Ebook: Healthcare of the Future

Healthcare of the Future, International Conference Biel/Bienne, 5 April 2019

Thomas BÜRKLE

Corresponding Author Thomas Bürkle, Bern University of Applied Sciences, Quellgasse 21, CH2501 Biel/Bienne, Switzerland; e-mail: thomas.buerkle@bfh.ch.

Bern University of Applied Sciences, Biel, Switzerland

Michael LEHMANN

Bern University of Applied Sciences, Biel, Switzerland

Kerstin DENECKE

Bern University of Applied Sciences, Biel, Switzerland

Murat SARIYAR

Bern University of Applied Sciences, Biel, Switzerland

Serge BIGNENS

Bern University of Applied Sciences, Biel, Switzerland

Erwin ZETZ

GS1 Switzerland, Bern, Switzerland

Jürgen HOLM

Bern University of Applied Sciences, Biel, Switzerland

Healthcare in 2030?

Imagine you live in the year 2030. Global warming is still a big issue. You live in the suburbs of a big city because few people still live in rural areas. You commute to work by public transport. Occasionally you will use your electric car. In many Western countries the majority of baby boomers have already reached retirement age with almost a quarter of the population older than 65, so medical care is also a constant issue.

As a human being, you can still get sick. The many elderly people and a life expectancy of almost 90 years means that chronic diseases and dementia have increased despite medical progress. However, technological progress and prevention due to increased health literacy have led to less than expected increases in health care costs. Thanks to intelligent assistants, older people can live safely at home for longer in a more self-determined manner. In 2030, digital medical services are standard via the internet. Your GP advises you via telemedical services to fill in a digital questionnaire with your medical problems. If necessary, the intelligent house-doctor system transmits measured vital and behavioural data to the family doctor. Furthermore, he requests from your electronic health record the three-monthly follow-up of your personal wearable devices, which continuously monitor your blood pressure, pulse, oxygenation, blood glucose and activity levels. His information system post-processes this huge amount of data in real time to present a medical dashboard of your current condition to your doctor while you are still in the videoconference. With the help of this decision support system your GP can easily distinguish those problems which he can solve remotely from those where he really needs to see you. He can even inform your employer that you will be unable to work for some time. The GP information system calculates in real time a recommended therapy scheme including your personal genomic data to ensure compatibility. Your GP reviews this recommendation and sends a medication order directly to the pharmacy. Amazon delivers your medication within an hour to your home with its rapid drone services. At the same time, your health insurance automatically receives a digital invoice for the treatment.

Well, like the people reading Jules Verne's “Around the World in Eighty Days” [1] in 1873, we don't know which of these scenarios might become reality in 2030, 2050 or ever, but we certainly live in a time when ubiquitous IT provides us with computers in our pockets which are powerful enough to support photography, video and audio recording, video telephony and access to a wide variety of information worldwide – we call it a mobile phone. We have already reached the stage where personalised medicine can examine the individual conditions of patients to find the appropriate therapy for each person. Data mining and artificial intelligence promise to discover new ways of treating previously incurable diseases; something which recently prompted a politician to say that within 10 years we will have overcome cancer [2]. On the other hand, an ageing society and the loss of family ties confronts us with an increasing number of elderly and multi-morbid persons striving to live independently for as long as possible.

This is the setting for the 2019 conference Healthcare of the Future. The medical informatics conference is centred around emerging digital communication options and their influence on future medical treatment. It originates from a research project which started in 2012 [3] with a scenario similar to the beginning of this introduction. A clinical pathway was drawn up for the case of an elderly Swiss lady called Elisabeth Brönnimann-Bertholet, who is suffering from diabetes and hypertension, under the assumption that her progredient hip arthrosis now requires surgery (fig 1).

In a visionary brainstorming process, Bern University of Applied Sciences BFH, the Swiss branch of the standardizing organization GS1 [4] and the umbrella association of the Swiss business sector ‘Economiesuisse’ [5] analysed the required medical and information processes and drafted an innovative cross-sectoral treatment pathway for Mrs. Brönnimann to obtain a total hip endoprosthesis (TEP). Communication within the pathway relied on emerging information technologies [3].

In the meantime, a new bachelor study programme for medical informatics has been founded [6], a department for medical informatics established, and an institute for medical informatics research constituted at the BFH. With this background, a larger second research project called “Hospital Of The Future Live” (SDZL) [3] began in 2016, with 25 partners including six Swiss hospitals, four major IT suppliers, IHE Suisse, and eHealth Suisse: the coordinating body for the implementation of the Swiss electronic health record Electronic Patient Dossier (EPD) [7]. The goal of SDZL was to turn parts of the visionary scenario into a tangible reality – at least in the laboratory environment of BFH medical informatics. SDZL [3] had a multi-stakeholder driven approach. Project goals were set and continuously adjusted in five plenary meetings with all involved parties. The cross-sectorial treatment pathway for TEP was split into a total of 68 more or less atomic work packages at home and in the outpatient situation prior to hospitalisation, the inpatient rehabilitation sector and the return to the home situation. These work packages centred around communication-intensive tasks where either current shortcomings were found or potential for improvement was expected. Work packages were then combined into (often cross-sectorial) student projects. A detailed description of the process can be found in [3].

A good example is the electronic Medication Management Assistant eMMA. This is a laboratory prototype for an app on mobile devices designed to help patients take their medications regularly, and has the goal of improving drug therapy adherence. eMMA uses a Conversational User Interface CUI to remind the user to take their drugs. If the medication is not taken, eMMA asks for the reasons, just like relatives who chat with the elderly via SMS [8]. Primarily, this app is designed to support Elisabeth at home prior to her inpatient treatment and after her return from rehabilitation. In a future setting, however, it would also be linked to Elisabeth's inpatient treatment to convey the medication information to the hospital staff and to receive the newly updated medication scheme at discharge. The future Swiss EPD [9] could have an important role in these transitions.

The 2019 conference “Healthcare of the Future” is to some degree a result of these research projects. Our goal for the conference is to discuss advanced interaction based on modern information technology between nurses, caregivers, patients and healthcare institutions with other specialists in medical informatics in an international setting. We would like to demonstrate whether and how this interaction could improve and accelerate healthcare processes, and we would like to discuss the future role of the empowered patient within their own care process.

After a short presentation of the conference background the programme will start with the keynote

“Digital Patient Communication: Improving the Hospital-Patient Relationship”. Three sessions in the scientific track deal with the topics

• Workflows in healthcare

• How does eHealth change the care process?

• Knowledge-based IT support

In parallel we will have young two researcher sessions under the topics

• eHealth and the informed patient

• Apps to support the patients and caregivers

Biel/Bienne 14 February 2019

The Programme Committee

References

[1] J-G. Verne, Around the World in Eighty Days http://www.gutenberg.org/files/103/103-h/103-h.htm. last visited 14 Feb 2019.

[2] Online Focus Special. Spahn hält Krebs in 10 Jahren für heilbar – Krebsgesellschaft bremst ihn aus. https://www.focus.de/gesundheit/ratgeber/krebs/krebs-spahn-will-krebs-in-10-jahren-besiegen-krebsgesellschaft-bremst-ihn-aus_id_10262417.html last visited 14 Feb 2019.

[3] T. Bürkle, K. Denecke, M. Lehmann, E. Zetz, J. Holm, Integrated Care Processes Designed for the Future Healthcare System. Stud Health Technol Inform 245 (2017), 20–24.

[4] GS1 Switzerland, https://www.gs1.ch/en/home last visited 14 Feb 2019.

[5] Economiesuisse, https://www.economiesuisse.ch/en last visited 14 Feb 2019.

[6] J. Holm, T. Bürkle, R. Gasenzer, F. von Kaenel, S. Nüssli, S. Bignens, S. Il Kim, M. Lehmann, A Novel Approach to Teach Medical Informatics. Stud Health Technol Inform. 216 (2015), 1011.

[7] C. Lovis, A. Schmid, S. Wyss, ehealth Suisse – coordinating e-health in Switzerland Healthcare IT Management 6(3) (2011), 46–47.

[8] M. Tschanz, T.L. Dorner, K. Denecke, eMedication Meets eHealth with the Electronic Medication Management Assistant (eMMA) Stud Health Technol Inform. 236 (2017), 196–203.

[9] Bundesgesetz über das elektronische Patientendossier (EPDG), 2015, https://www.admin.ch/opc/de/classified-compilation/20111795/index.html last visited 14 Feb 2019.

[10] Bundesgesetz über das elektronische Patientendossier (EPDG), 2015, https://www.admin.ch/opc/de/classified-compilation/20111795/index.html last visited Dec 21st, 2018.

Digitally engaging patients in their care processes was for many years limited to sharing care related documents (e.g. laboratory or radiology findings, discharge letters) with them through personal electronic health records. Newer concepts have led to the establishment of patient portals as patient frontends to a hospitalś electronic health record. Rarely however have complete patient pathways with pre-hospitalization, inpatient stay and post-hospitalization been evaluated to identify chains of communication processes involving clinical care scenarios, as well as subsequent home monitoring scenarios. Neither have such approaches been integrated with digital communication processes related to a patientś engagement in medical research projects. In order to enhance hospital-patient relationships in a holistic manner, we hypothesize that an integrated environment (e.g. patient portal) supporting shared decision making and communication in a patient´s care situation and in the same time providing communication processes for patient research engagement will optimize the patient-hospital relationship and be supportive in binding a patient to this care providing institution.

In this paper, we examine requirements, show potential user interfaces and describe a prototypical development for a Pathway Navigator App that guides the patient through healthcare episodes. Our use case is a fictional patient requiring surgery for a hip total endoprosthesis. Fundamental is the provision of appointment information and the option to contact the healthcare provider for rescheduling. This implied an architecture which was more complicated than expected. We realized an HL7 interface for appointment data from hospital information systems; no comparable standard was found for GP IT systems. The future Swiss Electronic Patient Dossier could enhance the integration of the Path App within a broader health-IT ecosystem.

Medical imaging is undergoing rapid change, induced by the increasing amount of image data, and advances in fields such as artificial intelligence. In order for a radiology service provider to respond to these challenges, it needs to adapt its workflow. To inform optimization strategies, the way that processes and resources interact in the real world must be understood. We report on our experiences with an approach that consists of merging a variety of data sources into a data model that allows efficient interactive queries, and then providing highly interactive visualizations to explore the data. Two examples are discussed: animation of patient flow through the radiology workflow, and the use of energy consumption patterns to characterize operational modalities.

Clinical pathways are often promoted as the holy grail of efficient healthcare provision. However, our experiences during the Swiss research project Hospital of the Future demonstrated that most Swiss hospitals do not implement clinical pathways in the sense of ‘… a document describing the common process of a multidisciplinary treatment for a particular type of patient’. In this paper, we will discuss reasons for the lack of pathway implementations. We differentiate between three different categories of explanations: (i) organization-specific impediments, (ii) environmental hurdles, and (iii) inherent problems of clinical pathways. Without additional support and regulation by the policy maker, it seems rather unlikely that an increase of pathway implementations will take place in the near-future in Switzerland.

Despite enormous growth in the use of consumer self-tracking devices, the data that many patients collect about their condition is seldom integrated into conversations that take place in the clinic. In this paper we explore the potential roles that self-tracking data could play during clinical interactions between patients with Ankylosing Spondylitis (a chronic rheumatic disease) and their clinicians. We develop a model of the data-centric activities that currently take place within the rheumatology clinic, using field observations, and to discuss how self-tracking data may contribute to each of these activities. We also interview two consultant rheumatologists regarding the opportunities and challenges that the use of self-tracking data may bring. We propose four different roles for self-tracking data in the clinic and discuss possible directions for designing to support these roles.

This research project seeks to develop our understanding of the spread of influenza through social interactions, individual and group activities as well as through public attitudes towards official health responses as they occur on social media platforms. We propose to conduct a series of workshops to: 1) develop a deep understanding of current social media crisis communications practices during influenza outbreaks; and 2) to assist public health agencies and health professionals to manage these outbreaks by exploring new strategies, frameworks and approaches to the potential role and use of social media platforms. The research proposal and methods outlined in this paper describe a transformational approach that bridges the divide between academics, practitioners and the general public through engaged scholarship which involves all constituent groups equally in the design, execution and co-creation of the research themes, problem focus and proposed solutions.

We analyzed the admission workflow in three Swiss hospitals of different size for normal and emergency admissions. Our goal was to detect shortcomings mainly in the administrative admission process due to media breaks. We obtained 9 different workflows (three per hospital) and a total of 22 shortcomings in the admission process which were present or likely in two or more of the hospitals. A considerable number could be traced back to missing information requiring time consuming extra work. We drafted five potential IT-based workflow changes and made, together with the hospital partners, a cost-benefit analysis which solution would be most interesting. As a result, a concept for an open multi center hospital admission portal was drafted, which, in theory, should influence 8 of the 22 problems found. Specifically, the prototype of the portal was designed for a direct triangular interaction between the referring doctor, the patient and the hospital staff.

The material master data catalogue in large hospitals may well exceed 50'000 articles required at one or another location for patient diagnosis and treatment. Most hospitals use a commercial material management IT system to deal with orders, eProcurement, incoming goods, warehouse management, internal commissioning and distribution. An analysis in three Swiss hospitals (including a hospital chain) demonstrated however, that despite existing standards maintenance of the material master data catalogue is often done manually based on different incoming formats such as csv, mail etc. We present components, which may enable seamless master data update using standardized formats and discuss in detail current barriers within hospital supply to give finally recommendations how to overcome them.

The World Health Organization estimates that as much as 80% of the population uses Traditional Medicine (TM) in some form, and in particular, herbal-based Traditional Medicine (HTM). However, TM is mostly orally transmitted and suffers from lack of standardizations and lack of computable TM data. Shareable standards could enable computational support of TM data management. In this paper, we outline the design and development of the West African Herbal Traditional Medicine (WATRIMed) Knowledge Graph (KG), which is an effort for bringing West Africa TM to the digital world and help establishing bridges with conventional medicine. WATRIMed entities have been enriched with knowledge from external publicly available knowledge bases and further mapped with the BioTopLite Upper Level Ontology. As of result, the model of the publicly available KG currently comprises 472 Concepts and 75 Properties (57 object properties and 18 data properties). It describes formally 115 medicinal plants, 179 chemical compounds and 67 recipes.

While clinical information systems usually store patient records in database tables, human interpretations as well as information transfer between institutions often require that clinical data can be represented as documents. To automate document generation from patient data in conjunction with the rich computational facilities of clinical decision support, we propose a template-based extension of the Arden Syntax, and discuss the benefits and limitations observed during a pilot application for patient recruitment. While the original Arden Syntax supports string concatenation as well as the substitution of unnamed placeholders, we integrated an additional method based on embedding expressions into strings. A dedicated parser identifies the expressions and automatically substitutes them at runtime, which can for example be harnessed to display the most recent value from a time series. The resulting mechanism supports the generation of extensive clinical documents without the need to apply specific operators. To evaluate the proposed extension, we implemented an Arden module that identifies an intensive care patient cohort that conforms to the eligibility criteria of a clinical trial and outputs a concise patient overview in different document formats. While string interpolation in the original Arden standard has been tailored to clinical event monitoring, we interpret that our accessible approach usefully extends Arden's data-to-text capabilities. Future research might target the development of an interactive template editor that would hide the complexity of formatting directives and conditional expressions behind a graphical user interface, and explore how computer-linguistic formalisms might facilitate advanced features such as automatic inflections of verbs and nouns.

Medication adherence is a widely recognized problem that is linked to overuse of healthcare system and negative health outcomes. Among the causes of non-adherence, forgetfulness plays a central role. mHealth interventions are particularly interesting to support medication adherence. Unfortunately, there is a lack of information about the quality and effectiveness of the app available on the market. In this article, we present the design and evaluation of an app for the Swiss market. The app was developed with a user-centered approach and was evaluated by both experts and end-users. The app functions include facilitated medication data entry through barcode scanning, and access to educational materials for specific drugs. Although the evaluation by experts and end-users revealed usability issues, such as the inability to customize the app, and a low evaluation of the performance (subjective assessment), it also found that the app contained most of the core functionalities that are expected for a medication adherence app. These are promising results, and will guide the future development of the app to respond to both experts and user expectations.

New developments in healthcare require an increased disease self-management of patients. Intelligent digital assistants equipped with a conversational user interface are intended to support patients in this challenging task by providing reminders, answering questions, or supporting in self-monitoring tasks. In this paper, we study the potentials of intelligent conversational agents in healthcare. We realized three systems for three different use cases (patient education, disease management, self anamnesis). Based on these implementations and experiences with usability tests, we performed an analysis of strengths, weaknesses, opportunities and threats (SWOT) using a questionnaire. The results show that conversational agents used in healthcare applications can be helpful. However, they have to be integrated into the healthcare process, supporting also the interaction between the healthcare team and a patient. In order to be attractive for a long-term usage, the scope of operation should autonomously adapt to the current health situation of a patient to provide relevant functionality as needed.

Automatic comparison of routinely collected EHR data with trial eligibility criteria can speed up patient recruitment. The present work aims to analyze to what extent the Austrian nation-wide EHR system ELGA could support this task. Using the open source tool ART-DECOR we tried to map a reference list of 150 common eligibility criteria specified in the EHR4CR project to the HL7 CDA templates that describe the structure of ELGA document types. For 61% of the criteria mappings could be made to ELGA template elements holding structured data. Comparing our results with similar work, we conclude that ELGA could be a useful component for the automatic identification of trial patients.

The EU falsified Medicines Directive 2011/62/EU will be applied in Switzerland as well. It mandates unique identifiers on medication packages and a process to ensure that these identifiers are decommissioned when the medication package is handed to the patient. While this is not a major problem for Swiss community pharmacies, it is yet unclear how decommissioning shall be managed within hospitals. This paper analyses the drug supply chain in 5 Swiss hospitals and drafts a system architecture to support a decommissioning process upon arrival of new drug deliveries at the hospital pharmacy.

An electronic health record (EHR) will be established nationwide in Switzerland in 2020. Patients can decide on their own whether they open an EHR. It is still unclear what might influence the patient decision. For this reason, we performed an online survey among the Swiss population to study whether there is a lack of knowledge on the EHR which impacts the willingness to open a personal health record and agree to health data sharing. A questionnaire with 13 question was distributed in a period of 4 weeks. More than 1200 participants replied to the survey. The results were analyzed with statistical methods. There are correlations between some of the questions in our survey. We conclude that the willingness to open a personal health record directly depends on the trust into the enabling technology.

In previous work, a mobile application for medication self-management (eMMA) was introduced. It contained a basic conversational user interface (CUI). In this work, we extended the CUI by integrating the chatbot framework RiveScript and an instruction interface. To study task success, dialog quality and efficiency, we performed a theoretical and a quantitative evaluation as well as a usability test. The results show that the technical extensions of eMMA were useful to improve the chatbot's quality. However, the underlying knowledge base still requires substantial extensions before the system can be used in practice.

This work concerns methods for automated rating of the progression of Multiple Sclerosis (MS). Often, MS patients develop cognitive deficits. The Brief Visuospatial Memory Test-Revised (BVMT-R) is a recognized method to measure optical recognition deficits and their progression. Typically, the test is carried out on paper using geometric figures which the patient should recognize and trace. The results are rated manually by a physician. The goal of this work was to digitize the BVMT-R and to support the interpretation of the test results using a machine learning (ML) algorithm. A convolutional neural network (CNN) was used to rate the drawings of a patient. As a result, the correct point value of the BVMT-R could be determined with an accuracy between 57% and 76% based on a training set of 624 patient drawings obtained from 135 patients. These drawings had been previously physician rated to serve as a gold standard. In our experiment, we obtained reasonable accuracy above 80% when more than 40 drawings were available, but our training sample was too small for more detailed analysis.

Conclusion: At the currently achieved classification accuracy, results analysis will remain a physician task, potentially supported with ML based preclassification, but there is hope that ML accuracy can be further improved to enable automated follow-ups.

Cancer is the second leading cause of death in Switzerland. Patients who have been diagnosed with colorectal carcinoma and received curative surgical R0-Resection frequently relapse or develop metastases in the first 2–3 years postoperatively. With timely detection through appropriate aftercare, some of these patients could potentially be cured. In order to optimize follow-up adherence, we implemented a study environment based on an app, which reminds patients to schedule their follow-up appointments timely with their GP or specialist. In addition, the study environment comprises a central server to collect pseudonomized study data regarding follow-up compliance. The next step will be a study to evaluate the potential impact of such an app. We present the outline of the planned study.