How can social robot use cases in healthcare be pushed - with an interoperable programming interface.

INTRODUCTION: Research into current robot middleware has revealed that most of them are either too complicated or outdated. These facts have motivated the development of a new middleware to meet the requirements of usability by non-experts. The proposed middleware is based on Android and is intended to be placed over existing robot SDKs and middleware. It runs on the android tablet of the Cruzr robot. Various toolings have been developed, such as a web component to control the robot via a webinterface, which facilitates its use. METHODS: The middleware was developed using Android Java and runs on the Cruzr tablet as an app. It features a WebSocket server that interfaces with the robot and allows control via Python or other WebSocket-compatible languages. The speech interface utilizes Google Cloud Voice text-to-speech and speech-to-text services. The interface was implemented in Python, allowing for easy integration with existing robotics development workflows, and a web interface was developed for direct control of the robot via the web. RESULTS: The new robot middleware was created and deployed on a Cruzr robot, relying on the WebSocket API and featuring a Python implementation. It supports various robot functions, such as text-to-speech, speech-to-text, navigation, displaying content and scanning bar codes. The system's architecture allows for porting the interface to other robots and platforms, showcasing its adaptability. It has been demonstrated that the middleware can be run on a Pepper robot, although not all functions have been implemented yet. The middleware was utilized to implement healthcare use cases and received good feedback. CONCLUSION: Cloud and local speech services were discussed in regard to the middleware's needs, to run without having to change any code on other robots. An outlook on how the programming interface can further be simplified by using natural text to code generators has been/is given. For other researchers using the aforementioned platforms (Cruzr, Pepper), the new middleware can be utilized for testing human-robot interaction. It can be used in a teaching setting, as well as be adapted to other robots using the same interface and philosophy regarding simple methods.

Usability Evaluation in a Remote Access Scenario.

We present an approach to use the think aloud method for formative usability evaluation for medical software in a remote access scenario which combines researchers in two different locations and test persons distributed across five Swiss hospitals into one study using MS-Teams. We could show that a) these tests can be performed remote in a tight time schedule and b) that results valuable for the formative development of the examined mockup solution could be achieved. Two sessions had to be rescheduled for technical problems but all test persons could complete the think aloud study in 30 minutes at their usual working environment. This offers the opportunity to software providers to develop medical software with better usability in close cooperation with future users.

Medical Informatics in a Tension Between Black-Box AI and Trust.

For medical informaticians, it became more and more crucial to assess the benefits and disadvantages of AI-based solutions as promising alternatives for many traditional tools. Besides quantitative criteria such as accuracy and processing time, healthcare providers are often interested in qualitative explanations of the solutions. Explainable AI provides methods and tools, which are interpretable enough that it affords different stakeholders a qualitative understanding of its solutions. Its main purpose is to provide insights into the black-box mechanism of machine learning programs. Our goal here is to advance the problem of qualitatively assessing AI from the perspective of medical informaticians by providing insights into the central notions, namely: explainability, interpretability, understanding, trust, and confidence.

Embedding Risk-Based Anonymization into Data Access Control for Providing Individual-Level Health Data in a Secure Way.

Especially in biomedical research, individual-level data must be protected due to the sensitivity of the data that is associated with patients. The broad goal of scientific data re-use is to allow many researchers to derive new hypotheses and insights from the data while preserving privacy. Data usage control (DUC) as an attribute-based access mechanism promises to overcome the limitations of traditional access control models achieving that goal. Park and Sandhu provided the usage control (UCON) model as an instance of DUC, which defines policies that evaluate certain attributes. Here, we present an UCON-based architecture, which is augmented with risk-based anonymization as provided by the R package sdcMicro and an extensible Access Control Markup Language (XACML) environment with a core policy decision point as implemented by authzforce.

Pro-Active Detection of Potentially Wrong Diagnoses Due to Substantial Changes of Laboratory Measurements.

For guiding decisions on medical diagnoses and diagnoses, it is crucial to receive valid laboratory test results. However, such results can be implausible for the physician, even if the measurements are within the range of known reference values. There are technical sources of implausible results that are related to the laboratory environment, which are frequently not detected through usual measures for ensuring technical validity. Here, we describe the development of a quality assurance tool that tackles this problem and replaces the current manual statistical analyses at the Center for Laboratory Medicine in St Gallen (ZLM). Further analysis of the factors responsible for shifts in laboratory test results requires to collect and analyze data related to reagents as well as calibration or reference probes. Due to a lack of standard operating procedures in many laboratories with respect to these processes, this remains one of the big challenges.

Developing an Ontology for Documenting Adverse Events While Avoiding Pitfalls.

Ontologies promise more benefits than terminologies in terms of data annotation and computer-assisted reasoning, by defining a hierarchy of terms and their relations within a domain. Here, we present central insights related to the development of an ontology for documenting events during interoperative neuromonitoring (IOM), for which we used the Basic Formal Ontology (BFO) as an upper-level ontology. This work has the following two goals: to describe the development of the IOM ontology and to guide the practice with respect to documenting of biomedical events, as available ontologies pose difficulties on certain issues. We address the following issues: (i) differentiate between the sets documentation, identification, continuant and explanation, understanding, occurrent as we had problems in applying the available ontology of adverse events, (ii) covering diseases and injuries in a consistent way, and (iii) deciding on which level to define relations.

Digi-Care: Exploring the Impacts of Digitization on Nursing Work in Switzerland.

In this paper we present first findings of the Digi-Care project, a multidisciplinary, multi-stakeholder research project investigating the impacts of digitization on nursing work practices and in particular the transmission of patient care information within and beyond nursing work practices. We completed the initial data collection of the funded 3-year research project and report on a plethora of significant and critical IT-related events. Some of them can be attributed to usability issues.

On the Concepts of Identity and Similarity in the Context of Biomedical Record Linkage.

Record linkage refers to a range of methods for merging and consolidating data in a manner such that duplicates are detected and false links are avoided. It is crucial for such a task to discern between similarity and identity of entities. This paper explores the implications of the ontological concepts of identity for record linkage (RL) on biomedical data sets. In order to draw substantial conclusions, we use the differentiation between numerical identity, qualitative identity and relational identity. We will discuss the problems of using similarity measures for record pairs and quality identity for ascertaining the real status of these pairs. We conclude that relational identity should be operationalized for RL.

Using Business Intelligence Tools to Support Medical Validation of Laboratory Tests.

Modern clinical laboratories have to confirm that the procedures used for specific tests are reliable and valid. There are several sources of errors and interferences that can invalidate the results. Medical validation refers to the plausibility check of the test results. Implausible results indicate that something might went wrong with a sample retrieved from the patient, e.g., the blood sample got contaminated with another fluid, which requires re-examination. Here, we describe how an integrated R-based business intelligence (BI) tool can be developed that increase the efficiency of the medical validation at the Institute of Clinical Chemistry (ICC) of the University Hospital Zurich. A BI software environment allowed us to digitalize steps in the validation process that were manually done in Excel worksheets, e.g., importing the data, calculating percentiles, and producing graphical outputs.

Sensor-Based Decision Support for the Allocation of Patient Attendants in Hospitals.

In hospitals, patient attendants are often necessary in order to closely monitor patients with high risk of self-endangering actions and reactions. However, such additional monitoring of patients is associated with high costs. In this paper, we describe a technical infrastructure for monitoring the patient's activities, which helps to assess whether an attendant should be requested. It was central to for us to use non-invasive sensors and to exploit a variety of patient data such as heart rate, micro-activity and oxygen saturation.

Prototyping a Tool for Processing Genetic Meta-Data in Microbiological Laboratories.

Next generation sequencing (NGS) technologies allow improved understanding of pathogens. In the upstream processing of generating genomic data, there is still a lack of process-oriented tools for managing corresponding meta data. In this paper, we provide a description of how a process-oriented software prototype was developed that allowed the capture and collation of metadata involved when doing NGS. Our question was: How to develop an interactive web application that supports the process-oriented management of genetic data independent of any sequencing technique?

Current Reasons for Not Using Clinical Pathways in Practice.

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.

Streamlining Hospital IT - Improving the Admission Process.

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.

Cross-Institutional Pathway Guidance - Chance or Extra Burden?

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.

Components for Material Master Data Management in Swiss Hospitals.

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.

Last Mile Towards Efficient Healthcare Delivery in Switzerland: eHealth Enabled Applications Could Speed Up the Care Process.

A precise and timely care delivery depends on an efficient triage performed by primary care providers and smooth collaboration with other medical specialities. In recent years telemedicine gained increasing importance for efficient care delivery. It's use, however, has been limited by legal issues, missing digital infrastructures, restricted support from health insurances and the digital divide in the population. A new era towards eHealth and telemedicine starts with the establishment of national eHealth regulations and laws. In Switzerland, a nation-wide digital infrastructure and electronic health record will be established. But appropriate healthcare apps to improve patient care based on this infrastructure remain rare. In this paper, we present two applications (self-anamnesis and eMedication assistant) for eHealth enabled care delivery which have the potential to speed up diagnosis and treatment.

Integrated Care Processes Designed for the Future Healthcare System.

Previous studies showed that a stronger focus on integrated care models is required, targeting at a seamless coordinated care reaching patients even at home and thus establish patient centered and patient driven innovation activities. Such integrated care model is important among others for ensuring traceability that is necessary when problems during treatment occur or in cases of product counterfeiting for ensuring patient safety. The objective of our work is to realize an efficient, continuous care process, considering an optimal, end-to-end treatment path. In this paper, we describe the process how to pave the way for developing technologies for realizing a cross-sector treatment pathway. Following a multi-stakeholder principle and by applying requirement analysis and world café methodology we designed first concepts and strategies.

A Novel Approach to Teach Medical Informatics.

The Bern University of Applied Sciences established the first Swiss Bachelor of Science in Medical Informatics. We demonstrate the specifics of the new curriculum that was based on requirements analysis and includes seminars and live case studies to enable problem-solving abilities.