7 templates of the eHDSI document types using the open source tool ART-DECOR. From the 149 EHR4CR data elements, 44 (30%) could be mapped to eHDSI document components. Despite this moderate coverage, eHDSI could still provide a substantial contribution for recruitment by an automatic pre-filtering process of large groups of potential trial candidates.

Background:

Privacy-preserving record linkage (PPRL) is the process of detecting dataset entries that refer to the same individual within two independent datasets, without disclosing any personal information. While applied in different fields, it particularly attained importance in the medical sector. One popular PPRL method are Bloom filters. However, Bloom filters were originally used for encoding strings only.

Objectives:

This paper evaluates an encoding method specifically designed for numerical data and adjusts it for encoding geocoordinates in Bloom filters.

Methods:

The proposed numerical encoding of geocoordinates is compared to the string-based method by using synthetic data.

Results:

The proposed method for encoding geocoordinates in Bloom filters attains a higher recall and precision than the conventional string encoding.

Conclusion:

Numerical encoding has the potential of increasing the record linkage quality of Bloom filters, as well as their privacy level.

Background:

Dysphagia is a dysfunction of the swallowing act and is highly prevalent in acute post-stroke patients and patients with chronic neurological diseases. Dysphagia is associated with several potentially life threatening complications. Thus, an early identification and treatment could reduce morbidity and mortality rates.

Objectives:

The aim of the study was to develop a multivariable model predicting the individual risk of dysphagia in hospitalized patients.

Methods:

We trained different machine learning algorithms on the electronic health records of over 33,000 patients.

Results:

The tree-based Random Forest Classifier and Adaboost Classifier algorithms achieved an area under the receiver operating characteristic curve of 0.94.

Conclusion:

The developed models outperformed previously published models predicting dysphagia. In future, an implementation in the clinical workflow is needed to determine the clinical benefit.

Changes in lipid homeostasis can lead to a plethora of diseases, raising the importance of reliable identification and measurement of lipids enabled by bioinformatics tools. However, due to the enormous diversity of lipids, most contemporary tools cover only a marginal range of lipid classes. To reduce such a shortcoming, this work extends the lipid species covered by Lipid Data Analyzer (LDA) to galactolipids and oxidized lipids. Appropriate mass lists were generated for MS¹ identifications and the proprietary decision rule sets were extended for MS² identifications of the novel lipid classes. Furthermore, LDA was extended to enable identification of oxidatively modified fatty acyl chains. With these extensions, LDA can reliably identify the most important galactolipids as well as oxidatively modified versions of the 22 previously implemented lipid classes. Comparison with other up to date lipidomics tools show that LDA has a better coverage of the newly implemented lipid species. The extended version of LDA provides researchers with a powerful platform to elucidate diseases caused by perturbations in the oxidized lipidome. LDA is freely available from https://genome.tugraz.at/lda.

Background:

Heart failure is a chronic disease that affects around 26 million people worldwide. Projections assume a substantial increase in prevalence over the next years. To improve the survival rate and quality of life in patients suffering from heart failure, the European Society of Cardiology published guidelines for diagnosis and treatment. Adherence of healthcare professionals’ medication prescriptions with regard to these guidelines is critical for optimal outcomes.

Methods:

Data from the conceptional phase of the existing disease management network ‘HerzMobil Tirol’ were analysed. Prescriptions and patient- reported intake data of the four major substances of recommended heart failure medication were used to calculate the relative prescribed doses as a percentage of the recommended target doses. A concept for visualisation of the prescription status was developed in cooperation with health professionals.

Results:

The documented prescriptions were analysed and used to develop a mock-up in order to visualise the prescription status for the individual patient.

Conclusion:

Analysis and visualisation can be managed by displaying the calculated daily relative dose per substance group in a traffic light system.

Background:

Patient appointment scheduling is one of the main challenging tasks in the healthcare administration and is constantly in the focus of theoretical researches.

Objectives:

The aim of this study was to investigate the applicability of the P-graph (Process graph) methodology to find the n-best alternative for patient’s scheduling.

Methods:

The patient appointment scheduling task was formalised as an integer linear programming problem and was considered as a process network synthesis problem. The optimal and n-best alternative solutions were determined by an efficient branch and bound algorithm implemented in a decision support system.

Results:

Experimental results show, that the P-graph methodology can be effectively applied to produce the optimal scheduling for the examinations and to find the alternatives of the best scheduling.

The research project 3P- Patients and Professionals in Productive Teams has studied different patient-centred teamwork models for patients with chronic conditions and multi-morbidities. This paper presents outcomes from a qualitative study on the information flow and technology use in patient-centred care teams utilizing telemedicine, located in three health regions of Norway and Denmark. The aim was to identity barriers for collaborative work and propose models for the e-solutions of the future. The study showed fragmentation in information storage with limited interoperability causing that several systems had to be used for telemedicine follow-up and there was limited teamwork support functionality.

Background:

The Community of Inquiry (CoI) describes success factors for online-based learning.

Objectives:

To develop approaches for automatic analysis of CoI to be visualized within student and teacher dashboards.

Methods:

Extending indicators from social network analysis and linguistics; evaluation within a case study.

Results:

The project is just starting.

Conclusion:

Results will help to better understand and improve cooperative online-based learning in higher education.

Background:

Information and communications technologies (ICTs) may facilitate shorting length of stay (LOS) of patients through the optimization of processes and delivery services.

Objectives:

This study aims to provide technology-based solutions and interventions based on health information technology (HIT) that have optimization potentials of patients’ LOS.

Methods:

This review study searched papers in PubMed, Scopus as well as Google Scholar without presuming time limits by the end of 2019. English and Persian Papers were included, which addressed an association between the ICT and LOS as well as its positive effect in shortening LOS.

Results:

Identified technologies were finally classified into eleven groups. Based on the findings, common health technologies such as health information systems, telemedicine especially tele-consultation, electronic discharge planning tools, and visual analytical dashboards in order to expedite the process and help to optimize LOS seem appropriate.

Conclusions:

HIT-based interventions have potential that may support better management of processes related to patients' admission, hospitalization, and discharge. However consistently evaluation along with using any new technology is necessary.

Background:

Fitbit and Garmin motion tracker devices are highly used in research. The validity and reliability of these devices is proven for healthy adults between 18 and 64.

Objectives:

Comparing data output of two devices.

Methods:

Observational case study on a test track and in the domestic environment of a 80- year-old female multimorbide geriatric patient.

Results:

High significant correlation of the devices on the test track [r=.776, p≤.001, Bca-CI-95% (.618;.874), N=33], but significant different in the domestic environment over time (z=4.840, p≤.001).

Conclusion:

The dominant/non-dominant body side and further sources of error may play a role in monitoring steps with these devices.

Background:

Telemedicine technology with the development of mobile applications (apps) has provided a new approach for the follow-up of patients.

Objectives:

This study aims to carry out an overview of the studies related to the use of mobile apps in the follow-up of surgical patients.

Methods:

In this study, an electronic search of four databases included PubMed, Scopus, Embase, and web of science was carried out. It included studies in the English language from the beginning of 2009 to June 2019.

Results:

Twenty-three articles were selected for the final analysis, that all of them were published from 2015 onwards. In most studies, fourteen to thirty-days follow-up period for different outpatient and inpatient surgeries was planned. Apps’ components in the studies mostly include indexes for evaluation of recovery quality, pain level, and the surgical site infection. The most important achievement of studies included feasibility, early detection of complications, reducing unscheduled in-person visits, patients’ self-efficiency, and satisfaction.

Conclusions:

Our review showed that mHealth-based interventions have potential that may support better management of post-discharge systematic follow-up of surgery patients.

Over the last few decades, implantable defibrillators have become an established method of treating malign cardiac arrhythmias. There are some situations, however, in which it would be premature to implant a permanent defibrillator. In such cases, a wearable cardioverter defibrillator (WCD) can provide temporary relief and protect patients from life-threatening cardiac arrhythmias. Treatment with WCD is now included in national and international guidelines. Nevertheless, there are still some deficits in connection with WCD, especially regarding rescue chain optimization. For example, there is currently no telemedical link in place to emergency call centers and healthcare practitioners in the case of an event. Likewise, there are still some problems with rhythm analysis, concerning both shock delivery and cardiopulmonary resuscitation (CPR). These deficits are now to be addressed within the framework of MiniDefi, a project funded by the German Federal Ministry of Education and Research (BMBF). The concepts are described here for the first time.

Background:

The process of developing a medical device has become increasingly complex, not least because of the Medical Device Regulation. Some of the associated changes affect in particular the software development companies. One of the challenges to provide safe software products is the usability engineering process. Adequate methods must be identified to find severe usability issues effectively and efficiently.

Objectives:

The aim of this study was a comparison of normative recommended formative evaluation methods.

Methods:

Two expert-based methods and two user-based methods were compared regarding effectiveness in finding issues, the level of detail and the temporal effort.

Results:

The heuristics and the isometrics, both showed a significant advantage regarding the effectiveness and similarity in level of detail and temporal effort.

Conclusion:

Based on this paper, the heuristics and the isometrics, both can be recommended, but further studies are necessary to consolidate this statement. Also, further methods should be considered, and more test persons must be involved to give an overall comparison of formative evaluation methods in the usability process of medical apps.

Background:

Audit trails of health information systems are not useful for business analytics.

Objectives:

To show how recent developments can be utilized to enable process mining in radiology.

Methods:

The SWIM lexicon is used to code the workflow steps.

Results:

Seven activities with their corresponding RadLex codes.

Conclusion:

The semantic enrichment of audit trails is an important step in operationalizing and improving the workflows in radiology.

Background:

Big Data Analytics is changing the way medical information is processed. FHIR aims to provide a robust infrastructure to enable the interoperability of clinical information.

Objectives:

Analyze the ongoing development of analytical implementations of FHIR.

Methods:

Pragmatic Review of current research and implementation projects.

Results:

US healthcare providers have implemented FHIR in their products, enabling scalable analytical tools. Europe demonstrated interest in FHIR.

Conclusion:

The potential of FHIR analytics is a value-added use case of the implementation of FHIR.

Frailty condition is an intermediate state in the ageing trajectory, preceding the onset of disability, and is becoming both challenging and priority to guarantee the sustainability of healthcare systems. To address it, we designed a software platform for supporting CGA and monitoring the activities performed at patients’ dwelling. We have implemented an alert engine to inform the care professionals of intrinsic capacity decline, and a decision support system for referral recommendations. Besides, the platform enables them to provide tailored interventions to their patients.

Background:

Connecting currently existing, heterogeneous rare disease (RD) registries would greatly facilitate epidemiological and clinical research. To increase their interoperability, the European Union developed a set of Common Data Elements (CDEs) for RD registries.

Objectives:

To implement the CDEs and the FAIR data principles in the Registry of Vascular Anomalies (VASCA).

Methods:

We created a semantic model for the CDE and transformed this into a Resource Description Framework (RDF) template. The electronic case report forms (eCRF) were mapped to the RDF template and published in a FAIR Data Point (FDP).

Results:

The FAIR VASCA registry was successfully implemented using Castor EDC (Electronic Data Capture) software.

Conclusion:

FAIR technology allows researchers to query and combine data from different registries in real-time.

Mobile applications (apps) can improve health outcomes. In this study, we have described an app developed for documenting the history of vaccination among Syrian children in one of the largest refugees’ camps in the Middle East region. This app includes health education information and automated reminders for parents, using a visual tool for parents with low literacy level. We have emphasized on the usability and technical concerns and have described the interdependency of technical and human considerations for such health app solution in a marginalized context.

Delirium is an acute mental disturbance that particularly occurs during hospital stay. Current clinical assessment instruments include the Delirium Observation Screening Scale (DOSS) or the Confusion Assessment Method (CAM). The aim of this work is to analyze the performance of machine learning approaches to detect delirium based on DOSS and CAM information obtained from two geropsychiatric wards in Tyrol. From a machine learning perspective, the questions of these two assessment instruments represent the features and the ICD 10 diagnoses of delirium (yes/no) is the corresponding class variable. We compare seven popular classification methods and analyze the performance and interpretability of the learning models. As our dataset is highly imbalanced, we also evaluate the effect of common sampling methods including down- and up-sampling methods as well as hybrid methods. Our results indicate a high predictive ability of advanced methods such as Random Forest that can handle even unbalanced datasets. Overall, combining a good performance of a prediction model with the ability of users to understand the prediction is challenging. However, for clinical application in fully electronic settings, a good performance seems to be more important than an easy interpretation of the prediction by the user. On the other hand, explanations of decisions are often needed to assess other criteria such as safety.

Background:

The quality requirements for medical software have become increasingly demanding. Several quality standards and models are already in place, but there is a debate on whether these are specific enough for medical software. Moreover, mapping requirements to quality criteria can be challenging but is required throughout the software development process.

Objectives:

We propose a workflow in which we apply proven methods and tools for systematic collection, analysis, and evaluation of software quality criteria based on the ISO/IEC 25010:2011.

Methods:

We employ affinity diagrams, Kano analysis and quality function deployment for the systematic requirement development, analysis, and management.

Results:

We outline a systematic approach on how to use the recommended process when developing medical software.

Conclusion:

The paper proposes a systematic approach for requirements management that could be used for mapping medical software quality criteria and stakeholder requirements, independent from the quality criteria (and the underlying model) itself.

Background:

Based on socio-economic and medical improvements as well as healthier lifestyles, a majority of baby boomer pensioners still feel fit and active and thus may struggle with transitioning into retirement. They could benefit from an ICT system to ease their transition into retirement and support general well- being.

Objectives:

The aim of this paper was to gain insights into the requirements for a digital coach to support their transition into retirement.

Methods:

Two rounds of focus groups with older employees close to retirement, people just retired and relatives of retired were conducted. Outcomes were then identified through a framework analysis and integrated into the design of a digital coach.

Results:

Four functional groups (i) physical activity, (ii) cognitive support, (iii) emotional support and (iv) social support were identified.

In this qualitative study, we explored the nurses’ experience in using hospital information systems (HIS) to identify barriers and facilitators of using this system. We interviewed twenty one purposefully-selected nurses who have experience in using HIS and analyzed the data using conventional content analysis. We identified 17 facilitators and 12 barriers classified into main themes. Lack of support for nurses, their resistance, any force for using HIS, perceived difficulty of using HIS, inadequate system quality, data loss, discontinuity of information in different systems are the main barriers. However, considering nurses’ perspectives, pilot implementation of HIS, training, planned implementation, appropriate financial and non-financial incentives, adding new and appropriate functionalities, increased ease of use and usability, easy access to information, improved data quality in HIS, and saving nurses’ working time through using HIS result in increased adoption the system to use.