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 577 records · Page 32Linked to original sources

PubMedDate not supplied

'Carrusel': an expert system for vestibular diagnosis.

Neuro-otology is the only field of otolaryngology in which diagnoses are mainly deductive. Although many technological advances have indeed occurred, the patient history still remains the most important part of the evaluation of a patient complaining of vertigo and/or dizziness. The use of artificial intelligence methods as an aid for the solution of clinical problems is not new. "Carrusel" is a Prolog build-up expert system dealing with the diagnosis of vestibular disorders that achieves a success rate of 97% when compared to the human experts involved in its design.

Expert Systems↗

PubMed2006

Context-sensitive autoassociative memories as expert systems in medical diagnosis.

BACKGROUND: The complexity of our contemporary medical practice has impelled the development of different decision-support aids based on artificial intelligence and neural networks. Distributed associative memories are neural network models that fit perfectly well to the vision of cognition emerging from current neurosciences. METHODS: We present the context-dependent autoassociative memory model. The sets of diseases and symptoms are mapped onto a pair of basis of orthogonal vectors. A matrix memory stores the associations between the signs and symptoms, and their corresponding diseases. A minimal numerical example is presented to show how to instruct the memory and how the system works. In order to provide a quick appreciation of the validity of the model and its potential clinical relevance we implemented an application with real data. A memory was trained with published data of neonates with suspected late-onset sepsis in a neonatal intensive care unit (NICU). A set of personal clinical observations was used as a test set to evaluate the capacity of the model to discriminate between septic and non-septic neonates on the basis of clinical and laboratory findings. RESULTS: We show here that matrix memory models with associations modulated by context can perform automatic medical diagnosis. The sequential availability of new information over time makes the system progress in a narrowing process that reduces the range of diagnostic possibilities. At each step the system provides a probabilistic map of the different possible diagnoses to that moment. The system can incorporate the clinical experience, building in that way a representative database of historical data that captures geo-demographical differences between patient populations. The trained model succeeds in diagnosing late-onset sepsis within the test set of infants in the NICU: sensitivity 100%; specificity 80%; percentage of true positives 91%; percentage of true negatives 100%; accuracy (true positives plus true negatives over the totality of patients) 93,3%; and Cohen's kappa index 0,84. CONCLUSION: Context-dependent associative memories can operate as medical expert systems. The model is presented in a simple and tutorial way to encourage straightforward implementations by medical groups. An application with real data, presented as a primary evaluation of the validity and potentiality of the model in medical diagnosis, shows that the model is a highly promising alternative in the development of accuracy diagnostic tools.

Decision Support Systems, Clinical↗

PubMed1990

An expert system for the nutritional management of the critically ill.

While there have been considerable advances in the last several years in the nutritional management of the critically ill, these improvements are not always recognized in intensive care environments. In this paper we describe the development and testing of an expert system, NUTRITIONAL ADVISOR, which would be be an aid in providing nutritional assessment and support of critically ill patients. We discuss various approaches to treating time-varying data in the knowledge base in order to provide a recommended level of nutritional support which varies smoothly from day to day.

Critical Care↗

PubMed1993

The role of expert systems in improving the test requesting patterns of clinicians.

The many strategies proposed for influencing the test requesting patterns of clinicians have had only limited success, largely because they are labour intensive and depend on motivation and commitment. Clinical protocols which have been locally agreed between laboratory staff and clinicians are potentially one of the more successful strategies, but detailed study of their application in different clinical settings has been limited by practical problems. Expert systems offer a way of implementing locally agreed protocols and, consequently, of assisting the identification, audit and refinement of laboratory testing strategies. Where these systems have been applied in specialist units they have resulted in savings in time by both clinical and laboratory staff, and an overall reduction in the number of clinical chemistry tests done within and out of hours. These systems offer promise as a method of improving laboratory utilization.

Clinical Laboratory Information Systems↗

PubMed1995

An expert system based preventive medicine examination adviser.

Periodic preventive medicine examinations generally rely on a standardized approach. In addition, they are often performed by physicians with only limited training in preventive medicine. Evaluation of a corporate-based program led to the prototype development of an artificial intelligence (AI)-based expert system to collect information from employees and make very specific recommendations for primary practitioners. Unique features include the customizing of questions for each subject and the selection of information to be acquired, both based on answers to previous questions. Recommendations are highly person specific and fall into four categories: laboratory testing, primary physician testing, counseling, and referral. The AI approach allows for easy updating of recommendations in order to meet changes in local preventive resources and national recommendations.

Artificial Intelligence↗

PubMed2002

The use of expert systems for improving test use and enhancing the accuracy of diagnosis.

The experience with BloodLink and LAS provides strong evidence that electronic knowledge support has a significant and lasting effect on laboratory test ordering by physicians. Compliance with CPG is also improved despite the ability of the guideline process to keep up to date. As discussed previously, the limitations to the application of protocols and CPG can be eliminated by electronic knowledge support. Indeed, this technology may be considered the future salvation of evidence-based medicine. It is also apparent that using the expert system to provide interpretations of the results ensures optimal use of the tests. The ability to reduce costs by 20% using stringent use control measures is meaningless if by misunderstanding, all of the potential information is not understood. In the future, as computer connectivity becomes pervasive within the practice of medicine, systems, such as BloodLink and LAS, will be used routinely for many aspects of care. Molecular genetic testing and proteomics will become a major component of routine medical practice. The complexity of what to order, the implications of performing the tests, on whom to do them, and what the vast array of data mean, will demand the use of CARTKS. It is becoming increasingly popular for patients to obtain their own results and to manage their own medical record. In some jurisdictions patients may order their own tests. We will undoubtedly see the development of knowledge support tools that are designed for patient use. The CARTKS provided by computer systems is the most powerful approach to use control and it has the additional benefit of doing so while enhancing medical care.

Decision Support Systems, Clinical↗

PubMed1988

Expert system for the selection of high-performance liquid chromatographic methods in pharmaceutical analysis. Validation of the rules for the selection of the mobile phase.

The rules for the selection of the mobile phase and the validation performed on 44 pharmaceutical preparations, containing one to five active compounds, are described. These rules are incorporated into an expert system, called LABEL, for the selection of high-performance liquid chromatographic methods in pharmaceutical analysis. A single stationary phase type is used, namely a nitrile or cyanopropyl (CN) column, which can be used in both normal-phase (NP) and reversed-phase (RP) chromatography. Three mobile phase systems were evaluated on this column type: NP, RP with water and RP with buffer. LABEL selects one of these three systems on the basis of the rules incorporated for the mobile phase selection, checks if the addition of ion-suppressing agents to the eluting agent is necessary and finally gives the starting composition of the mobile phase in each of the three systems. For this selection the number of compounds in the sample, the acid-base properties and the hydrophobicity of the solutes are the more important factors. The validation of the rules on 44 pharmaceutical preparations resulted in an immediate success in 82% of all cases. In half of the remaining cases, the system proposed can be adapted with a minor change in conditions, so that it can also be used in practice.

Chromatography, High Pressure Liquid↗

PubMed1992

Expert system design in hematology diagnosis.

A two-part study was designed to test the hypothesis that sufficient information is available from a modern hematology analyzer (the Coulter STKS) to reach a reliable intermediate conclusion which can be used as input to the next decision-making level in the design of a high-performance expert system for hematology diagnosis. In phase one, we analyzed the performance of three probabilistic systems (using Bayes' rule) which interpret STKS data: a control system which took the traditional approach of classifying cases into specific diagnoses, and two test systems which were designed to reach only an intermediate conclusion but not a final diagnosis. One of the test systems classified cases into "textbook categories" of disease and the other utilized defined diagnostic patterns. The systems were tested with 150 cases. The pattern approach ranked the correct choice first in 141 of 150 cases (94%). In phase two, we abandoned Bayes' rule, reformulated the pattern approach into a heuristic classification system, and tested its reliability on 820 cases. The algorithm of the reformulated system was able to classify all 820 cases into the same predominant pattern as a panel of three experienced laboratory hematologists.

Algorithms↗

PubMed1995

Expert systems in the health administration curriculum.

With the growing use of computers and on-line hospital information systems, a need exists for health care managers trained in computing and computer applications. This article reviews the advances in health care computing and reports on the design and implementation of a new course in a specific computer application, known as expert systems, in a health administration curriculum. The specific course framework is described and several student projects are presented and discussed.

Computer Communication Networks↗

PubMed1989

Expert system reasoning about dynamic systems by semi-quantitative simulation.

Current symbolic knowledge representation techniques are inadequate for describing complex dynamic systems, which are time-varying and contain feedback loops. These systems are particularly difficult to represent when quantitative knowledge about the relationships within the system is incomplete. This paper describes a symbolic extension of the system dynamics method which can answer 'what if' questions about system dynamics models semi-quantitatively. The method consists of (1) definition of generic model 'building blocks' which map directly onto difference equations; (2) development of a symbolic causal model of a system in terms of the generic functional 'building blocks', any available quantitative or semi-quantitative parameters, and a set of generic default values; (3) automatic translation of the model into a system of first-order difference equations; and (4) numerical integration of the equations by standard methods. A complex model with semi-quantitative parameters, representing the human cardiovascular system, is used to illustrate the method. This method couples the descriptive abilities of mathematics with the symbolic power of causal inference methods by providing the same knowledge base for both computational levels. It also eases truth maintenance, knowledge acquisition, and explanation. It may prove useful for expert system development in a variety of application domains whose processes are time-varying and homeostatic.

Computer Simulation↗

PubMed1997

[Optimization of dose distribution of radiation in cancers of the cavum: association of an expert-system and a mathematical algorithm].

Optimization of radiation therapy in nasopharyngeal carcinoma is particularly complex due to both the proximity of at risk organs and the high dose that has to be delivered. To obtain an optimal dose distribution, a knowledge-based optimization technique has been designed that associates an expert-system, named CAVCAV, with numeric optimization (gradient projection method). Based on clinical and physical criteria, CAVCAV determines the geometric characteristics of the radiation fields (beam direction, location and shape of the shielding blocks) for the three stages of radiation therapy of nasopharyngeal carcinomas. Stage 2-treatment fields proposed by CAVCAV, though not perfectly adapted to the patient, are mathematically (beam weights, beam directions, isocenter position) and geometrically (adaptation of fields and shape of blocks by virtual simulation) optimized.

Algorithms↗

PubMedDate not supplied

[Computer-assisted design in removable partial dentures. Expert system and software for framework tracing].

Stelligraph, a software program for designing the removable partial denture offers many possibilities in computer assisted technology. The design can be realized on any particular case, based on three different concepts. This software program can also provide on individual, manual and personalized design this offening complete freedom in the conception. This software program is an expert system in removable partial denture by providing the general practitioner with a rational design as well as clinical guidance for oral rehabilitation.

Denture Design↗

PubMed1994

MEDUSA: a fuzzy expert system for medical diagnosis of acute abdominal pain.

Even today, the diagnosis of acute abdominal pain represents a serious clinical problem. The medical knowledge in this field is characterized by uncertainty, imprecision and vagueness. This situation lends itself especially to be solved by the application of fuzzy logic. A fuzzy logic-based expert system for diagnostic decision support is presented (MEDUSA). The representation and application of uncertain and imprecise knowledge is realized by fuzzy sets and fuzzy relations. The hybrid concept of the system enables the integration of rule-based, heuristic and case-based reasoning on the basis of imprecise information. The central idea of the integration is to use case-based reasoning for the management of special cases, and rule-based reasoning for the representation of normal cases. The heuristic principle is ideally suited for making uncertain, hypothetical inferences on the basis of fuzzy data and fuzzy relations.

Abdomen, Acute↗

PubMed1989

Interaction with a 'sex-expert' system enhances attitudes towards computerized sex therapy.

The present experiment investigated whether a new rule-based expert system, Sexpert, designed to assess and treat sexual dysfunction would be positively evaluated by näive users. In a between groups design, four groups of eight students were randomly assigned to one of two experimental groups or one of two control groups. Ss in the experimental groups interacted with one of two versions of Sexpert. Ss in one control group filled out a questionnaire concerning their sexual functioning while Ss in the other interacted with a non-sex related computer program. Perceived dissimilarity to other established treatments for sexual dysfunction and semantic differential attitudes measures taken both before and after the experimental manipulations showed a significant positive shift in favor of computerized sex therapy for those Ss who interacted with either version of Sexpert but not for Ss in either of the control conditions.

Adult↗

PubMedDate not supplied

Structure Elucidator: a versatile expert system for molecular structure elucidation from 1D and 2D NMR data and molecular fragments.

StrucEluc is an expert system that allows the computer-assisted elucidation of chemical structures based on the inputs of a series of spectral data including 1D and 2D NMR and mass spectra. The system has been enabled to allow a chemist to utilize fragments stored in a fragment database as well as user-defined fragments submitted by the chemist in the structure elucidation process. The association of fragments in this way has been shown to dramatically speed up the process of structure generation from 2D NMR data and has helped to minimize or eliminate the need for user intervention thereby further enabling the vision of automated elucidation. The use of fragments has frequently transformed very difficult 2D NMR elucidation challenges into easily solvable tasks. A strategy to utilize molecular fragments has been developed and optimized based on specific challenging examples. This strategy will be described here using real world examples. Experience gained by solving more than 150 structure elucidation problems from a variety of literature sources is also reviewed in this work.

Journal Article↗

PubMedDate not supplied

[Main principles of rapid diagnosis and intensive care in emergency states: their realization in expert systems].

A retrospective analysis of 543 case histories over 1980-1990 in the town of Yekaterinburg and analysis of published data permitted the authors to single out the signs characterizing the most frequent syndromes requiring urgent intensive care. By either diagnostic value, these signs are distributed into main, accessory, and ruling out. An expert system has been created, making use of the productive-Freimont's approach to representing information on the basis of blurred multiplicities and ambiguous logics. The diagnosis was made by stages: first the main signs were analyzed, determining the severity of patient's status, then (after first aid was rendered) accessory and ruling out signs, which help make the diagnosis more precise. The system was tried in 231 patients, 102 of these with acute respiratory failure, 63 with acute hemodynamic insufficiency, and 66 with acute cerebral insufficiency. Primary diagnosis of the underlying syndrome was correct in 87-89% of cases, of the concomitant syndrome in 92-97%. Repeated evaluations (in 1-3 and 24 h) taking account of the time course of the symptoms and of the results of unsophisticated instrumental examinations increased the share of correct diagnoses to 92-96%.

Acute Disease↗

PubMed1993

Expert system for data acquisition to achieve a constant signal-to-noise ratio: application to imaging of DNA sequencing gels.

Normally, data acquisition and processing in chemical measurements are based on equal time (effort) for each data point. This leads to uneven signal-to-noise ratios (S/N) for each point. We present an expert system which decides in real time whether adequate S/N has been achieved for each point. If so, that data point will be omitted in all further acquisition or processing operations, greatly increasing the overall efficiency. The special case of analyzing DNA sequencing gels is tested with this scheme. A factor of 7.6 reduction in effort is demonstrated for a data set of 384 x 250 pixels, which normally would require 6 million sequential operations (64 frames).

Base Sequence↗

PubMed1995

An expert system to teach troubleshooting of common problems associated with the automated anesthesia recordkeeper.

Automated anesthesia recordkeepers have been used to monitor patients during surgery in up to 90% of cases at The Ohio State University. The record-keeping devices are complex and can be difficult to troubleshoot. The 1st-CLASS Fusion Program, an expert system "shell-program," has been programmed to allow the resident or nurse anesthetist to solve the two most common types of problems associated with the recordkeeper: printer problems and patient monitor problems. Use of this program allows the resident or nurse anesthetist to troubleshoot the recordkeeper quickly and accurately and promotes in the user a sense of competence and control over the technology.

Anesthesia↗