Search

Issues of non-use of available health information technology (HIT) have been referred to as the ‘last mile problem’ impeding harnessing the full potential of HIT. We reflect upon which competencies are needed to address the last mile problem by ensuring a context-sensitive implementation. We argue that there is a need for context-sensitive digital integrators, who can navigate the realm where technological systems meet practice. This entails a situated, socio-technical, context-sensitive approach and competencies which are not easily addressed through formal training but require lifelong situated learning, as the field evolves continuously. Our ambition is to highlight the complexities of implementation and integration into local practice. This paper emphasizes the role of digital integrators in the hope of fostering further discussions on how to acknowledge and nourish these competencies in order to address and go beyond the last mile problem.

The WHO Health Emergencies Programme combined online tools with adult learning techniques to develop an innovative online leadership course. A combination of self-paced learning and online classes were used to deliver skills-based leadership training tailored to public health staff working in emergency response roles. Although using an online approach was considered a temporary solution to counter travel restrictions during the pandemic, the advantages have challenged preconceptions that effective learning, networking and peer exchange for leadership can only be achieved through face-to-face learning.

Issues of non-use of available health information technology (HIT) have been referred to as the last mile problem' impeding harnessing the full potential of HIT. We reflect upon which competencies are needed to address the last mile problem by ensuring a context-sensitive implementation. We argue that there is a need for context-sensitive digital integrators, who can navigate the realm where technological systems meet practice. This entails a situated, socio-technical, context-sensitive approach and competencies which are not easily addressed through formal training but require lifelong situated learning, as the field evolves continuously. Our ambition is to highlight the complexities of implementation and integration into local practice. This paper emphasizes the role of digital integrators in the hope of fostering further discussions on how to acknowledge and nourish these competencies in order to address and go beyond the last mile problem.

Photo response non-uniformity (PRNU) noise is a sensor pattern noise characterizing the imaging device. It has been broadly used in the literature for image authentication and source camera identification. The abundant information that the PRNU carries in terms of the frequency content makes it unique, and therefore suitable for identifying the source camera and detecting forgeries in digital images. However, PRNU estimation from smartphone videos is a challenging process due to the presence of frame-dependent information (very dark/very textured), as well as other non-unique noise components and distortions due to lossy compression. In this paper, we propose an approach that considers only the non-textured frames in estimating the PRNU because its estimation in highly textured images has been proven to be inaccurate in image forensics. Furthermore, lossy compression distortions tend to affect mainly the textured and high activity regions and consequently weakens the presence of the PRNU in such areas. The proposed technique uses a number of texture measures obtained from the Grey Level Cooccurrence Matrix (GLCM) prior to an unsupervised learning process that splits the feature space through training video frames into two different sub-spaces, i.e., the textured space and the non-textured space. Non-textured video frames are filtered out and used for estimating the PRNU. Experimental results on a public video dataset captured by various smartphone devices have shown a significant gain obtained with the proposed approach over the conventional state-of-the-art approach.

Big data analytics is a rapidly expanding issue in computer engineering, and health informatics is one of the most challenging topics. Big data investigation in healthcare could certainly make improvements to medical study as well as the quality of treatment offered to patients. Machine Learning (ML) algorithms due to powerful and efficient handling of data analytics could gain knowledge from data to discover patterns and trends in the database to make predictive models. Our study aims to review the most recent scholarly publications about big data analytics and its applications which include predictive models in healthcare. A systematic search of articles in the three most significant scientific databases: ScienceDirect, PubMed, and IEEE Xplore was carried out following the PRISMA methodology. This study shows how machine learning algorithms are evolving into a promising field for supporting intelligent decisions by analyzing large data sets and thereby improving treatments while reducing costs. However, there remain challenges to overcome and there is still room for improvement to develop methods and applications. Finally, we outline the unsolved issue and the future perspectives for health sciences in the big data era.

Failure Mode & Effect Analysis (FMEA) is a method that has been used to improve reliability of products, processes, designs, and software for different applications, including electronics manufacturing. In this paper we propose a modification of this method to extend its application for data veracity and validity improvement. The proposed DVV-FMEA method is based on engineering features and in addition, provides transparency and understandability of the data and its pre-processing, making it reproducible and trustful.