SEARCH · Search PubMed
Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
The prerequisites and methods to provide explanations for medical knowledge-based systems using first order calculi are discussed. The implementation of a general hypertext-based explanation component and its integration in two different medical knowledge-based systems are described.
There is a growing interest in using care maps in ICU. So far, the emphasis has been on developing the critical path, problem/outcome, and variance reporting for specific diagnoses. This paper presents a conceptual knowledge-based care protocol system design for the ICU. It is based on the manual care map currently in use for managing myocardial infarction in the ICU of the Sturgeon General Hospital in Alberta. The proposed design uses expert rules, object schemas, case-based reasoning, and quantitative models as sources of its knowledge. Also being developed is a decision model with explicit linkages for outcome-process-measure from the care map. The resulting system is intended as a bedside charting and decision-support tool for caregivers. Proposed usage includes charting by acknowledgment, generation of alerts, and critiques on variances/events recorded, recommendations for planned interventions, and comparison with historical cases. Currently, a prototype is being developed on a PC-based network with Visual Basic, Level-Expert Object, and xBase. A clinical trial is also planned to evaluate whether this knowledge-based care protocol can reduce the length of stay of patients with myocardial infarction in the ICU.
This report describes a new simplified judgment system which enables users to register appropriate judgment rules with ease and to apply them to a wide variety of medical problems. The rule utilized in this system is 3-AND-3-OR, quite a simple one. By applying this judgment rule to the data of as many as 60 items, judgment results of the individual on each item is given by four different grades or categories, namely: 1) normal, 2) borderline, 3) abnormal, and 4) severe. As many as 20 types can be obtained simultaneously. The simplicity of the algorithm allows medical users who are not the experts in computer technology to use this system on a DOS-based personal computer.
Explore the source record for details and available documents.
Decision-support systems hold a specialized body of knowledge in computerized form such that the non- specialist can obtain expert-level information. The goal of these systems in clinical sciences is usually to assist patient care by providing the clinician with improved diagnosis or treatment planning. Decision-support systems consist of three components: the user interface through which the clinician or patient enters signs or symptoms, the set of data describing clinical knowledge in the domain of the program, and an inference engine to manipulate the data set in light of a patient's specific signs or symptoms to arrive at a diagnosis or treatment plan. Such systems usually use one of three mechanisms of analysis alone or in combination: classification trees, Bayesian conditional probabilities, or rule-based (heuristic) systems. Numerous problems must be solved before decision-support systems will become commonplace in clinical practice. Data entry of patients' signs and symptoms is often tedious. The quality of the clinician's initial observations is of great importance in determining the quality of the output. It is also often difficult to convey to a program the subtlety of clinical information observed. Knowledge required in clinical data bases is often unavailable or imprecise. As these and other challenges are addressed we can anticipate increased utility of decision support programs in the future.
The computer program PEDINFUS, first described in 1991, has been fundamentally revised and further developed. The area of application has been considerably widened as additive parenteral nutrition has been included and the group of newborn and preterm infants has been taken into account. Consequently, the program can be used for children of all age groups. In addition, the program has a graphical user interface and can be used on several hardware platforms. The flexibility of the program has also been increased to a considerable degree. Now the nutrient amounts per kilogram per day, the limits of the laboratory values, the combination of enteral food and infusion solutions, and the already drawn-up infusion plans can be changed at liberty. Considerably more matters of clinical interest accompanying parenteral nutrition have been integrated in the program. Further plausibility controls have also been introduced to achieve greater certainty in the calculation of the infusion solutions. In consequence, the preconditions for ensuring and controlling the quality of infusion therapy regimens can be established on an improved level.
The hospital materials management function--ensuring that goods and services get from a source to an end user--encompasses many areas of the hospital and can significantly affect hospital costs. Performing this function in a manner that will keep costs down and ensure adequate cash flow requires effective management of a large amount of information from a variety of sources. To effectively coordinate such information, most hospitals have implemented some form of materials management information system (MMIS). These systems can be used to automate or facilitate functions such as purchasing, accounting, inventory management, and patient supply charges. In this study, we evaluated seven MMISs from seven vendors, focusing on the functional capabilities of each system and the quality of the service and support provided by the vendor. This Evaluation is intended to (1) assist hospitals purchasing an MMIS by educating materials managers about the capabilities, benefits, and limitations of MMISs and (2) educate clinical engineers and information system managers about the scope of materials management within a healthcare facility. Because software products cannot be evaluated in the same manner as most devices typically included in Health Devices Evaluations, our standard Evaluation protocol was not applicable for this technology. Instead, we based our ratings on our observations (e.g., during site visits), interviews we conducted with current users of each system, and information provided by the vendor (e.g., in response to a request for information [RFI]). We divided the Evaluation into the following sections: Section 1. Responsibilities and Information Requirements of Materials Management: Provides an overview of typical materials management functions and describes the capabilities, benefits, and limitations of MMISs. Also includes the supplementary article, "Inventory Cost and Reimbursement Issues" and the glossary, "Materials Management Terminology." Section 2. The MMIS Selection Process: Outlines steps to follow and describes factors to consider when selecting an MMIS. Also includes our Materials Management Process Evaluation and Needs Assessment Worksheet (which is also available online through ECRInet(TM)) and a list of suggested interview questions to be used when gathering user experience information for systems under consideration. Section 3A. MMIS Vendor Profiles: Presents information for the evaluated systems in a standardized, easy-to-compare format. Profiles include an Executive Summary describing our findings, a discussion of user comments, a listing of MMIS specifications, and information on the vendor's business background. Section 3B. Discussion of Vendor Profile Conclusions and Ratings: Presents our ratings and summarizes our rationale for all evaluated systems. Also includes a blank Vendor Profile Template to be used when gathering information on other vendors and systems. We found that, in general, all of the evaluated systems are able to meet most of the functional needs of a materials management department. However, we did uncover significant differences in the quality of service and support provided by each vendor, and our ratings reflect these differences: we rated two of the systems Acceptable--Preferred and four of the systems Acceptable. We have not yet rated the seventh system because our user experience information may not reflect the vendor's new ownership and management. When this vendor provides the references we requested, we will interview users and supply a rating. We caution readers against basing purchasing decisions solely on our ratings. Each hospital must consider the unique needs of its users and its overall strategic plans--a process that can be aided by using our Process Evaluation and Needs Assessment Worksheet. Our conclusions can then be used to narrow down the number of vendors under consideration...
Explore the source record for details and available documents.
Explore the source record for details and available documents.
The software requirements specification is the single most important document in the software development process. It provides the basis for development as well as for validation. The SRS needs to include adequate definition of all requirements without specifying implementation or project management issues. The SRS should be completed early in the development process. However, it is very likely that changes will occur during the development life cycle. This is not an excuse for approving and releasing the current version of the SRS. When changes occur, the SRS must be revised. In any case, the concept is to deal with the current, approved version of the SRS. Ultimately, the SRS should include all the information needed to proceed into the design phase of software development.
Explore the source record for details and available documents.
A new approach in ECG training is presented. The overall approach is based on a combination of the "page-turning architecture", the "reference model" and AI techniques. A thorough analysis of the training requirements in this field has been carried out; the results determined the educational scenarios and the associated evaluation sessions. The system (CARDIO-LOGOS) is intended to be used mainly by internal medicine physicians and general practitioners, as well as by medical students. The layered structure of the whole CBT application together with the advanced learning strategies and the interactive multimedia technology offer a flexible environment that encourages experimentation and supports individualised training for a wide variety of users.
The monitoring and treatment of patients in a care unit is a complex task in which even the most experienced clinicians can make errors. A hemato-oncology department in which patients undergo chemotherapy asked for a computerized system able to provide intelligent and continuous support in this task. One issue in building such a system is the definition of a control architecture able to manage, in real time, a treatment plan containing prescriptions and protocols in which temporal constraints are expressed in various ways, that is, which supervises the treatment, including controlling the timely execution of prescriptions and suggesting modifications to the plan according to the patient's evolving condition. The system to solve these issues, called SEPIA, has to manage the dynamic, processes involved in patient care. Its role is to generate, in real time, commands for the patient's care (execution of tests, administration of drugs) from a plan, and to monitor the patient's state so that it may propose actions updating the plan. The necessity of an explicit time representation is shown. We propose using a linear time structure towards the past, with precise and absolute dates, open towards the future, and with imprecise and relative dates. Temporal relative scales are introduced to facilitate knowledge representation and access.
Computer-based patient education materials are becoming more widely used in an attempt to increase the efficacy and efficiency of the delivery of health care. This paper discusses the authors' experiences in designing and implementing interactive multimedia presentations for patient education in an orthopaedic surgery office setting. Content must be chosen carefully to effectively educate without alienating the patient; simple graphics and animation are best for conveying complex medical and surgical concepts. The interface must be simple; both mouse input and touchscreen have proven acceptable and require minimal instruction. Improvements in program design will result in task-oriented evaluation systems that allow the patient to use the information gained to demonstrate understanding.
Two commercially available complete anesthetic simulators were studied in the United States. Although there are some differences between the two systems, each consists of an adult manikin allowing some direct anesthetic interventions, a system of producing physiologic signals to any commercial monitoring system, and the ability to interface with an anesthetic machine and ventilator. In addition, both simulators model the responses to a variety of drugs used by anesthetists. With their associated computer controls, it is possible to mimic a number of recognized anesthetic critical situations and to record the responses made by the anesthetist and determine the effects on the "patient." In use, one system is devoted principally to teaching crisis resource management to anesthetists. The other system is used more generally to teach anesthetists how to approach a variety of problems. In our opinion, each system could be used in either of these ways. Both systems are capable of development into valuable teaching tools for anesthetists and for others involved in critical care. There is potential for the training of paramedics or nurses involved in anesthetic and recovery room care and intensive care. Other options include the investigation of critical events and the development and subsequent testing of clinical management protocols. Anesthetists are familiar with the use of manikins in the teaching of airway management and basic and advanced life support. Newer manikins can be used to practice skills in intravascular cannulation; some can be used with monitoring equipment and defibrillators to provide more realistic teaching. Computer programs, especially those for personal computers (PCs), can also be used to simulate the pharmacophysiologic behavior of patients in a variety of states. Now available are combined systems using manikins controlled by computer, with interfaces to anesthetic machines, ventilators, and monitoring equipment. Two systems are commercially available in the United States. In this report, we briefly describe their technical specifications and how we saw them being used.
For the registration, documentation and evaluation of patient data in cranio-maxillo-facial (cmf) trauma surgery a Windows-based application front end for relational data base systems (RDBS) has been developed. A simple-to-learn, easily reconfigurable user interface can be adjusted to the dynamically changing needs of individual departments. A graphical user interface (GUI) eases the entry of complex information like fracture positions, the location of implanted osteosynthesis material, etc. The new program also simplifies the daily routine documentation tasks. Being linked to a Hospital Information System (HIS) it makes use of the patients' individual base data stored there. Statistical data for various studies can be extracted from the database. The program has been successfully tested on a collective of 1.178 cmf trauma patients. Predefined analyses can be generated now by the simple click of a button for various case selections. New users learn to operate the program in a very short time.
Explore the source record for details and available documents.
Clinical users expectations from medical informatics are evolving due to the wide availability of biomedical information services on the Internet. Thanks to hypertexts and advanced browsing tools users with no informatical expertise can travel on the Internet and easily gain access to textual databases. With a multimedia computer other kinds of information can be grabbed: images, sounds and audiovisual documents. Basic Internet services (electronic mail, discussion lists, file transfer protocol, terminal emulation) can be accessed from a wide range of hardware equipment. However, the real power of a world-scale computer network like the Internet will be unleashed only when its global connectivity will be linked to the powerful retrieval ability of existing clinical and related databases. While biomedical journals editors and other medical information providers are in the way to offer electronic versions of their paper-based products, at the leading edge of this world-scale process is the USA National Library of Medicine, with the Internet-compatible version of its Grateful Med software which is expected to be launched during 1996.