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 1,099 records · Page 61Linked to original sources

PubMed2006

How do experts recognize schizophrenia: the role of the disorganization symptom.

OBJECTIVE: Research on clinical reasoning has been useful in developing expert systems. These tools are based on Artificial Intelligence techniques which assist the physician in the diagnosis of complex diseases. The development of these systems is based on a cognitive model extracted through the identification of the clinical reasoning patterns applied by experts within the clinical decision-making context. This study describes the method of knowledge acquisition for the identification of the triggering symptoms used in the reasoning of three experts for the diagnosis of schizophrenia. METHOD: Three experts on schizophrenia, from two University centers in Sao Paulo, were interviewed and asked to identify and to represent the triggering symptoms for the diagnosis of schizophrenia according to the graph methodology. RESULTS: Graph methodology showed a remarkable disagreement on how the three experts established their diagnosis of schizophrenia. They differed in their choice of triggering-symptoms for the diagnosis of schizophrenia: disorganization, blunted affect and thought disturbances. CONCLUSIONS: The results indicate substantial differences between the experts as to their diagnostic reasoning patterns, probably under the influence of different theoretical tendencies. The disorganization symptom was considered to be the more appropriate to represent the heterogeneity of schizophrenia and also, to further develop an expert system for the diagnosis of schizophrenia.

Decision Support Systems, Clinical↗

PubMed1990

Artificial intelligence for medical decision making.

Artificial intelligence techniques find extensive applications in medical decision making and other aspects of health care. A number of successful expert systems have been developed in various disciplines of medicine. This paper gives an overview of expert system techniques, describes some practical systems, and discusses the relevance of such systems in clinical diagnosis and management of diseases.

Decision Making, Computer-Assisted↗

PubMed1992

Inference systems for automated image analysis.

The radiodiagnostic process is a complicated activity involving the integration of knowledge from low-level image features into more abstract, higher-order entities. This involves spatial and density information at a lower level and area and features at a higher level. The spatial density distribution in a radiographic image is not uniquely related to the three-dimensional structure of the object. Therefore, more information other than just first-order density characteristics of radiographs must be utilized to improve automated interpretation of the image. Prior knowledge of the size, shape and location of anatomical structures and pathognomic features is very useful for improving the process of computer-aided image analysis. Inference systems as used in expert systems can be applied to facilitate the integration of information obtained from the patient and the radiograph in the diagnostic process.

Expert Systems↗

PubMed1995

Issues of the Human Reliability Analysis in the Context of Probabilistic Safety Studies.

This article addresses methodological issues of the human reliability analysis (HRA) in the context of probabilistic safety studies. Several conventional HRA techniques, more often used for the evaluation of the human error probabilities (HEPs), have been classified. A taxonomy of human actions, failure events, and related factors is outlined in order to distinguish action phases, human behavior types and incorrect outputs (errors of omission or commission), error types (slips, lapses, and mistakes), and performance-shaping factors (PSFs) influencing the human performance. A tree is proposed to facilitate the selection of a specific method for the evaluation of human reliability with regard to attributes of the situation analyzed. A software system based on the expert system technology to facilitate and document PSA and HRA is outlined. At the end of the article some research challenges in the domain are discussed.

expert systems↗

PubMed1987

The expert teaching system: a new method for learning rhinoplasty using interactive computer graphics.

We have developed software that employs interactive computer graphics to simulate the surgical experience of rhinoplasty by allowing the surgeon to experiment within a model of nasal behavior. For any of three preoperative noses, the surgeon can choose and see the effects of dorsal resection, modification of nasal spine or caudal septum, alar cartilage resection, osteotomy, alar wedge resection, and a variety of nasal grafts. The available choices and views total nearly 3000 images, or approximately 200 different surgical solutions. The surgeon can get textual analysis at any time or see accelerated healing to the projected nasal appearance at 1 year. We believe that the ability to experiment without risk, to safely learn the biological laws governing nasal behavior, should augment the development of surgical judgement in rhinoplasty.

Computer Graphics↗

PubMed1989

The use of inference strategies in the differential diagnosis of microcytic anemia.

A new expert system developed on a Macintosh personal computer using a commercially available artificial intelligence shell was compared with four different discriminant functions (DFs) for the differentiation of microcytic anemia into etiologic categories. Several databases were used with a different composition but all contained at least some samples from thalassemic individuals and from patients with iron deficiency anemia. The DFs analyzed were those proposed by England and Fraser, Green and colleagues, Mentzer, and by Shine and Lal. None of the databases performed satisfactorily when used singly, whereas very high false-positive rates were obtained by one of them. The diagnostic efficiency was somewhat improved by combining several DFs. An expert system using an artificial intelligence "shell" with an "interference engine" was developed using cluster analysis and a set of learning examples. The input necessary for the system to achieve a conclusion consists of MCV, RBC, and RDW as well as a statement as to whether the patient has anemia. Based upon the values of these parameters, the expert system will give an "advice" regarding the probabilities for thalassemia, iron deficiency, and/or other probabilities such as previous transfusions, anemia of chronic disease, laboratory error, etc. In a prospective trial, the system functioned with an accuracy of better than 85%.

Anemia, Hypochromic↗

PubMed1997

IDIS-KS: an intelligent drug information system as a knowledge server.

Expert System technology in combination with other technologies such as Networks and Data Base systems can prove to be a valuable tool for medical experts, providing decision support and information services, and therefore facilitating and improving their everyday tasks. IDIS-KS described in this paper, is an consultation and information system dedicated to deliver drug information and suggestions about possible treatments to medical practitioners in the National area of Greece.

Computer Communication Networks↗

PubMedDate not supplied

Identifying the residential location of rapists.

The spatial offence behaviour of 45 British serial rapists was examined in order to generate a predictive model, of use to criminal investigators. Two alternative hypotheses were explored. One predicted that rapists would commute into an area to carry out their offence. The second predicted that they would "maraud" out from a fixed location. Of the 45 offenders, 39 fitted the "maurader" hypothesis. However, the area covered by this model was an average of nearly 180 square miles. A second complementary theory, developed from facets of offenders' backgrounds, was therefore used to refine the predictions of distance travelled to and between offences. This enabled the size of the residential zone predicted from the marauder model to be reduced to a mean area of just over ten square miles. Tests of these models, combined into a small scale expert system, predicted the correct area for 82% of the cases. Suggestions for the further development of this expert system are discussed.

Adolescent↗

PubMed1993

Graphical knowledge presentation in a MUMPS-based decision-support system.

Conventional knowledge-based medical expert systems present information and elicit responses in the form of text. PHOENIX, a decision-support system designed to help non-radiologist physicians select diagnostic imaging procedures, offers a graphical user interface. The system constructs and displays algorithms, or flowcharts, from the rules in its knowledge base. Users can view the flowcharts and move through them by answering questions at branch points. The system provides detailed textual explanations of the rules and descriptions of the imaging procedures. The system is written in MUMPS, a common programming language for biomedical information systems, and is easily incorporated into clinical computer systems.

Algorithms↗

PubMedDate not supplied

Clinical problem solving--the role of expert laboratory systems.

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.

Clinical Laboratory Information Systems↗

PubMedDate not supplied

Real-time flexible preventive maintenance scheduling.

There are still obstacles to overcome as we enter the programming phase of this project. We envision an automated system, similar to an expert system, that performs the interval/history analysis and makes the changes. Initially a field will need to be added to the inventory to denote whether a device belongs to one of the previously described groups that are exempt from interval changes. An intermediate step will be the formatting of a periodic report showing equipment that meets the change criteria as described in the two rules. For now, the actual changes would be reviewed and made by our management and technical staff. This report would be retained as documentation of the basis for each change, for our own benefit and to meet JCAHO requirements. We are still discussing whether the repair count should include all repairs (user error, abuse, unpredictable failure, etc.) or just those that are "significant and preventable" and could have been averted by PM. This is perhaps a question whose answer might vary from hospital to hospital, depending upon size and patient mix. With more emphasis being placed on process outcomes, on quality of work, and on getting the most benefit for our efforts, we believe our flexible, real-time PM scheduling program is a major step in the right direction. It is outcome-driven and it focuses resources where they are needed the most.

Appointments and Schedules↗

PubMedDate not supplied

An overall strategy for the testing of chemicals for human hazard and risk assessment under the EU REACH system.

In its White Paper, "Strategy for a Future Chemicals Policy," published in 2001, the European Commission (EC) proposed the REACH (Registration, Evaluation and Authorisation of CHemicals) system to deal with both existing and new chemical substances. This system is based on a top-down approach to toxicity testing, in which the degree of toxicity information required is dictated primarily by production volume (tonnage). If testing is to be based on traditional methods, very large numbers of laboratory animals could be needed in response to the REACH system, causing ethical, scientific and logistical problems that would be incompatible with the time-schedule envisaged for testing. The EC has emphasised the need to minimise animal use, but has failed to produce a comprehensive strategy for doing so. The present document provides an overall scheme for predictive toxicity testing, whereby the non-animal methods identified and discussed in a recent and comprehensive ECVAM document, could be used in a tiered approach to provide a rapid and scientifically justified basis for the risk assessment of chemicals for their toxic effects in humans. The scheme starts with a preliminary risk assessment process (involving available information on hazard and exposure), followed by testing, based on physicochemical properties and (Q)SAR approaches. (Q)SAR analyses are used in conjunction with expert system and biokinetic modelling, and information on metabolism and identification of the principal metabolites in humans. The resulting information is then combined with production levels and patterns of use to assess potential human exposure. The nature and extent of any further testing should be based strictly on the need to fill essential information gaps in order to generate adequate risk assessments, and should rely on non-animal methods, as far as possible. The scheme also includes a feedback loop, so that new information is used to improve the predictivity of computational expert systems. Several recommendations are made, the most important of which is that the European Union (EU) should actively promote the improvement and validation of (Q)SAR models and expert systems, and computer-based methods for biokinetic modelling, since these offer the most realistic and most economical solution to the need to test large numbers of chemicals.

Cytochrome P-450 Enzyme System↗

PubMed2006

An overall strategy for the testing of chemicals for human hazard and risk assessment under the EU REACH system.

In its White Paper, Strategy for a Future Chemicals Policy, published in 2001, the European Commission (EC) proposed the REACH (Registration, Evaluation and Authorisation of CHemicals) system to deal with both existing and new chemical substances. This system is based on a top-down approach to toxicity testing, in which the degree of toxicity information required is dictated primarily by production volume (tonnage). If testing is to be based on traditional methods, very large numbers of laboratory animals could be needed in response to the REACH system, causing ethical, scientific and logistical problems that would be incompatible with the time-schedule envisaged for testing. The EC has emphasised the need to minimise animal use, but has failed to produce a comprehensive strategy for doing so. The present document provides an overall scheme for predictive toxicity testing, whereby the non-animal methods identified and discussed in a recent and comprehensive ECVAM document, could be used in a tiered approach to provide a rapid and scientifically justified basis for the risk assessment of chemicals for their toxic effects in humans. The scheme starts with a preliminary risk assessment process (involving available information on hazard and exposure), followed by testing, based on physicochemical properties and (Q)SAR approaches. (Q)SAR analyses are used in conjunction with expert system and biokinetic modelling, and information on metabolism and identification of the principal metabolites in humans. The resulting information is then combined with production levels and patterns of use to assess potential human exposure. The nature and extent of any further testing should be based strictly on the need to fill essential information gaps in order to generate adequate risk assessments, and should rely on non-animal methods, as far as possible. The scheme also includes a feedback loop, so that new information is used to improve the predictivity of computational expert systems. Several recommendations are made, the most important of which is that the European Union (EU) should actively promote the improvement and validation of (Q)SAR models and expert systems, and computer-based methods for biokinetic modelling, since these offer the most realistic and most economical solution to the need to test large numbers of chemicals.

Journal Article↗

PubMed1990

NEOANEMIA: a knowledge-based system emulating diagnostic reasoning.

Medical diagnosis can be modeled in terms of the classical notions of abduction, deduction, and induction. Abduction is making a preliminary guess that allows one to establish a set of plausible diagnostic hypotheses, followed by deduction for exploring their consequences and induction for testing the hypotheses with available patient data or for planning the acquisition of new data. Such a description of diagnostic reasoning at a knowledge level helps the construction of an expert system by fashioning the adopted expert system building tool to reflect the structure of the problem rather than by fitting the problem to the tool. To this aim, reasoning strategies need to be represented abstractly, separate from medical facts and relations, to make the design more transparent and explainable.

Anemia↗

PubMed2001

Improved process control alarm operation.

Alarms are the main connection from the automation to the operator, when addressing process operation outside of its normal function. They are often as much a source of operator overload and consternation as help. Better engineering of the relative role of the operator and automation would materially help overcome the difficulties. Expert systems have been proposed as a solution. But Expert systems are really another form of automation. There remains that aspect of the alarms, which must address our inability to cover and understand a possibly larger domain of the operation not appropriate to traditional controls or present-day automation. Appropriate tools for this domain must support operator discretion and initiative. The paper suggests a set of such general, computer science based, tools requiring only the most basic configuration. They are viewed as implemented on top of those properly detailed alarm displays and interlocks, which reflect the more formal plant operating policies. They include: (a) Various forms of alarm logging and trending; (b) Short, automatically generated, word summaries of alarm activity, which allow low level data to propagate to the highest levels, including: one word and priority summaries; (c) Causal alarm pattern analyses that help the operator to predict or diagnose alarm behavior; (d) Automatic adaptation of alarms and alarm limits to varying process situations; (e) Uniform use of alarm policies to simplify alarm configuration.

Journal Article↗

PubMed1996

May we support your decision?

Expert systems to support medical decision-making have so far achieved few successes. Current technical developments, however, may overcome some of the limitations. Although there are several theoretical currents in medical artificial intelligence, there are signs of them converging. Meanwhile, decision support systems, which set themselves more modest goals than replicating or improving on clinicians' expertise, have come into routine use in places where an adequate electronic patient record exists. They may also be finding a wider role, assisting in the implementation of clinical practice guidelines. There is, however, still much uncertainty about the kinds of decision support that doctors and other health care professionals are likely to want or accept.

Bayes Theorem↗

PubMed2002

Nearest neighbour classification of otoneurological data.

We studied the nearest neighbour classification of patient cases with benign positional vertigo, Meniere's disease, sudden deafness, traumatic vertigo, vestibular neuritis, and vestibular schwannoma. The classification results were compared to the inference results obtained by an otoneurological expert system ONE whose inference mechanism somewhat resembles the classical nearest neighbour method. With respect to the predictive accuracy, the classification results of these two systems agreed. The best predictive accuracy for the expert system ONE was 79.7% and for the nearest neighbour method 80.5%. However, differences in the true positive rates for sudden deafness, traumatic vertigo, vestibular neuritis, and vestibular schwannoma were found. The nearest neighbour classification results will be used in the refinement of ONE's knowledge base.

Data Collection↗

PubMed1987

Artificial intelligence--its use in nephrology.

Artificial intelligence techniques and expert systems are graduating from research laboratories to enter many human domains of activities. However, initial expectations of the seventies have been transformed with time to a more sober reality. Starting from examples in nephrology, this paper tries to give a balanced view of this new technology. Justification, indication and limitation of present expert systems are discussed as regards their possible goals. The respective roles of the experts and knowledge engineers are described. The need to integrate the artificial intelligence approach into present patient database management systems in order to build up expert database systems is evaluated.

Database Management Systems↗