PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Expert Systems”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13Linked to original sources
PubMed1989

A controlled evaluation of diagnostic criteria in the development of a rheumatology expert system.

As an intermediate stage in the development of an expert system to support undergraduate teaching in rheumatology, a decision tree incorporating the diagnostic criteria to be used in the expert system was produced by a team of rheumatologists. In a controlled trial, 119 final-year medical students each diagnosed 10 rheumatology cases, drawn from a pool of 96 cases, with or without the aid of the decision tree. Students who used the decision tree correctly diagnosed the following conditions more frequently than the control group: polymyalgia rheumatica (p less than 0.05), myopathies (p less than 0.01), systemic lupus erythematosus (p less than 0.05), pyrophosphate arthropathy (p less than 0.05), seronegative spondylarthropathies (p less than 0.01), intra-articular bleeding (p less than 0.05) and traumatic synovitis (p less than 0.05). The overall diagnostic accuracy of the students who used the decision tree was 81% compared with 68% for the control group (p less than 0.001).

Decision Trees↗
PubMed1993

A computerized expert system for handling the output of the Technicon H1 haematology analyser.

A computer-based expert system is described which handles the output of the Technicon H1 in the haematology laboratory of a large teaching hospital. Using patient request data, analyser results, error and morphology flags, the expert system decides; whether to validate the main indices plus differential; whether a blood film is required for manual review; and which abnormal results require phoning to the requesting doctor. The results of this computer-assisted analysis are sent to a printer adjacent to the analyser. The print-out details any further action required of the operator before release of results to the main hospital computer, and serves as a log of all samples run on that analyser. Benefits of the expert system include greatly simplified interpretation of the large array of analyser flags, and consistency in sample handling for all operators over all shifts.

Algorithms↗
PubMed2000

Controlling for chance agreement in the validation of medical expert systems with no gold standard: PNEUMON-IA and RENOIR revisited.

In the validation of medical expert systems, agreement among different human specialists on a random sample of cases may be taken as a substitute to a missing gold standard. Distance measures between pairs of experts, extensively described in previous studies, do not take into account the influence of chance-expected agreement. A weighted kappa index, with three different weighting schemes, is proposed as an alternative to be applied in the general situation of N cases assessed by E experts about K possible diagnoses, each of them qualified with one of G ordinal categories. A hierarchical cluster analysis, applied to the kappa matrices generated, allows for the classification of the expert system among clinical specialists, providing a relative assessment of its diagnostic ability. The above methodology is applied to the validation of two medical expert systems, PNEUMON-IA and RENOIR.

Cluster Analysis↗
PubMed1986

Expert system detection of drug interactions: results in consecutive inpatients.

Although drug interactions (DI) are a common cause of morbidity, their large number precludes remembering them. To address this problem, we constructed a microcomputer-based expert system and assessed its efficacy in 90 consecutive inpatients. It was found that, without the expert system, a knowledge of the patient's medication list did not affect the frequency of occurrence of DI. Also, without the expert system, no DI were predicted, clinically, whereas the expert system predicted 27 DI of which, in retrospect, 10 actually occurred. Unsuspected DI were most likely if: a drug was not within the specialty of the clinician, DI host factors were present, or the DI involved a commonly prescribed drug pair. Although none of the drug interactions were life-threatening, in two cases, the DI was the cause for admission. Since the offending medications could usually be adjusted in dose, drug interactions were easily corrected once clinicians were made aware of them.

Aged↗
PubMed2001

Advanced monitoring and control of anaerobic wastewater treatment plants: diagnosis and supervision by a fuzzy-based expert system.

A fuzzy-based expert system (ES) for the diagnosis and supervision for anaerobic digesters is presented. The system was developed in a Microsoft Windows support using fuzzy logic inference together with a rule base for the implementation of expert knowledge. The ES runs on-line through three main modules, which determine the state and trend of the process, and the best set points for the actuation on the final control elements of the plant. Two further modules run in parallel, when they are required by the operator, using off-line and on-line information for the detection of inhibition due to toxic compounds in the process and for the validation of the on-line diagnosis. The diagnosis and supervision ES was tuned up in order to adjust the membership functions describing the process, and lately tested, running on-line, to study the response of the rule base.

Anaerobiosis↗
PubMed1989

[PARTICLE--an expert system for microscopic image analysis].

The pathologist is usually not an expert in engineering or image analysis. Therefore an expert system was developed, entitled PARTICLE, to help pathologists producing image analysis programs in histological pathology. The PARTICLE expert system is based on karyometric data using the AMBA/R dialogue and programming system.

Expert Systems↗
PubMedDate not supplied

[Design of an expert system for decision-making in an emergency situation].

OBJECTIVES: To study the clinical applicability of the expert system URGSANT as a help in making up decisions in emergencies. MATERIAL AND METHODS: URGSANT is an expert system implemented in INSIGT 2+ which is structured in a modular and hierarchical form. It contemplates 44 urgent situations relating to the central nervous system, hematopoietic, cardiovascular, respiratory, gastrointestinal, genitourinary, endocrinological, and miscellaneous group. Validation of the program was made by four anesthesiologists who evaluated the performance of the program in 25 emergency cases and in 25 other situations that were treated by other specialists. RESULTS: The rationale of the system was basically correct. In most cases the program was considered efficient or very efficient during the different clinical situations and only in one case its guidance was wrong. CONCLUSIONS: The URGSANT expert system is an efficient and useful method for the clinician during emergency situations.

Anesthesiology↗
PubMedDate not supplied

Expert system development in nursing: implications for critical care nursing practice.

OBJECTIVE: To obtain information about how highly experienced critical care nurses reason to plan care and make decisions about a critically ill unstable patient, and to determine the usefulness of this information for expert system development. DESIGN: Descriptive, using think-aloud technique and protocol analysis. SETTING: Laboratory. PATIENT: A simulated patient case whose condition deteriorated over a 12-hour shift. The case depicted an elderly female with congestive heart failure and atrial fibrillation with rapid ventricular response. RESULTS: Protocol analysis revealed the information (data) that subjects used and how they structured that information to plan care and make decisions. Examination of subjects' reasoning processes allowed the investigators to identify "if-then" rules that could be used in expert system design. CONCLUSIONS: The reasoning processes identified would assist in expert system development. An expert system designed to represent experienced critical care nurses' knowledge and reasoning processes would preserve that expertise in a computer system that could then be used to assist less experienced nurses to improve their reasoning skills and strategies.

Adult↗
PubMed1996

Criteria-based expert system for cardiac ischemia evaluation in the emergency department.

OBJECTIVE: To develop and evaluate a cardiac ischemia computer expert system using a criteria-based expert shell for assessment of chest pain patients in a community hospital ED setting. METHODS: A retrospective, comparison study of the expert system against the clinical judgment of board-certified emergency physicians (EPs) was performed in 1 community hospital ED. All chest pain patients had either a cardiac catheterization, Persantine stress testing, or both within 1 month of ED presentation. A final diagnosis of acute myocardial infarction or unstable angina by a consultant cardiologist represented the criterion standard for cardiac ischemia. RESULTS: Of the 59 patients meeting study criteria, 28 (47%) had cardiac ischemia. The expert system had equal sensitivity (100%) and was more than twice as specific (39% vs 16%) in diagnosing ischemic cardiac disease as were the board-certified EPs (p < 0.001; McNemar's chi-square with Yates' correction). CONCLUSIONS: The criteria-based system built around a system of findings ordered by Bayes' rule has potential to augment the ability of the EP to accurately diagnose ischemic heart disease.

Adult↗
PubMed1989

[The physician and the computer. 28. Expert systems].

The authors review problems of expert systems and their application in medicine. They discuss their application, structure and function. Special attention is devoted to questions which concern the users, in particular the selection of the decision making method with regard to the character of the problem and then the structure of the knowledge base. The structure of the medical knowledge base has some specific features which are formulated as the classification of rules of medical knowledge.

Expert Systems↗
PubMed1994

Use of neural networks as medical diagnosis expert systems.

A major bottleneck in building expert systems is the process of acquiring the required knowledge in the form of production rules. A novel class of neural networks is proposed to articulate the knowledge it learned from a set of examples. It provides an appealing solution to the problem of knowledge acquisition. After training, the knowledge embedded in the numerical weights of trained neural networks can be easily extracted and represented in the form of production rules. The approach is demonstrated by an example of a hypothesis regarding the pathophysiology of diabetes.

Age Factors↗
PubMed2000

Remote access to an expert system for infectious diseases.

An expert-system antibiotic information database was developed in order to help non-specialist doctors to choose the appropriate treatment for patients with infectious diseases. Fifty doctors conducted a pilot trial of the database, using modern access and the telephone network. During an eight-month study period, 1053 queries were received. The range of duration of the queries was 130-350 s. Of the queries, 473 (45%) were for particular patients with an infectious disease. The response rate to a questionnaire mailed out to the users at the end of the project was 100%. All doctors, even those who had limited experience with computers, found it easy to understand and to use the database.

Anti-Bacterial Agents↗
PubMed1991

Set-covering diagnostic expert system for psychiatric disorders: the third world context.

This paper presents an implementation of the set-covering model for diagnosing psychiatric disorders. Such a model is useful as the basis for the inference mechanism of an expert system in that it provides a satisfactory solution to the difficult problem of multiple simultaneous disorders. The set covers have been formed through the 'diagonal search method' in which the combination of an element with the rest of the elements along the diagonals in the combination matrix was found to be adequate. 'Abductive logic' has been used to reach the possible final solution. Another feature of this expert system is its elicitation system. Provision has been made in the expert system for observations to be made and questions to be asked of the patient in difficult-to-elicit psychiatric signs. It makes this expert system usable by the non-expert clinicians. This has been specially designed in the context of third-world conditions. The system has been tested on cases given in the DSM-III case book with 100% success. However, the system's knowledge should be expanded and refined if it is to be used in psychiatric clinical practice.

Developing Countries↗
PubMed1989

Heuristic determination of relevant diagnostic procedures in a medical expert system for gynecology.

Many professions including medicine have standard operating procedures for the performance of their tasks. In the construction of expert systems, knowledge engineers have exploited this fact in devising heuristic rules that mimic the standard practice among such personnel (i.e., experts). This article suggests that the expert system designer should not stop at the level of the standard operating procedure heuristic but should instead investigate the reasons that the standard procedures have become standard. Because the experts in a field often do not understand the reasons for the standard operating procedures of their profession, this effort not only rewards the system designer but the expert as well. Because medical training does not always emphasize the logical reasoning underlying certain standard operating procedures, the ability to perform this reasoning is especially important in medicine. Further, a medical expert system for consultation or education would make a valuable impact by incorporating such knowledge and inference rules. This article investigates the development of a computerized medical expert system that applies the principles of artificial intelligence by limiting the number of questions and tests to find the solution for an ill-defined complex problem. Finally, we describe a logic program that tests the basic ideas.

Artificial Intelligence↗
PubMedDate not supplied

Expert systems integrated with information systems.

Amongst the users of the AIDA applications there is a rapidly growing interest in the use of expert systems, not as independent systems, but as logical extensions of their already existing information systems. In this paper a prototype system (IDEA) will be described that consists of a set of utilities for the construction of an expert system within the context of an AIDA application. Although IDEA does not excel in sophisticated knowledge representations nor in search strategies (the development of which was not our primary concern) it is able to demonstrate that the facilities provided by AIDA together with the IDEA facilities result in an expert system which is characterized by a high degree of integration with the already operational information system.

Artificial Intelligence↗
PubMed1989

Expert systems for human service programs.

Although computer programs called "expert systems" do not necessarily emulate the heuristics and logic used by human experts, they can consistently produce useful, better-than-average recommendations. Backward and forward reasoning chains have applicability to human service problems in social work, education, and vocational rehabilitation. There is increasing evidence that useful expert systems that do not require exotic languages and machines will soon begin inroads toward their staggering potential for "helping people" in human services make better decisions in matters of eligibility determination, casework quality control, written service plans for clients or students, job placement, service acquisition, policy interpretation, and other concerns.

Decision Making, Computer-Assisted↗
PubMed1988

The Annotator's Assistant: an expert system for direct submission of genetic sequence data.

As DNA sequencing technology improves and more rapid techniques become routine in molecular biology labs, researchers need to expedite the incorporation of information into genetic sequence databases, such as GenBank, by directly submitting sequence data. The Annotator's Assistant is an expert system that runs on an IBM PC and helps the molecular biologist, who may have little knowledge of the structure or content of a GenBank entry, to construct a complete and valid sequence submission file. This expert system uses a simple molecular biology knowledge base and a selection of customized screen entry forms to guide the user through the entry and annotation of a sequence and its biological features. The system compiles information about the contributor, journal references, physical and functional characteristics of the nucleic acid, source organism and features, and checks it to eliminate incomplete answers and simple errors. Users supply input by answering direct and multiple-choice questions, selecting menu items and completing entry forms; on-line help is available. Users may also enter new or unusual information using generic forms. Several modules of the expert system were converted into Prolog programs and compiled, decreasing the running time significantly. The expert system rules and the data entry forms are easy to modify, update and customize for specific sequence classes.

Base Sequence↗