Medical informatics and the Internet in medicine最新文献

This paper proposes a patient-identity security mechanism, including an identity cipher/decipher and a user-authentication protocol, to ensure the confidentiality and authentication of patients' electronic medical records (EMRs) during transit and at rest. To support the confidentiality of an EMR, the identity cipher/decipher uses a data-hiding function and three logical-based functions to encrypt/decrypt a patient's identifying data and medical details in an EMR. The ciphertext of the patient's identifying data is patient-EMR related, whereas that of medical details is healthcare agent-EMR related. To support the authentication of an EMR, the user-authentication protocol based on a public key infrastructure uses certificates and dynamic cookies for verification/identification. The identity cipher has been simulated using C programming language running on a 1500 MHz Pentium PC with 512 MB of RAM. The experimental results show that healthcare agents can install large amounts of patients' encrypted EMRs in healthcare databases efficiently. In addition, separately storing the keys in a user's token and an EMR database for decryption increases the safety of patients' EMRs. For each user-authentication trail, the use of certificates and dynamic cookies for verification/identification ensures that only authorized users can obtain access to the EMR, and anyone involved cannot make false claims on the transmission made.

Current approaches for mining association rules usually assume that the mining is performed in a static database, where the problem of missing attribute values does not practically exist. However, these assumptions are not preserved in some medical databases, like in a home care system. In this paper, a novel uncertainty rule algorithm is illustrated, namely URG-2 (Uncertainty Rule Generator), which addresses the problem of mining dynamic databases containing missing values. This algorithm requires only one pass from the initial dataset in order to generate the item set, while new metrics corresponding to the notion of Support and Confidence are used. URG-2 was evaluated over two medical databases, introducing randomly multiple missing values for each record's attribute (rate: 5-20% by 5% increments) in the initial dataset. Compared with the classical approach (records with missing values are ignored), the proposed algorithm was more robust in mining rules from datasets containing missing values. In all cases, the difference in preserving the initial rules ranged between 30% and 60% in favour of URG-2. Moreover, due to its incremental nature, URG-2 saved over 90% of the time required for thorough re-mining. Thus, the proposed algorithm can offer a preferable solution for mining in dynamic relational databases.

An image-analysis system based on the concept of Support Vector Machines (SVM) was developed to assist in grade diagnosis of brain tumour astrocytomas in clinical routine. One hundred and forty biopsies of astrocytomas were characterized according to the WHO system as grade II, III and IV. Images from biopsies were digitized, and cell nuclei regions were automatically detected by encoding texture variations in a set of wavelet, autocorrelation and parzen estimated descriptors and using an unsupervised SVM clustering methodology. Based on morphological and textural nuclear features, a decision-tree classification scheme distinguished between different grades of tumours employing an SVM classifier. The system was validated for clinical material collected from two different hospitals. On average, the SVM clustering algorithm correctly identified and accurately delineated 95% of all nuclei. Low-grade tumours were distinguished from high-grade tumours with an accuracy of 90.2% and grade III from grade IV with an accuracy of 88.3% The system was tested in a new clinical data set, and the classification rates were 87.5 and 83.8%, respectively. Segmentation and classification results are very encouraging, considering that the method was developed based on every-day clinical standards. The proposed methodology might be used in parallel with conventional grading to support the regular diagnostic procedure and reduce subjectivity in astrocytomas grading.

This paper presents a longitudinal study (over 4 months) of an A&E department where the existing whiteboards were replaced with PC-based computer systems. The study was conducted in two parts - an observation of the physical whiteboard usage and in-depth interviews with all users of both the traditional whiteboard usage and the replacement technology. The research was conducted with the systems manager and all whiteboard users (i.e. nursing management, nurses, doctors, porters, and agency staff) across a spread of time frames. Although the technology supported simple information requirements, complex co-ordination, collaboration, and awareness issues were left unsupported. The important role of a pen-holder (information co-ordinator) was poorly supported by the replacement technology as was the task of annotating information with changing situations and needs. Specific deployment issues are derived from these findings that should guide designers when implementing technology replacements for current physical information formats (e.g. whiteboards, notice boards, shared paper notes).

Electronic Patient Records systems configured into large enterprise models have become the assumed best route forward. In England, as in several other countries, this has expanded to a major meta-enterprise procurement programme. However, concerns are raised that such systems lack user ownership, and experience from other sectors shows difficulties with large enterprise systems. At a time of great change and once again shifting organizations, is this move simply building large and ponderous edifices with unstable materials? Latest software engineering research is now demonstrating the potential of an alternative model, enabling trusted information brokers to search out in real time at point of use data held in registered local and departmental systems. If successful, this could enable a new and less cumbersome paradigm. The data could move where needed whatever the service configuration. A concept demonstrator has been built set in the context of health and social care in England. It is important for all technological support to the health sector to be reviewed as new technologies emerge so as to identify and exploit new opportunities, and the results of this 3 year project show that the health record information broker route merits further investigative research.

There can be no doubt that the clinical info-structure is being significantly enriched with the deployment of new systems throughout the health sector. From a technological perspective, the initial emphasis has been mainly on functionality and only latterly on the usability of these clinical information systems. However, the large scale and rapid pace of the changes being wrought in the health sector will have a major impact on clinicians and patients, not least in how they interact with the technology. Therefore, it is not only hardware and software but people-ware, too, that needs to be actively managed; not simply a one-off functional specification but an ongoing, complex relationship. Usability is the human factor that encompasses the ethical, educational, and evaluative aspects of design. There is also a strong case for regarding usability of clinical information systems as a key critical success factor for the management of change within the health-care domain. In particular, the relationship between usability, and education and training is examined.

This paper presents an overview of several evidence-based medicine and patient information studies conducted across the UK health service over a 4 year period, investigating clinicians', managers', and patients' perceptions of digital resources (primarily digital libraries) in hospitals, Primary Care Trusts, NHS Direct (patient call centre) and patient groups. In-depth interviews and focus groups are analysed using grounded theory methodologies and through content analysis used to produce quantitative finding. The perceived impacts of three different methods employed for delivering health informatics are presented. The findings highlight some generic issues relevant for health informatics in the UK health sector as well as some specific issues for medical digital libraries. This paper reviews in more detail the issues of medical technology implementation (traditional implementation, on the wards, and intermediaries within in communities). A breakdown of the clinicians' and patients' information journey (information initiation, facilitation and interpretation) is also presented with regard to medical digital libraries and online resources. Broad guidelines derived from these findings are provided for health-informatics deployment.

Patient safety is a fundamental requirement of modern health-care systems and the application of information technology (IT) to this activity should have improvements in the area as one of its goals. Indeed, ensuring that the diagnostic IT strategy is optimized, for example, the use of IT in service redesign or data analysis, forms one of the main platforms for the National Framework for Service Improvement in Radiology. This paper presents both the concept behind and the results of a project that has been under way in the UK involving St Helens and Knowsley NHS Trust and IRS Ltd concerned with implementing effective IT-driven scientific support in the field of medical radiation protection. Locally developed software is employed in assessing, managing, and analysing patient dose data arising from X-ray examinations performed in the busy department of a large district general hospital (DGH). Such data are analysed in a variety of ways, for example, over time and according to location (department or X-ray room). This analysis not only provides a measure of performance against nationally agreed dose reference levels (DRLs) but also enables a detailed analysis of any variations as well as the establishment of local DRLs (performance indicators). This process provides quantitative input to management strategies aimed at service improvement. Such strategies are geared towards the support of the Ionizing Radiations (Medical Exposures) Regulations 2000 as well as implementation of quality-management principles at the heart of radiology practices.

ISABEL is a web-based clinical decision-support system for use by health care professionals. The Web site has been developed by the ISABEL Medical Charity. The system has come to the attention of the Department of Health, which is examining its potential effectiveness in the wider clinical context and exploring options for promoting its wider use in the NHS. The objectives of the work reported here were to review the existing use of ISABEL and to identify impediments to its development. A questionnaire was sent by e-mail to selected users of the system. Based on an analysis of the results (n=518), we found ISABEL to be a useful tool with many users. We believe that there is evidence of its success sufficient to support its continued availability and development. However, the largest hurdles to its increased use are systemic ones within the NHS and the way services are delivered.

Clinical coding is variable in UK general practice. The reasons for this remain undefined. This review explains why there are no readily available alternatives to recording structured clinical data and reviews the barriers to recording structured clinical data. Methods used included a literature review of bibliographic databases, university health informatics departments, and national and international medical informatics associations. The results show that the current state of development of computers and data processing means there is no practical alternative to coding data. The identified barriers to clinical coding are: the limitations of the coding systems and terminologies and the skill gap in their use; recording structured data in the consultation takes time and is distracting; the level of motivation of primary care professionals; and the priority within the organization. A taxonomy is proposed to describe the barriers to clinical coding. This can be used to identify barriers to coding and facilitate the development of strategies to overcome them.