Objectives This systematic review aimed to assess the performance and clinical feasibility of machine learning (ML) algorithms in prediction of in-hospital mortality for medical patients using vital signs at emergency departments (EDs). Design A systematic review was performed. Setting The databases including Medline (PubMed), Scopus and Embase (Ovid) were searched between 2010 and 2021, to extract published articles in English, describing ML-based models utilising vital sign variables to predict in-hospital mortality for patients admitted at EDs. Critical appraisal and data extraction for systematic reviews of prediction modelling studies checklist was used for study planning and data extraction. The risk of bias for included papers was assessed using the prediction risk of bias assessment tool. Participants Admitted patients to the ED. Main outcome measure In-hospital mortality. Results Fifteen articles were included in the final review. We found that eight models including logistic regression, decision tree, K-nearest neighbours, support vector machine, gradient boosting, random forest, artificial neural networks and deep neural networks have been applied in this domain. Most studies failed to report essential main analysis steps such as data preprocessing and handling missing values. Fourteen included studies had a high risk of bias in the statistical analysis part, which could lead to poor performance in practice. Although the main aim of all studies was developing a predictive model for mortality, nine articles did not provide a time horizon for the prediction. Conclusion This review provided an updated overview of the state-of-the-art and revealed research gaps; based on these, we provide eight recommendations for future studies to make the use of ML more feasible in practice. By following these recommendations, we expect to see more robust ML models applied in the future to help clinicians identify patient deterioration earlier.

Hip fractures are amongst the leading causes of admission to an orthopaedic ward. Systematized pathways with reduced admission time have become increasingly common as an essential tool for quality development and to improve efficiency in the hospital setting. The aim of this study was to clarify if the patients feel empowered and able to perform self-care after short time stay in hospital (STSH) due to a hip fracture. The study used descriptive phenomenology to describe experiences of the pathway. Field studies were conducted in hospitals and in the patients' homes. Interviews were performed with 10 patients recruited from two wards at a Danish University hospital, 4 family members and 15 health professionals from three hospitals. The open attitude of reflective lifeworld research guided the analysis. The findings revealed that patients felt unprepared and insecure about their future, but also had a strong desire to be in charge of their own lives. Of all the patients interviewed, none had any recollection of the information given to them by health professionals during their hospital admission. This study demonstrates that empowerment of patients with hip fractures is not adequately achieved in the pathway with STSH.

Early hypertext systems were monolithic and closed, but newer systems tend to be open, distributed, and support collaboration. While this development has resulted in increased openness and flexibility, integration or adaptation of various different tools (such as content editors, viewers, services, or even other link servers) has remained a tedious task. Many developers were implementing essentially similar components, simply for the benefit of having their own platform on which to experiment with hypertexts. The open hypermedia community is addressing this issue of interoperability between open hypermedia systems. The goal of this effort is to provide an open framework that can be used by application developers outside the community to construct more powerful hypermedia-aware applications. The design and evolution of this framework is presented along with the requirements that drove its development. The framework has matured to the point where it has supported the creation of a number of research prototypes. These prototypes are described and evaluated with respect to their use of the framework.

Computing support for large engineering enterprises providesan example of the need for hypermedia-based collaborativecomputing systems composed of a large numberof distributed heterogeneous tools. These computingenvironments place complex requirements on the underlyinghypermedia platform. To support integrationof independently written tools for these environments,hypermedia platforms must address several importantissues such as scalability, openness, distribution, heterogeneity,...