Search

Background: Diabetes mellitus (DM) is a metabolic disorder that causes abnormal blood glucose (BG) regulation that might result in short and long-term health complications and even death if not properly managed. Currently, there is no cure for diabetes. However, self-management of the disease, especially keeping BG in the recommended range, is central to the treatment. This includes actively tracking BG levels and managing physical activity, diet, and insulin intake. The recent advancements in diabetes technologies and self-management applications have made it easier for patients to have more access to relevant data. In this regard, the development of an artificial pancreas (a closed-loop system), personalized decision systems, and BG event alarms are becoming more apparent than ever. Techniques such as predicting BG (modeling of a personalized profile), and modeling BG dynamics are central to the development of these diabetes management technologies. The increased availability of sufficient patient historical data has paved the way for the introduction of machine learning and its application for intelligent and improved systems for diabetes management. The capability of machine learning to solve complex tasks with dynamic environment and knowledge has contributed to its success in diabetes research., Motivation: Recently, machine learning and data mining have become popular, with their expanding application in diabetes research and within BG prediction services in particular. Despite the increasing and expanding popularity of machine learning applications in BG prediction services, updated reviews that map and materialize the current trends in modeling options and strategies are lacking within the context of BG prediction (modeling of personalized profile) in type 1 diabetes., Objective: The objective of this review is to develop a compact guide regarding modeling options and strategies of machine learning and a hybrid system focusing on the prediction of BG dynamics in type 1 diabetes. The review covers machine learning approaches pertinent to the controller of an artificial pancreas (closed-loop systems), modeling of personalized profiles, personalized decision support systems, and BG alarm event applications. Generally, the review will identify, assess, analyze, and discuss the current trends of machine learning applications within these contexts., Method: A rigorous literature review was conducted between August 2017 and February 2018 through various online databases, including Google Scholar, PubMed, ScienceDirect, and others. Additionally, peer-reviewed journals and articles were considered. Relevant studies were first identified by reviewing the title, keywords, and abstracts as preliminary filters with our selection criteria, and then we reviewed the full texts of the articles that were found relevant. Information from the selected literature was extracted based on predefined categories, which were based on previous research and further elaborated through brainstorming among the authors., Results: The initial search was done by analyzing the title, abstract, and keywords. A total of 624 papers were retrieved from DBLP Computer Science (25), Diabetes Technology and Therapeutics (31), Google Scholar (193), IEEE (267), Journal of Diabetes Science and Technology (31), PubMed/Medline (27), and ScienceDirect (50). After removing duplicates from the list, 417 records remained. Then, we independently assessed and screened the articles based on the inclusion and exclusion criteria, which eliminated another 204 papers, leaving 213 relevant papers. After a full-text assessment, 55 articles were left, which were critically analyzed. The inter-rater agreement was measured using a Cohen Kappa test, and disagreements were resolved through discussion., Conclusion: Due to the complexity of BG dynamics, it remains difficult to achieve a universal model that produces an accurate prediction in every circumstance (i.e., hypo/eu/hyperglycemia events). Recently, machine learning techniques have received wider attention and increased popularity in diabetes research in general and BG prediction in particular, coupled with the ever-growing availability of a self-collected health data. The state-of-the-art demonstrates that various machine learning techniques have been tested to predict BG, such as recurrent neural networks, feed-forward neural networks, support vector machines, self-organizing maps, the Gaussian process, genetic algorithm and programs, deep neural networks, and others, using various group of input parameters and training algorithms. The main limitation of the current approaches is the lack of a well-defined approach to estimate carbohydrate intake, which is mainly done manually by individual users and is prone to an error that can severely affect the predictive performance. Moreover, a universal approach has not been established to estimate and quantify the approximate effect of physical activities, stress, and infections on the BG level. No researchers have assessed model predictive performance during stress and infection incidences in a free-living condition, which should be considered in future studies. Furthermore, a little has been done regarding model portability that can capture inter- and intra-variability among patients. It seems that the effect of time lags between the CGM readings and the actual BG levels is not well covered. However, in general, we foresee that these developments might foster the advancement of next-generation BG prediction algorithms, which will make a great contribution in the effort to develop the long-awaited, so-called artificial pancreas (a closed-loop system)., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Background: Telemedicine services have been successfully used in areas where there are adequate infrastructures such as reliable power and communication lines. However, despite the increasing number of merchants and seafarers, maritime and Arctic telemedicine have had limited success. This might be linked with various factors such as lack of good infrastructure, lack of trained onboard personnel, lack of Arctic-enhanced telemedicine equipment, extreme weather conditions, remoteness, and other geographical challenges., Objective: The purpose of this review was to assess and analyze the current status of telemedicine services in the context of maritime conditions, extreme weather (ie, Arctic weather), and remote accidents and emergencies. Moreover, the paper aimed to identify successfully implemented telemedicine services in the Arctic region and in maritime settings and remote emergency situations and present state of the art systems for these areas. Finally, we identified the status quo of telemedicine services in the context of search and rescue (SAR) scenarios in these extreme conditions., Methods: A rigorous literature search was conducted between September 7 and October 28, 2015, through various online databases. Peer reviewed journals and articles were considered. Relevant articles were first identified by reviewing the title, keywords, and abstract for a preliminary filter with our selection criteria, and then we reviewed full-text articles that seemed relevant. Information from the selected literature was extracted based on some predefined categories, which were defined based on previous research and further elaborated upon via iterative brainstorming., Results: The initial hits were vetted using the title, abstract, and keywords, and we retrieved a total of 471 papers. After removing duplicates from the list, 422 records remained. Then, we did an independent assessment of the articles and screening based on the inclusion and exclusion criteria, which eliminated another 219 papers, leaving 203 relevant papers. After a full-text assessment, 36 articles were left, which were critically analyzed. The inter-rater agreement was measured using Cohen Kappa test, and disagreements were resolved through discussion., Conclusions: Despite the increasing number of fishermen and other seafarers, Arctic and maritime working conditions are mainly characterized by an absence of access to health care facilities. The condition is further aggravated for fishermen and seafarers who are working in the Arctic regions. In spite of the existing barriers and challenges, some telemedicine services have recently been successfully delivered in these areas. These services include teleconsultation (9/37, 24%), teleradiology (8/37, 22%), teledermatology and tele-education (3/37, 8%), telemonitoring and telecardiology (telesonography) (1/37, 3%), and others (10/37, 27%). However, the use of telemedicine in relation to search and rescue (SAR) services is not yet fully exploited. Therefore, we foresee that these implemented and evaluated telemedicine services will serve as underlying models for the successful implementation of future search and rescue (SAR) services., (©Ashenafi Zebene Woldaregay, Ståle Walderhaug, Gunnar Hartvigsen. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 28.06.2017.)

Intro: The proper use of ICT services can support seniors in living independently longer. While such services are starting to emerge, current proprietary solutions are often expensive, covering only isolated parts of seniors' needs, and lack support for sharing information between services and between users. For developers, the challenge is that it is complex and time consuming to develop high quality, interoperable services, and new techniques are needed to simplify the development and reduce the development costs. This paper provides the complete view of the experiences gained in the MPOWER project with respect to using model-driven development (MDD) techniques for Service Oriented Architecture (SOA) system development in the Ambient Assisted Living (AAL) domain., Method: To address this challenge, the approach of the European research project MPOWER (2006-2009) was to investigate and record the user needs, define a set of reusable software services based on these needs, and then implement pilot systems using these services. Further, a model-driven toolchain covering key development phases was developed to support software developers through this process. Evaluations were conducted both on the technical artefacts (methodology and tools), and on end user experience from using the pilot systems in trial sites., Results: The outcome of the work on the user needs is a knowledge base recorded as a Unified Modeling Language (UML) model. This comprehensive model describes actors, use cases, and features derived from these. The model further includes the design of a set of software services, including full trace information back to the features and use cases motivating their design. Based on the model, the services were implemented for use in Service Oriented Architecture (SOA) systems, and are publicly available as open source software. The services were successfully used in the realization of two pilot applications. There is therefore a direct and traceable link from the user needs of the elderly, through the service design knowledge base, to the service and pilot implementations. The evaluation of the SOA approach on the developers in the project revealed that SOA is useful with respect to job performance and quality. Furthermore, they think SOA is easy to use and support development of AAL applications. An important finding is that the developers clearly report that they intend to use SOA in the future, but not for all type of projects. With respect to using model-driven development in web services design and implementation, the developers reported that it was useful. However, it is important that the code generated from the models is correct if the full potential of MDD should be achieved. The pilots and their evaluation in the trial sites showed that the services of the platform are sufficient to create suitable systems for end users in the domain., Conclusions: A SOA platform with a set of reusable domain services is a suitable foundation for more rapid development and tailoring of assisted living systems covering reoccurring needs among elderly users. It is feasible to realize a tool-chain for model-driven development of SOA applications in the AAL domain, and such a tool-chain can be accepted and found useful by software developers., (Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.)

The Ambient Assisted Living domain is a fast growing area with many new technological artefacts and services developed. Most of the systems developed address end-users' needs. Yet, they have not achieved a large market penetration. The work presented here argues that this is primarily due to not sufficiently addressing the quality requirements posed by the health care organizations. Satisfying quality requirements requires a standardized and easily accessible framework for measuring quality. We present the initial steps towards such a framework by building on relevant ISO standards.

Ambient Assisted Living systems for the ageing and cognitively disabled do not exist in isolation. What characterizes such systems is the cooperation of several different stakeholders in the care process and the service platforms need to address this. This paper reports on our work in the EU IST MPOWER project where we have designed and implemented interoperability services based on patterns, service-oriented architectures, web services and XSDL transformations. The services we present are freely available as open source under the MIT license.

The objective of the study presented here was to perform an empirical investigation on factors affecting healthcare workers acceptance and utilisation of e-learning in post-school healthcare education. E-learning benefits are realised when key features of e-learning are not only applied, but deemed useful, compatible with the learning process and supportive in order to reach the overall goals of the learning process. We conducted a survey of 14 state-enrolled nurses and skilled-workers within the field of healthcare in Norway. The results show that perceived compatibility and subjective norm explain system usage of the e-learning tool amongst the students. We found that the fact that the students considered the e-learning to be compatible with the course in question had a positive effect on e-learning tool usage. We also found support for factors such as facilitating conditions and ease of use leads to the e-learning tool being considered useful.

Industrial countries are faced with a growing elderly population. Homecare systems with assistive smart house technology enable elderly to live independently at home. Development of such smart home care systems is complex and expensive and there is no common reference model that can facilitate service reuse. This paper proposes reusable actor and service models based on a model-driven development process where end user organizations and domain healthcare experts from four European countries have been involved. The models, specified using UML can be reused actively as assets in the system design and development process and can reduce development costs, and improve interoperability and sustainability of systems. The models are being evaluated in the European IST project MPOWER.

An aging population and an increase in chronically ill patients demand teamwork treatment models. To support these with information systems, interoperability is a prerequisite. Model-driven software development (MDSD) with special healthcare extensions can enable reuse of components and improve conformance to international standards. In this paper, a MDSD HealthCare Framework is proposed and demonstrated for homecare services. Using the framework, information systems will improve their conformance to international standards and the interoperability with other systems.

Chronic diseases are increasing rapidly and this phenomenon is becoming a major burden to the health delivery system around the world. A new health care paradigm with focus on chronic treatment and care will actualize the need for interoperable standards based services due to the complexity of care where different health levels and professions are involved. Given the complexity of the domain, we argue the need for a systematic and formal approach to the development of interoperable information systems if there shall be any real support of the cooperating actors. We describe our work on technical interoperability done in the Linkcare project addressing new models of care and technology to support them in the domain of the chronically ill using concrete results from an architecture built using the MAFIIA architecture framework and the UML 2.0 profile for software services, and argue that building formal architectural descriptions on the basis of shared interface descriptions and profiles are an important part of achieving continuity of care based on sustainable health systems.