International journal of bio-medical computing最新文献

The development and dissemination of Electronic Medical Records (EMR) is impeded because of several reasons. One of the reasons is considered the ‘unruliness’ of narrative data. In this article it is illustrated how the medical record can be structured to make it accessible from different perspectives, without the need to change the free text format of the narratives. The organising principles behind three existing medical record structures are analysed: the source-oriented, problem-oriented and time-oriented medical record. These principles are combined in a model of the medical record with four different views on medical data: a typological view, a time view, a problem view, and a process view. A data model is presented in which each of these views can be defined. In the discussion some examples are given of EMRs in which some of these views have been applied on coded data.

General practitioners (GPs) possess a wealth of information on the health of their patients. Hence, they are in a unique position to gather information for research, education or management. The chief goal of the Registration Network Family Practices is to establish a computerized database containing certain patient characteristics and all relevant health problems excluding minor, temporary illnesses. The database can be seen as a dynamic population sampling frame of chronic and/or severe morbidity, also including risk factors and psychosocial problems. The best way to make use of the Registration Network Family Practices is by researchers identifying and sampling patients with particular health problems. The database contained patient characteristics and problemlists of 61 887 persons, on September 1, 1995. At that time 214389 health problems had been entered in the database. The database is increasingly being used as a source of information for studies by researchers and students. Researchers find the database a useful tool, but they have to keep in mind that data on the process of care are not directly available. Furthermore, there is a limit to the number of studies which can be performed in the network practices, due to time limitations and the burden on the doctors and patients.

In this contribution the topic of this special issue is introduced: electronic patient records (EPRs). The characteristics of EPRs are presented. A number of problems that have to be solved before EPRs can be used on a large scale is discussed.

Despite a number of well recognized shortcomings of paper medical records, the use of a Computer Patient Record (CPR) is not widespread among specialists. The complexity of specialized care combined with the diversity of their domains of expertise, make it a challenge to design a CPR that satisfies the needs of a specialist. Ideally, CPRs are tailored to the specific tasks of each user, and yet general enough to permit exchange and sharing of information. The basic philosophy behind our CPR is a ‘mother’ record, which is extended with specialized sub-records. Two different types of subrecords are discussed: one to accommodate standardized data entry in the context of a specialty or research protocol, and another for structured recording of accidental findings outside one's own domain of expertise. The CPR supports the entry of free text and does not impose structured data entry on the physician, but stimulates him to do so by confronting him with the benefits of a structured CPR.

The paper describes a quality control program based on the principles of clinical methodology and indicators defined by physicians and hospital administrators according to general as well as local needs. The program is supported by a knowledge-based system which can be used in two ways: with on-line helps and hints to ensure effective and efficient medical decisions on a simulated patient for training purposes; and without facilities supporting the user to be used on an on-line setting for performance evaluation. The quality control program includes the evaluation of effectiveness and efficiency of patient care with respect to the overall process, single hypotheses and individual decisions: the evaluation regards the number and reliability of activated hypotheses, costs, time spent, number and appropriateness of investigations. The overall process is recursive, in that the results of each cycle are used by physicians to define new goals and indicants for the next cycle; quality control is active because physicians under evaluation are directly involved in the definition of goals and indicants and in the evaluation of results; evaluation is objective because indicants are predefined, and evaluation criteria are transparent.

In 1992 the Dutch College of General Practitioners (NHG) started a project, which lasted until May 1994. The project had three major objectives:

• establishing as exactly as possible what benefits we gain from using an Electronic Medical Dossier (EMD) can we find an influence on the quality of care? Which drawbacks or problems are there

• advising on the optimal use of an EMD; What is the best place to record certain data?

• advising the Working Committee on Informatics (WCIA), of Dutch National Association of General Practitioners (LHV) and NHG on the directions for the new Reference Model 1995.

To obtain these goals panel discussions and a questionnaire were used. The project resulted in advice on how to use the EMD in the most efficient way. Also we have learned about the use of GP-information systems and the perception about this usage by the Dutch GPs.

This paper analyses the purpose, background, scope, and success to date of designing and implementing a comprehensive electronic patient record system for community care in the UK, in the context of the increasing policy focus upon community care. The project is situated in Plymouth in the UK, a major provider of community care. The paper indicates intended benefits of the system for patients, professionals, and health care organisations. The rationale behind the record content is explained, as is the record structure. Intended uses of the records form a further baseline for study, and the paper assesses the key success factors to achieving the goal of reliability, quality, and effective use of resources.

This contribution deals with legal issues which arise in the application of electronic health records. Especially the issues with regard to ensuring both the authenticity of data and their originators are discussed.

This paper describes the current state of a medical language processor for Dutch. The goal is to implement a language specific front-end compatible with some existing applications that aim at the intelligent extraction and processing of information from patient discharge summaries. A complete chain for processing and understanding Dutch medical documents will be the ultimate result. The text focuses mainly on the language specific aspects of the language processing chain. Evaluation results of the already functioning components are given as well as an outline for future developments and enhancements. A short theoretical background is provided (cf. also [1–3]: Rossi Mori et al., Proc. SCAMC 90, 1990, pp. 185–189; Wingert, in: Informatics and Medicine, an advanced course, Springer-Verlag, 1977, pp. 579–646; Wingert, Proc. MEDINFO 80, 1980, pp. 1321–1331) before the description of each component in order to familiarise the non-experienced reader with the basic notions of computational linguistics.