Medical informatics = Medecine et informatique最新文献

In patients presenting with trauma, early diagnosis of neck injuries is likely to affect long-term outcome. This paper reports a study that compared lateral images of the cervical spine produced by a Picture Archiving and Communication System (PACS) with the same images produced using computed radiography (CR). The study was undertaken at the Hammersmith Hospital, London. Data were collected on 100 patients who presented with trauma. Both soft copy (PACS) and hard copy (CR) images of the cervical spine were produced for each patient from the same radiographic exposure. The images were viewed by five clinical members of the Accident and Emergency Department. Data were collected on the level of the cervical spine that could be viewed, the clinical management following the viewing of the image and the use of PACS 'tools'. Overall no statistically significant differences between modalities were found in the level of visualization. Within viewer differences were found for three viewers: one indicating better visualization with PACS and two indicating better visualization with CR. The results relating to patient management indicate greater clinician confidence following the viewing of PACS images for two viewers. The use of PACS 'tools' improved visualization of the cervical spine for one viewer.

This paper addresses the problem of integrating healthcare information systems, from a technological viewpoint. We propose to take the concept of an ¿integration service' as an elementary concept in discussing the problem of integration. We then propose a taxonomy for grouping integration services according to their functionality and their domain specificity. The use of this taxonomy for decomposing an integration problem into (less complex) sub-problems is demonstrated. Finally, a sequence of steps to be taken in solving an integration problem is discussed.

Integration of information has enabled expeditious operation in air transfer, banking, shopping, and stock brokerage, but not in healthcare. Existing health information systems (HIS) are concerned too much with departmental performance and charge billing, and neglect the end users--the patients and the physicians. The resultant HIS then has divergent operation to antagonize the physicians, and has fragmented data to the disadvantage of patients. Recognizing the problems and the trend of HIS, this study proposed and implemented a patient-centred and physician-oriented HIS in a Urology clinic. The proposed HIS had patient care as its core, and accurately coded the patient's diagnoses and therapy information. It also offered a friendly environment and complete function for the physician to administrate medical records and to provide healthcare services. The HIS had client/server structure and an open system to protect the hardware investment and the software implementation. It will be the key to success in complete hospital environments.

The objective was to determine whether or not a laboratory based computer diagnostic program could aid the clinician in solving problems, outside his or her field of expertise, by expertly interpreting ¿Emergency Room' haematological and biochemical data and providing a list of possible diagnoses. The program, which uses Fuzzy Sets and pattern recognition as its Inference Mechanism coupled with a data base comprised of haematological and biochemical responses to disease collected over a period of 10 years in a teaching hospital, analysed data published in two leading journals--the 'Clinical Problem-Solving' section of the New England Journal of Medicine and the 'Lesson of the Week' feature of the British Medical Journal. It was found that the computer program often presented diagnoses not thought of by the clinician. With such a system, sometimes as few as three routine investigations suggested the diagnosis. The diagnostic accuracy could be improved with a more structured approach to ¿Emergency Room' laboratory investigations. It is concluded that the computer, programmed to recognize a disease by the pattern of its response to routine haematological and biochemical investigations, could contribute significantly to diagnosis.

Until now computer-assisted parasite identification was based on database applications requiring data specification on an individual basis, thus limiting the ability of the system to handle rule-based knowledge as humans are used to do. A new Expert PArasite IdentificatiON (EPAION: Greek term for expert) system was developed to serve as an interface between the database and the user, where the database is a repository for bionomic and morphological facts about the parasites for the expert system. The system was developed by using a logic-based computer language which allows the definition of rules and facts to assist the creation of queries to the database. The components of the system are the knowledge base, the multimedia data base, the inference mechanism, and the graphical user interface. The operational modules of the system are the Parasite Identifier and the system Utilities. This expert system facilitates knowledge incorporation in a manner simulating the natural mental process, thus allowing the checking of the accuracy of the information that the user feeds to the computer and the creation of intelligent queries to the database. These characteristics accelerate focusing and optimize the parasite identification scheme regardless of the user's profile of competency.

In this paper we describe an approach to utilize Case-Based Reasoning methods for trend prognoses for medical problems. Since using conventional methods for reasoning over time does not fit for course predictions without medical knowledge of typical course pattern, we have developed abstraction methods suitable for integration into our Case-Based Reasoning system ICONS. These methods combine medical experience with prognoses of multiparametric courses. We have chosen the monitoring of the kidney function in an Intensive Care Unit (ICU) setting as an example for diagnostic problems. On the ICU, the monitoring system NIMON provides a daily report based on current measured and calculated kidney function parameters. We abstract these parameters to a daily kidney function state. Subsequently, we use these states to generate course-characteristic trend descriptions of the renal function over the course of time. Using Case-Based Reasoning retrieval methods, we search in the case base for courses similar to the current trend descriptions. Finally, we present the current course together with similar courses as comparisons and as possible prognoses to the user.

IBIS is a broad range informatics tool, which can provide essential assistance to users during quality development projects in the health care environment. It can be used to set up a preliminary process model and specify variable and their interrelationships; the system propagates various quality related effects through the process structure, in a bottom up fashion, by linking quality indices to outcomes, repetitively, until arriving at the final outcome, at the top. An incorporated interactive browser is used to simulate the running process, to test and evaluate it, though a cause--effect interaction on intermediate or final outcomes. The tool provides guided support throughout the quality development procedure and during the continuous improvement process. At the same time, it constitutes an effective training tool on the principles of quality work. Additionally, IBIS can be used for the quality system's documentation, by means of a multimedia presentation, incorporating descriptive text, images and graphical displays, video sequences and sound.

We present a local Dissemination of EPIC, a project which has been devised to support health and social primary care by an information system. One key point of the EPIC project was a standardization effort at European level, providing a standardized basis for the management system based on client needs for planning and manpower control. Whilst EPIC has been designed as a general community information system, the main EPIC applications focus is on the care of the elderly. Savona is a middle size Italian town with a high percentage of elderly people and has already had an experience of integration of health and social care within an Italian project. It has therefore been regarded as a suitable site for the dissemination of EPIC. The EPIC application solved some of the information problems which emerged during the validation of the previous Italian project, such as the definition of the requirements; the collection, processing and retrieval of the clinical/social data; the definition of responsibilities and relations of the operators.

The maturing of telecommunication technologies has ushered in a whole new era of applications and services in the health care environment. Teleworking, teleconsultation, mutlimedia conferencing and medical data distribution are rapidly becoming commonplace in clinical practice. As a result, a set of problems arises, concerning data confidentiality and integrity. Public computer networks, such as the emerging ISDN technology, are vulnerable to eavesdropping. Therefore it is important for telemedicine applications to employ end-to-end encryption mechanisms securing the data channel from unauthorized access of modification. We propose a network access and encryption system that is both economical and easily implemented for integration in developing or existing applications, using well-known and thoroughly tested encryption algorithms. Public-key cryptography is used for session-key exchange, while symmetric algorithms are used for bulk encryption. Mechanisms for session-key generation and exchange are also provided.