Search

Objective: Hospitals and healthcare providers should assess and compare the quality of care given to patients and based on this improve the care. In the Netherlands, hospitals provide data to national quality registries, which in return provide annual quality indicators. However, this process is time-consuming, resource intensive and risks patient privacy and confidentiality. In this paper, we presented a multicentric 'Proof of Principle' study for federated calculation of quality indicators in patients with colorectal cancer. The findings suggest that the proposed approach is highly time-efficient and consume significantly lesser resources. Materials and methods: Two quality indicators are calculated in an efficient and privacy presevering federated manner, by i) applying the Findable Accessible Interoperable and Reusable (FAIR) data principles and ii) using the Personal Health Train (PHT) infrastructure. Instead of sharing data to a centralized registry, PHT enables analysis by sending algorithms and sharing only insights from the data. Results: ETL process extracted data from the Electronic Health Record systems of the hospitals, converted them to FAIR data and hosted in RDF endpoints within each hospital. Finally, quality indicators from each center are calculated using PHT and the mean result along with the individual results plotted. Discussion and conclusion: PHT and FAIR data principles can efficiently calculate quality indicators in a privacy-preserving federated approach and the work can be scaled up both nationally and internationally. Despite this, application of the methodology was largely hampered by ELSI issues. However, the lessons learned from this study can provide other hospitals and researchers to adapt to the process easily and take effective measures in building quality of care infrastructures. [ABSTRACT FROM AUTHOR]

Now and in the coming years a new European Rail Traffic Management System (ERTMS) is being deployed on a larger scale. In the system level chosen in the Netherlands (Level 2) lineside signals will disappear and the train driver will receive all information needed for safe and efficient train operation through an interface inside the train cab. Furthermore, procedures, driving skills and communication will alter. Many train drivers will thus need to be trained in driving with ERTMS. Train operating companies (TOC) have to decide on efficient and effective strategies to organise this extensive training volume and to reassure that drivers become and remain proficient after training when roll-out of ERTMS may not have been fully completed. In this paper the central questions to be answered are: How many hours/duties does a driver have to do during a certain period of time on an ERTMS track section to become proficient with ERTMS (learning period), and to stay proficient (retaining period)? The approach taken is unique for rail industry (to the authors' knowledge) and is based on big data analyses. In this study, we were able to study the collective performance of train drivers, by big data analysis while at the same time maintaining privacy through pseudonymisation of the train driver database and their individual performances, characteristics and other potential privacy sensitive data. Databases containing detailed information on all planned and accomplished train service times/positions of the last three years (2015-2017) of a large TOC were combined with personal data from HR databases (age, experience, ERTMS training history, job assessment results, etcetera). From the data, delays caused by rolling stock and train operating related issues were identified. The amount and duration of these delays were correlated with the personal data to test research hypotheses. Again, at the same time we maintained privacy of the individuals' personal data. Although the research has some limitations due to the small amount of existing ERTMS lines, and associated rolling stock, the results show some clear correlations. Thus, quantifiable directions to the minimum amount of ERTMS driving per 3 months during the first year and in the years after are presented. The results are now being translated into models for training and rostering related to the phase of ERTMS roll-out. [ABSTRACT FROM AUTHOR]

Integrated care means doing justice to life in all its facets and supporting it where that is necessary for the client. This advocates the coordination of different forms of care and support and the integrated use of data that is available on these different facets of life. It can be challenging to provide the necessary care, in particular when different people are involved and decisions need to be based on care plans, reports, and other types of information originating from different individuals. However, there is a common understanding that technology is an important facilitator in tackling this challenge. Technology already supports care processes and complements the role of people in many ways. For instance, it takes over tasks and helps to save time, obtain new insights and simplify complexity. Most of the time, using technology comes down to creating, collecting, analyzing and applying big data, or combinations of these. In fact, all our actions - in healthcare, as in society in general - are directed by subjective and objective data, which is often hidden in the minds of people, but also increasingly collected digitally. Until now, the use of different technologies and data is too often not integrated in the organization and put away in separate silos as the use of a technical instrument in care processes is often initiated for specific reasons that do not affect the entire organization or client population. Meanwhile though, more and more opportunities are coming up to connect the different data flows that exist in healthcare, and to utilize the data both organization-transcending as for the individual client. Developments in intelligent software systems AI, amongst others, offer the possibility to rapidly collect, integrate, exchange, edit and analyze large amounts of data. This allows people to respond more proactively to incidents, gain new insights about health, provide customized care and support and improve the cooperation between individuals and disciplines. However, many longterm care organizations in The Netherlands experience these opportunities as something elusive and find it hard to take advantage of them. Though many organizations in Dutch longterm care are interested in the exploration of data-driven healthcare, a common challenge is that enthusiastic innovators within care organizations often have limited time to invest in data-driven care, and do so alone or with the support of only few colleagues. Therefore, innovators from different organizations regularly come together within networks where they share experiences and experiment. At the same time, despite the promises of data-driven healthcare, there are many dilemmas around privacy, security, access to data, risk of stigmatization and medicalization and the increasing dependence on technology, for instance. When experimenting, the dilemmas should be taken seriously and in co-creation between multiple organizations, codes of conduct on these issues can be developed step-by-step. This paper will share some experiences and lessons learned, both by individual organizations and in workshops in which they collaborated. The approach is that by creating room for experimenting, starting small and sharing experiences with other parties, 'big data' can be made small. [ABSTRACT FROM AUTHOR]