Volume 61, Issue 5-6 - Digital Health / Guest Editors: Hannes Schlieter, Ali Sunyaev, Rüdiger Breitschwerdt, Martin Sedlmayr

The Medical Device Directive (MDD) will be replaced on 26.05.2020 by the new Medical Device Regulation (MDR). The European Parliament wants to create a transparent, solid, predictable and sustainable legal framework. One of the major upcoming changes effects the perspective on software as a medical device. This paper describes the fundamental relationships between the policy framework and the challenges faced by manufacturers and operators of medical devices, in particular medical software and artificial intelligence (AI) systems, who need to verify compliance. To address this topic, we review and discuss the main implications of medical device regulations on software as a medical device and digital health applications along the MDR structure. Furthermore, we address practical limitations of the implementation, such as the availability of notified bodies and costs of the approval procedure.

Today, medical data such as diagnoses, procedures, imaging reports and laboratory tests, are not only collected in context of primary research and clinical studies. In addition, citizens are tracking their daily steps, food intake, sport exercises, and disease symptoms via mobile phones and wearable devices. In this context, the topic of “data donation” is drawing increased attention in science, politics, ethics and practice. This paper provides insights into the status quo of personal data donation in Germany and from a global perspective. As this topic requires a consideration of several perspectives, potential benefits and related, multifaceted challenges for citizens, patients and researchers are discussed. This includes aspects such as data quality & accessibility, privacy and ethical considerations.

The ongoing digital transformation will potentially change traditional health care practices fundamentally. However, change agents usually face serious challenges arising from the highly institutionalized nature of this industry. Using the gamification of glucose monitoring as part of diabetes care as an example, this paper focuses on strategies to transform health care, allowing not only to cope with, but also to change this context: gamification encourages behavioral changes in patients, establishes new roles between patients and providers, and thereby elevates patient empowerment.

Interoperability in healthcare is a long-standing and addressed phenomenon. In the literature, it is discussed as both the cause of an insufficiently perceived digitalization and in context with an inadequate IT-based integration in healthcare. In particular, technical and organizational aspects are highlighted from the perspective of the different involved actors to achieve sufficient interoperability. Depending on the individual case, various established international industry standards in healthcare (e. g. DICOM, HL7 or FHIR) promise simple adaptation and various application advantages. In addition to the technical view, this article assumes economic challenges as the main causes for the lack of interoperability not discussed in the forefront. The economic challenges were mentioned and sparingly discussed in few cases in the literature. This article aims to fill this gap by offering a first characterization of identified and discussed economic challenges in the literature with respect to the lack of interoperability in healthcare. Based on a systematic literature search, 14 of the original 330 articles can be identified as relevant, allowing a more economic perspective on interoperability. In this context, different economic effects will be described; this includes cost-benefit decisions by individual stakeholders under different kinds of uncertainty or balancing of known individual costs for interoperability against uncertain and skewed distributed benefits within an ecosystem. Furthermore, more sophisticated cost-benefit approaches regarding interoperability challenges can be identified, including cost-benefit ratios that shift over time, or lock-in effects resulting from CRM-motivated measures that turn (non)interoperability decisions into cost considerations for single actors. Also, self-reinforcing effects through path dependencies, including direct and indirect network effects, have an impact on single and linked interoperability decisions.

Digital health interventions (DHIs) have the potential to help the growing number of chronic disease patients better manage their everyday lives. However, guidelines for the systematic development of DHIs are still scarce. The current work has, therefore, the objective to propose a framework for the design and evaluation of DHIs (DEDHI). The DEDHI framework is meant to support both researchers and practitioners alike from early conceptual DHI models to large-scale implementations of DHIs in the healthcare market.

This paper examines the access strategies to Information and Communication Technology (ICT) for electronic Human Resource Management (e-HRM) in the context of public service organizations. Emphasizing the importance of public values, such as long-term employee health and well-being, it addresses an emergent and underexplored topic through a narrative review of 12 empirical studies. The findings suggest that the public service organizations use, firstly, internal development and, secondly, alliances as ICT access strategies for managing public servants. The paper discusses practical implications for public and private organizations.

Providing a suitable rehabilitation at home after an acute episode or a chronic disease is a major issue as it helps people to live independently and enhance their quality of life. However, as the rehabilitation period usually lasts some months, the continuity of care is often interrupted in the transition from the hospital to the home. Relieving the healthcare system and personalizing the care or even bringing care to the patients’ home to a greater extent is, in consequence, the superior need. This is why we propose to make use of information technology to come to participatory design driven by users needs and the personalisation of the care pathways enabled by technology. To allow this, patient rehabilitation at home needs to be supported by automatic decision-making, as physicians cannot constantly supervise the rehabilitation process. Thus, we need computer-assisted patient rehabilitation, which monitors the fitness of the current patient plan to detect sub-optimality, proposes personalised changes for a patient and eventually generalizes over patients and proposes better initial plans. Therefore, we will explain the use case of patient rehabilitation at home, the basic challenges in this field and machine learning applications that could address these challenges by technical means.

Identification of small molecules remains a central question in analytical chemistry, in particular for natural product research, metabolomics, environmental research, and biomarker discovery. Mass spectrometry is the predominant technique for high-throughput analysis of small molecules. But it reveals only information about the mass of molecules and, by using tandem mass spectrometry, about the mass of molecular fragments. Automated interpretation of mass spectra is often limited to searching in spectral libraries, such that we can only dereplicate molecules for which we have already recorded reference mass spectra. In my thesis “Computational methods for small molecule identification” we developed SIRIUS, a tool for the structural elucidation of small molecules with tandem mass spectrometry. The method first computes a hypothetical fragmentation tree using combinatorial optimization. By using a Bayesian statistical model, we can learn parameters and hyperparameters of the underlying scoring directly from data. We demonstrate that the statistical model, which was fitted on a small dataset, generalizes well across many different datasets and mass spectrometry instruments. In a second step the fragmentation tree is used to predict a molecular fingerprint using kernel support vector machines. The predicted fingerprint can be searched in a structure database to identify the molecular structure. We demonstrate that our machine learning model outperforms all other methods for this task, including its predecessor FingerID. SIRIUS is available as commandline tool and as user interface. The molecular fingerprint prediction is implemented as web service and receives over one million requests per month.