The open medical informatics journal最新文献

Background: Computerized provider order entry (CPOE) systems are implemented in various clinical contexts of a hospital. To identify the role of the clinical context in CPOE use, we compared the impact of a CPOE system on the medication process in both non-surgical and surgical specialties.

Methods: We conducted a qualitative study of surgical and non-surgical specialties in a 1237-bed, academic hospital in the Netherlands. We interviewed the clinical end users of a computerized medication order entry system in both specialty types and analyzed the interview transcripts to elicit qualitative differences between the clinical contexts, clinicians' attitudes, and specialty-specific requirements.

Results: Our study showed that the differences in clinical contexts between non-surgical and surgical specialties resulted in a disparity between clinicians' requirements when using CPOE. Non-surgical specialties had a greater medication workload, greater and more diverse information needs to be supported in a timely manner by the system, and thus more intensive interaction with the CPOE system. In turn these factors collectively influenced the perceived impact of the CPOE system on the clinicians' practice. The non-surgical clinicians expressed less positive attitudes compared to the surgical clinicians, who perceived their interaction with the system to be less intensive and less problematic.

Conclusion: Our study shows that clinicians' different attitudes towards the system and the perceived impact of the system were largely grounded in the clinical context of the units. The study suggests that not merely the CPOE system, the technology itself, influences the perceptions of its users and workflow-related outcomes. The interplay between technology and clinical context of the implementation environment also matters. System design and redesigning efforts should take account of different units' specific requirements in their particular clinical contexts.

This discussion paper considers the adoption of socio-technical perspectives and their theoretical and practical influence within the discipline of health informatics. The paper highlights the paucity of discussion of the philosophy, theory and concepts of socio-technical perspectives within health informatics. Instead of a solid theoretical base from which to describe, study and understand human-information technology interactions we continue to have fragmented, unelaborated understandings. This has resulted in a continuing focus on technical system performance and increasingly managerial outputs to the detriment of social and technical systems analysis. It has also limited critical analyses and the adaptation of socio-technical approaches beyond the immediate environment to the broader social systems of contemporary society, an expansion which is increasingly mandated in today's complex health environment.

Information and Communication Technologies (ICT) have merged into the world of healthcare slowly but surely. However, the marriage between the use of technology and its full impact in the health sector has not been fully realised. The focus of this paper is to highlight the impact of ICT on revolutionising access to healthcare information and thus quality of health for populations of the developing world. This paper highlights on the importance of being able to access health information and how traditional media methods have been utilised to allow this within a developing country setting, highlighting the clear digital divide. The paper then addresses the impact of convergent communication technologies and mobile technologies in providing a means of addressing existing healthcare problems within a developing country setting.

There are huge amounts of biomedical data generated by research labs in each cancer institution. The data are stored in various formats and accessed through numerous interfaces. It is very difficult to exchange and integrate the data among different cancer institutions, even among different research labs within the same institution, in order to discover useful biomedical knowledge for the healthcare community. In this paper, we present the design and implementation of a caGrid-enabled caBIG(TM) silver level compatible head and neck cancer tissue database system. The system is implemented using a set of open source software and tools developed by the NCI, such as the caCORE SDK and caGrid. The head and neck cancer tissue database system has four interfaces: Web-based, Java API, XML utility, and Web service. The system has been shown to provide robust and programmatically accessible biomedical information services that syntactically and semantically interoperate with other resources.

Support Vector Machines (SVMs) represent a powerful learning paradigm able to provide accurate and reliable decision functions in several application fields. In particular, they are really attractive for application in medical domain, where often a lack of knowledge exists. Kernel trick, on which SVMs are based, allows to map non-linearly separable data into potentially linearly separable one, according to the kernel function and its internal parameters value. During recent years non-parametric approaches have also been proposed for learning the most appropriate kernel, such as linear combination of basic kernels. Thus, SVMs classifiers may have several parameters to be tuned and their optimal values are usually difficult to be identified a-priori. Furthermore, combining different classifiers may reduce risk to perform errors on new unseen data. For such reasons, we present an hyper-solution framework for SVM classification, based on meta-heuristics, that searches for the most reliable hyper-classifier (SVM with a basic kernel, SVM with a combination of kernel, and ensemble of SVMs), and for its optimal configuration. We have applied the proposed framework on a critical and quite complex issue for the management of Chronic Heart Failure patient: the early detection of decompensation conditions. In fact, predicting new destabilizations in advance may reduce the burden of heart failure on the healthcare systems while improving quality of life of affected patients. Promising reliability has been obtained on 10-fold cross validation, proving our approach to be efficient and effective for an high-level analysis of clinical data.

By performing repeated sit-stand-sit movements to create stress on knee joints, short transient bursts of high frequency acoustic emission (AE) released by the knee joints were acquired from two age matched groups consisting of healthy and osteoarthritic (OA) knees, and significant differences between these two groups were discovered from the signal analysis performed. The analysis is based on a four-phase model of sit-stand-sit movements and a two-feature descriptor of AE bursts. The four phases are derived from joint angle measurement during movement, and they consist of the ascending-acceleration and ascending-deceleration phases in the sit-to-stand movement, followed by the descending-acceleration and descending-deceleration phases in the stand-to-sit movement. The two features are extracted from AE measurement during movement, and they consist of the peak magnitude value and average signal level of each AE burst. The proposed analysis method is shown to provide a high sensitivity for differentiation of the two age matched healthy and OA groups, with the most significant difference found to come from the peak magnitude value in the ascending-deceleration phase, clear quantity and strength differences in the image based visual display of their AE feature profiles due to substantially more AE bursts from OA knee joints with higher peak magnitude values and higher average signal levels, and two well separated clusters in the space formed by the principal components. These results provide ample support for further development of AE as a novel tool to facilitate dynamic integrity assessment of knee joints in clinic and home settings.

The aim of this work is to introduce and design image processing methods for the quantitative analysis of epicardial fat by using cardiac CT imaging.Indeed, epicardial fat has recently been shown to correlate with cardiovascular disease, cardiovascular risk factors and metabolic syndrome. However, many concerns still remain about the methods for measuring epicardial fat, its regional distribution on the myocardium and the accuracy and reproducibility of the measurements.In this paper, a method is proposed for the analysis of single-frame 3D images obtained by the standard acquisition protocol used for coronary calcium scoring. In the design of the method, much attention has been payed to the minimization of user intervention and to reproducibility issues.In particular, the proposed method features a two step segmentation algorithm suitable for the analysis of epicardial fat. In the first step of the algorithm, an analysis of epicardial fat intensity distribution is carried out in order to define suitable thresholds for a first rough segmentation. In the second step, a variational formulation of level set methods - including a specially-designed region homogeneity energy based on Gaussian mixture models- is used to recover spatial coherence and smoothness of fat depots.Experimental results show that the introduced method may be efficiently used for the quantification of epicardial fat.