Integration of a stand-alone expert system with a hospital information system. (73/376)

A stand-alone PC expert system for evaluating the appropriateness of inpatient admissions has been integrated with an existing hospital information system. The expert system supports preadmission screening for appropriateness of inpatient admissions. The HIS provides extensive clinical data in a coded electronic form, permitting high-level decision support. The integrated system was developed for a 20 week randomized clinical trial to evaluate the effects of preadmission screening on inappropriate inpatient admissions. Three factors of the integration are considered: programmatic integration of the expert system, seamless presentation of mixed platform applications, and integration of coded data from the stand-alone application into the HIS data structure.  (+info)

The design of a rule-based clinical event monitor in a multi-vendor hospital computing environment. (74/376)

The Clinical Event Monitor (CEM) described here is a prototype system designed to explore the issues involved in building an institutional CEM that permits rapid, automated evaluation of clinical transactions and notification to clinicians of exceptional events in a multi-vendor computing environment. The CEM uses expert systems, database, and systems integration techniques. Ancillary (departmental) applications, including as Patient Registration, Laboratories, and Pharmacy have been licensed from commercial vendors. Application-to-application and application-to-database interfaces were built to mirror subsets of the ancillary patient databases into an institutional relational database (Oracle). The CEM receives registration updates via an HL7 message and evaluates data dependencies in rules via an interface to the relational database. The CEM engine was built using Nexpert, a commercially available expert system shell. Our short term goals were to: (1) build and maintain a patient census within the expert system environment via net based HL7 update broadcasts; (2) explore the data-driven features of Nexpert, (3) deliver prototype exception reports. This paper describes in general terms the design features of the CEM and in detail the features of a patient registry to NEXPERT bridge (from Oracle via HL7 structured transactions to NEXPERT) and the delivery of exception reports.  (+info)

Comparison of different information content models by using two strategies: development of the best information algorithm for Iliad. (75/376)

Iliad is a diagnostic expert system for internal medicine. Iliad's "best information" mode is used to determine the most cost-effective findings to pursue next at any stage of a work-up. The "best information" algorithm combines an information content calculation together with a cost factor. The calculations then provide a rank-ordering of the alternative patient findings according to cost-effectiveness. The authors evaluated five information content models under two different strategies. The first, the single-frame strategy, considers findings only within the context of each individual disease frame. The second, the across-frame strategy, considers the information that a single finding could provide across several diseases. The study found that (1) a version of Shannon's information model performed the best under both strategies---this finding confirms the result of a previous independent study, (2) the across-frame strategy was preferred over the single-frame strategy.  (+info)

Reuse of knowledge represented in the Arden syntax. (76/376)

Knowledge Data Systems is building a medical expert system for monitoring clinical events. This system uses the Arden syntax as a knowledge representation. Having encoded may different types of rules in the Arden syntax, we have noticed a number of shortcomings of the syntax. Many of these shortcomings originate from Arden's procedural orientation, from its failure to separate factual medical knowledge from knowledge of how the medical facts should be applied to a particular clinical situation. The absence of this separation leads to redundancy of knowledge and to difficulties in knowledge reuse. We suggest that standards for representing medical logic preserve this separation to engender knowledge reuse. We propose a general framework for representing medical logic which supports both knowledge sharing and reuse.  (+info)

Q & A: a query formulation assistant. (77/376)

Inexperienced users of online medical databases often do not know how to formulate their queries for effective searches. Previous attempts to help them have provided some standard procedures for query formulation, but depend on the user to enter the concepts of a query properly so that the correct search strategy will be formed. Intelligent assistance specific to a particular query often is not given. Several systems do refine the initial strategy based on relevance feedback, but usually do not make an effort to determine how well-formed a query is before actually performing the search. As part of the Interactive Query Workstation (IQW), we have developed an expert system, Questions and Answers (Q&A), that assists in formulating an initial strategy given concepts entered by the user and that determines if the strategy is well-formed, refining it when necessary.  (+info)

Evaluating drug prescribing in a large, ambulatory population: application of an embedded expert system. (78/376)

DUR is a process of problem detection and intervention designed to improve the quality and economy of drug prescribing. Retrospective DUR attempts to detect and address patterns of prescribing that might be indicative of inappropriate therapy. When the process is extended to a largely ambulatory population such as Medicaid beneficiaries, a number of complications are introduced due to the large numbers of patients and sparsity of data. In order to examine the impact of implementing a Medicaid DUR program, we developed a system that would apply screening criteria to prescription claims. It has been used to screen prescribing of groups of two antihypertensive drugs in the 1990 Maryland Medicaid population for 177,409 Medicaid eligible individuals. Potentially significant problems were detected with respect to dosing, duplication of therapeutic agents and drug interactions. The system represents, we believe, a significant improvement in the ability to detect and report prescribing decisions by increasing the specificity of the detection system. By the application of this system to a set of real-world data, we have demonstrated that it is feasible to implement such a system and derive results that are potentially useful in reducing the incidence of inappropriate physician decision-making.  (+info)

Decision support system and medical liability. (79/376)

Expert systems, which are going to be an essential tool in Medicine, are evolving in terms of sophistication of both knowledge representation and types of reasoning models used. The more efficient they are, the more often they will be used and professional liability will be involved. So after giving a short survey of configuration and working of expert systems, the authors will study the liabilities of people building and the using expert systems regarding some various dysfunctions. Of course the expert systems have to be considered only for human support and they should not possess any authority themselves, therefore the doctors must keep in mind that it is their own responsibility and as such keep their judgment and criticism. However other professionals could be involved, if they have participated in the building of expert systems. The different liabilities and the burden of proof are discussed according to some possible dysfunctions. In any case the final proof is inside the expert system by itself through re-computation of data.  (+info)

A cost effective expert system to assist physicians: epileptologists' assistant. (80/376)

While medical expert systems helped demonstrate that artificial intelligence was possible, few medical systems have been heralded as practical successes. We believe that expert systems will be practical successes if they cost effectively handle most of a physician's workload (i.e., routine care). To accomplish this goal, technology must appear invisible to the user; the system must be intuitive and anticipate users' needs. "Epileptologists' Assistant" is an example of our approach of combining a graphical user interface with an expert system and data base in a system to help in a routine specialty clinic. The goal is for two nurses and a physician to handle the workload of three physicians while increasing the quality of care. The current system reduces physician time by 66%. Our ultimate goal is to create a unified family of systems for medical specialties.  (+info)