Medical informatics and the Internet in medicine最新文献

Current tools for assessing risks associated with mental-health problems require assessors to make high-level judgements based on clinical experience. This paper describes how new technologies can enhance qualitative research methods to identify lower-level cues underlying these judgements, which can be collected by people without a specialist mental-health background. Content analysis of interviews with 46 multidisciplinary mental-health experts exposed the cues and their interrelationships, which were represented by a mind map using software that stores maps as XML. All 46 mind maps were integrated into a single XML knowledge structure and analysed by a Lisp program to generate quantitative information about the numbers of experts associated with each part of it. The knowledge was refined by the experts, using software developed in Flash to record their collective views within the XML itself. These views specified how the XML should be transformed by XSLT, a technology for rendering XML, which resulted in a validated hierarchical knowledge structure associating patient cues with risks. Changing knowledge elicitation requirements were accommodated by flexible transformations of XML data using XSLT, which also facilitated generation of multiple data-gathering tools suiting different assessment circumstances and levels of mental-health knowledge.

The shape and appearance of the optic nerve head region are sensitive to changes associated with glaucoma and diabetes that may be otherwise asymptomatic. The changes can be diagnostic of the diseases, and tracking of the changes in sequential images can be used to assess treatment and the progress of the illness. At present, change detection and tracking are performed manually, which can be a cause of poor repeatability. We are concerned with developing automated techniques of generating quantitative descriptions of the retinal images that might be used in diagnosis and assessment. In this paper, we investigate the use of images that have been collected and stored remotely, as this will replicate capture and automated processing by outreach clinics. Normal and abnormal images were collected from a range of sources, to simulate the mass screening process. The images were processed using simple signal-processing methods and divided into two groups. Using a chi-squared test, the separation of normal and abnormal images using this test was found to be highly significant (p < 0.05, n = 60).

The National Health Service National Programme for Information Technology is currently developing messaging standards to make available key information about an individual patient's care across and within different health-care settings. The complexity of this task makes it imperative that adequate tooling support is made available so as to aid consistency of design, implementation, conformance testing, and maintenance. Connecting for Health commissioned a proof of concept study to investigate whether the Object Web Language (OWL) and its associated tools could provide a basis for the message development and implementation environments. This study indicated that OWL is very much suited to such a task and should be seriously considered.

The vision of evidence-based medicine is that of experienced clinicians systematically using the best research evidence to meet the individual patient's needs. This vision remains distant from clinical reality, as no complete methodology exists to apply objective, population-based research evidence to the needs of an individual real-world patient. We describe an approach, based on techniques from machine learning, to bridge this gap between evidence and individual patients in oncology. We examine existing proposals for tackling this gap and the relative benefits and challenges of our proposed, k-nearest-neighbour-based, approach.

Thalidomide damage comprises a range of rare and complex disorders rarely encountered in normal clinical practice. Specific problems associated with the condition include chronic pain and medical procedures including taking blood. The benefit of international networking and the findings of recent research are mentioned. This leads to the establishment of four key requirements for a specialist database, and four priority issues to be included in the planning of a health information service for this group, of which the creation of a database is first. The other three priority issues are the creation of a web-based delivery system, the need to consolidate the specialist information available, and the need to create a system for evaluating and approving the information to be delivered. System design and implementation are discussed and key tasks identified, showing how the four key components of the service will be developed. Difficulties encountered have included decisions about standards to be adopted and identifying commercial organizations capable of completing different aspects of the work. This study illustrates the relevance and possibility of specialist reference centres for other rare disease groups.

Information-technology policies in many countries are full of aspirational statements and not generally based on the available evidence. This paper aims to contribute to a proper discussion of the evidence on electronic health records (EHR). The paper describes the methods we used in a review of the impact of EHR on clinical work and administration, summarizes our findings, and discusses their relevance in the context of policy makers' information requirements. We argue that the literature has, to date, largely failed to deliver usable findings.

In the healthcare sector, where the decisions made by software aid in the direct treatment of patients, software requires high levels of assurance to ensure the correct interpretation of the tasks it is automating. This paper argues that introducing adaptable decision processes within eHealthcare initiatives can reduce software-maintenance complexity and, due to the instantaneous, distributed deployment of decision models, allow for quicker updates of current best practice, thereby improving patient care. The paper provides a description of a collection of technologies and tools that can be used to provide the required adaptation in a decision process. These tools are evaluated against two case studies that individually highlight different requirements in eHealthcare: a breast-cancer decision-support system, in partnership with several of the UK's leading cancer hospitals, and a dental triage in partnership with the Royal Liverpool Hospital which both show how the complete process flow of software can be abstracted and adapted, and the benefits that arise as a result.

The Primary Care Data Quality programme (PCDQ) is a quality-improvement programme which processes routinely collected general practice computer data. Patient data collected from a wide range of different brands of clinical computer systems are aggregated, processed, and fed back to practices in an educational context to improve the quality of care. Process modelling is a well-established approach used to gain understanding and systematic appraisal, and identify areas of improvement of a business process. Unified modelling language (UML) is a general purpose modelling technique used for this purpose. We used UML to appraise the PCDQ process to see if the efficiency and predictability of the process could be improved. Activity analysis and thinking-aloud sessions were used to collect data to generate UML diagrams. The UML model highlighted the sequential nature of the current process as a barrier for efficiency gains. It also identified the uneven distribution of process controls, lack of symmetric communication channels, critical dependencies among processing stages, and failure to implement all the lessons learned in the piloting phase. It also suggested that improved structured reporting at each stage - especially from the pilot phase, parallel processing of data and correctly positioned process controls - should improve the efficiency and predictability of research projects. Process modelling provided a rational basis for the critical appraisal of a clinical data processing system; its potential maybe underutilized within health care.

The purpose of the Centre for Operational Research in Public Health (CORPH) is to optimize the accessibility to health information, thus making it possible to measure and follow up the health status of the Belgian population. The Standardized Procedures for Mortality Analysis (SPMA) software was developed in order to facilitate the use of vital statistics for health policy-makers and scientific researchers. Nowadays, SPMA is available on the Internet, because accessibility to health information is crucial. SPMA serves via a system of menus as the interface between databases (population, birth, and mortality) on one hand and statistical procedures on the other hand. Users can choose the parameters such as year, cause of death, geographical level, and statistical indicator, and so dynamic reports are produced 'on demand'. These procedures are available for the following modules: overall mortality, specific cause mortality, and perinatal statistics. Analysis can be carried out for one specific year or for a period over time. Pre-defined procedures accessible through menus make SPMA user-friendly, as it can be used without any preliminary knowledge of the statistical package. Tables, charts, or maps display the results. Users need only an Internet browser to access the application.