Search

Highlights • Implementation process of Electronic Health Records (EHRs) is critical for success. • Vast literature available on EHR implementations in different settings and contexts. • Organizational, Human and Technological factors influence success across settings. • Dynamic interaction of the identified factors trigger success. • Consideration of the specific healthcare context and end-users is important., Aim To summarize the findings from literature reviews with a view to identifying and exploring the key factors which impact on the success of an EHR implementation across different healthcare contexts. Introduction Despite the widely recognised benefits of electronic health records (EHRs), their full potential has not always been achieved, often as a consequence of the implementation process. As more countries launch national EHR programmes, it is critical that the most up-to-date and relevant international learnings are shared with key stakeholders. Methods A rapid umbrella review was undertaken in collaboration with a multidisciplinary panel of knowledge-users and experts from Ireland. A comprehensive literature review was completed (2019) across several search engines (PubMed, CINAHL, Scopus, Embase, Web of Science, IEEE Xplore, ACM Digital Library, ProQuest, Cochrane) and Gray literature. Identified studies (n = 5,040) were subject to eligibility criterion and identified barriers and facilitators were analysed, reviewed, discussed and interpreted by the expert panel. Results Twenty-seven literature reviews were identified which captured the key organizational, human and technological factors for a successful EHR implementation according to various stakeholders across different settings. Although the size, type and culture of the healthcare setting impacted on the organizational factors, each was deemed important for EHR success; Governance, leadership and culture, End-user involvement, Training, Support, Resourcing, and Workflows. As well as organizational differences, individual end-users also have varying Skills and characteristics, Perceived benefits and incentives, and Perceived changes to the health ecosystem which were also critical to success. Finally, the success of the EHR technology depended on Usability, Interoperability, Adaptability, Infrastructure, Regulation, standards and policies, and Testing. Conclusion Fifteen inter-linked organizational, human and technological factors emerged as important for successful EHR implementations across primary, secondary and long-term care settings. In determining how to employ these factors, the local context, individual end-users and advancing technology must also be considered.

The large collections of news images available from stock photo agencies provide interesting insights into how different celebrities are related to each other, in terms of the events they attend together and also in terms of how often they are photographed together. In this paper, we leverage such collections to predict which celebrities will attend future events. The main motivation for this is in the event-based indexing of online collections of multimedia content, an area that has attracted much attention in recent years. Based on the metadata associated with a corpus of stock photos, we propose a language model for predicting celebrities attending future events. A temporal hierarchical version of the language model exploits fresh data while still making use of all historical data. We extract a social network from co-appearance of public figures in the events depicted in the photographs, and combine this latent social information with the language model to further improve prediction accuracy. The experimental results show that combining textual, network and temporal information gives the best prediction performance. Our analysis also shows that the prediction models, when trained by the most recent data, are most accurate for political and sports events.

To provide good results, image search engines need to rank not just the most relevant images, but also the highest quality images. To surface beautiful pictures, existing computational aesthetic models are trained with datasets from photo contest websites, dominated by professional photos. Such models fail completely in real web scenarios, where images are extremely diverse in terms of quality and type (e.g. drawings, clip-art, etc). This work aims at bridging and understanding this "aesthetic gap". We collect a dataset of around 100K web images with `quality' and `type' (photo vs non-photo) annotations. We design a set of visual features to describe image pictorial characteristics, and deeply analyse the peculiar beauty of web images as opposed to appealing professional images. Finally, we build a set of computational aesthetic frameworks based on deep learning and hand-crafted features that take into account the diverse quality of web images, and show that they significantly outperform traditional computational aesthetics methods on our dataset.

Studies suggest that self-harm users found it easier to discuss self-harm-related thoughts and behaviors using social media than in the physical world. Given the enormous and increasing volume of social media data, on-line self-harm content is likely to be buried rapidly by other normal content. To enable voices of self-harm users to be heard, it is important to distinguish self-harm content from other types of content. In this paper, we aim to understand self-harm content and provide automatic approaches to its detection. We first perform a comprehensive analysis on self-harm social media using different input cues. Our analysis, the first of its kind in large scale, reveals a number of important findings. Then we propose frameworks that incorporate the findings to discover self-harm content under both supervised and unsupervised settings. Our experimental results on a large social media dataset from Flickr demonstrate the effectiveness of the proposed frameworks and the importance of our findings in discovering self-harm content.

MRI is an important diagnostic tool for acute medical admissions. Its relevance to in-hospital mortality and length of stay (LOS) has been examined at St James's Hospital in Dublin, Ireland.All patients admitted for medical emergencies from 2010 through 2012 were studied (18,534 episodes); any relationship between an MRI request, underlying diagnosis on any in-hospital death, and LOS was examined. Logistic regression with generalized estimating equations, adjusted for correlated observations (readmissions), odds ratio estimates, and zero-truncated Poisson regression for LOS were used.MRI procedures were requested in 8.6% of episodes. The in-hospital mortality rate was significantly higher when MRI was performed (7.8% vs 4.6%, P.001). The unadjusted odds ratio for in-hospital death during that episode was 1.74 (95% confidence interval, 1.26-2.37; P.001) compared with episodes without MRI. The hospital stay for those MRI episodes was longer (median, 9.1 days; interquartile range, 4.0-26.8 days) than for non-MRI episodes (median, 5.8 days; interquartile range, 2.2-12.2; P.001). Each unit increase in MRI waiting time (cutoffs set at 0, 1, 3, 7, and 14 days) gave an estimated increase of 1.12 days in hospital LOS, adjusted for illness severity and comorbidities.MR imaging identified in a subgroup of emergency patients at higher risk of an in-hospital death. These patients have longer LOS attributable in part to procedure wait times, not merely to illness severity or comorbidities.

The Multimedia Grand Challenge was held at ACM Multimedia 2013 in Barcelona, Spain. At this fifth annual event, researchers from academia attacked multimedia challenges inspired by industry. This report provides an overview of the 2013 Multimedia Grand Challenge, describing the six challenges and the selection procedure for finalists and eventual winners as well as summarizing the winning solutions, which should definitely be regarded as showcases for the multimedia research community.

Natural User Interface (NUI) systems can enable the scrubbed clinician to assume direct control of medical image interaction while maintaining sterility in the Operating Room. Surgeons and radiologists trialed a touch-free image control system based on the Leap Motion and Microsoft Kinect v2 controllers. Feedback was reported on the perceived utility and usability of both devices. The speed and accuracy of the two controllers was measured. Results showed marginal to average acceptability of both controllers. Surgeons and Interventional Radiologists found Microsoft Kinect to have better utility and to be potentially useful for the majority (54%) of them. The accuracy of the Leap Motion sensor was superior and comparable with that of a computer mouse. A link was established between the system usability and the perception of utility with better usability translating into better utility. Advantages and limitations of each device are highlighted. Design improvements and deployment considerations are discussed.