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 595 records · Page 33Linked to original sources
PubMedDate not supplied

Design and development of an expert system to assist diagnosis and treatment of chronic hepatitis using traditional Chinese medicine.

The treatment of chronic hepatitis with traditional Chinese medicine shows good therapeutic effectiveness in clinical practice. Since the process for the diagnosis in Chinese medicine is quite different from that of modern Western medicine, many physicians of modern medicine cannot practise it readily and effectively. We describe an expert system designed to support physicians who may not be familiar with the domain of traditional Chinese medicine, to treat chronic hepatitis by using Chinese medicine. This system was developed by logic programming language PROLOG, where the knowledge of Chinese medicine is represented in a semantic network structure and the reasoning strategy is based on the hypothesize-and-test approach. This system can guide the user to collect patient information easily, and based on those items of information this leads to the possible diagnosis and treatment for chronic hepatitis using Chinese medicine. The results of this system are compared with 40 patient case records and analysed by a specialist in Chinese medicine.

Artificial Intelligence↗
PubMed1992

Computer assisted development of diagnostic expert systems. A domain-independent package (EMPTY) for acquisition and use of expert's medical knowledge.

The package EMPTY has been developed with the aim of providing a tool based on well assessed methodological principles which can support both the organisation and use of medical knowledge for diagnostic and educational purposes. EMPTY is domain-independent and results in two interactive programs: ASK guides the acquisition of medical knowledge and RUN supports medical decision-making and provides facilities for medical education. The knowledge bases developed on ASK have a standard formal structure: they include taxonomies, definitions and descriptions of diseases, clinical findings and investigations; production rules for activation and refinement of diagnostic hypotheses; frame-like profiles of diseases; and quantitative criteria for scoring the clinical evidence on the base of available data.

Computer-Assisted Instruction↗
PubMed1996

Usefulness of a computerized expert system associated with systematic O-serotyping for the early detection of outbreaks of hospital acquired infections and for the presumptive antibiotic therapy of Pseudomonas aeruginosa infections.

Over a four-year period, the systematic O-serotyping of all Pseudomonas aeruginosa isolated in Hôpital de Rodez associated with the use of a computerized expert system, facilitated the early detection of two outbreaks of nosocomial infections with multiresistant serotype O:11 and multiresistant serotype O:12 P. aeruginosa respectively involving ten patients over 16 months and six patients over six months. Over this four-year period, serotype O:12 represented 14% of 404 clinical isolates of P. aeruginosa, and most isolates of this serotype were resistant to multiple antibiotics. Combination experiments showed that fosfomycin/amikacin together were active against 86% of O:12 isolates. Fosfomycin/amikacin might be considered as a therapeutic alternative to ceftazime/amikacin for the presumptive antipseudomonal therapy of serotype O:12 infections.

4-Quinolones↗
PubMed2006

The EEG assessment of low-grade hepatic encephalopathy: comparison of an artificial neural network-expert system (ANNES) based evaluation with visual EEG readings and EEG spectral analysis.

OBJECTIVE: The EEG provides an objective staging of hepatic encephalopathy (HE), but its interpretation may be biased by inter-observer variability. This study aims at comparing an entirely automatic EEG classification of HE based on an artificial neural network-expert system procedure (ANNES) with visual and spectral analysis based EEG classifications. METHODS: Two hundred and thirty-eight consecutive cirrhotic patients underwent closed-eye EEG. They were followed up for up to one-year to detect bouts of overt HE and death. The EEG was classified by ANNES, qualitative visual reading, main basic rhythm frequency and spectral analysis. The classifications were assessed on the basis of: (i) match with liver function, (ii) prognostic value and (iii) repeatability. RESULTS: All classifications were found to be related to the severity of liver failure, with cognitive findings and a history of previous bouts of HE. All of them had prognostic value on the occurrence of overt HE and on survival. The ANNES based classification was more repeatable than the qualitative visual one, and had the advantage of detecting low power EEG, but its efficiency in analyzing low-grade alterations was questionable. CONCLUSIONS: An entirely automatic - ANNES based - EEG classification of HE can improve the repeatability of EEG assessment, but further improvement of the device is required to classify mild alterations. SIGNIFICANCE: The ANNES based EEG grading of HE needs further improvements to be recommended in clinical practice, but it is already sufficient for detecting normal and clearly altered EEG tracings.

Electroencephalography↗
PubMed1987

Methuselah--an expert system for diagnosis in geriatric psychiatry.

This report is based on the notion that criteria for "successful" diagnosis differ for different medical specialties. Diagnostic judgement in highly unstructured task domains is best characterized as clinical problem formulation with pragmatic implications for interventions. This concept is illustrated by the implementation of a computer-based diagnostic expert system for geriatric psychiatry. The program begins with guiding the patient's interview by the clinician. This is followed by the diagnostic process which is conducted in three steps. In the first step, candidate syndromes of disease states are identified by matching the presenting complaints with symptom lists of clinical syndromes. In the second step, the candidate syndromes serve as the organizers for gathering additional patient data (e.g., information from referral source and past illnesses) to seek constellations of findings which form a coherent clinical context. In this phase, the program can also prompt the clinician to obtain additional information from the patient or other available sources to resolve conflicts or, if necessary, invoke the concurrent presence of two independent syndromes to attain convergence (i.e., minimize the number of unexplained findings). In a final step, the syndromes with highest credence value, reflected by the number of linkages to patient data, are sharpened to specific diagnostic formulations. This is accomplished by frames of diagnoses which are associated with each syndrome. Once again, the patient data can be consulted to achieve optimal matches. A summary statement to the clinician lists the essential supporting evidence for the chosen diagnosis and can communicate alternatives or unresolved issues for clarifying interventions. Although no decisive evidence is available, informal observations of clinicians support the notion that clinical reasoning in highly unstructured domains is largely contextual and seeks apprehension of "gestalts" in successive steps. The diagnostic program of this report aims at simulating this process.

Aged↗
PubMed1994

[Expert systems in medicine: possible uses in anesthesia].

The euphoric assumption that powerful computers fed with sophisticated software programmes may serve as a substitute for human knowledge and decision making has been replaced by a more realistic concept of how computers may help in collecting data and their interpretation on the basis of human knowledge and experience. The computer is now used as a dedicated tool to support man in overtaking cumbersome and monotonous processes and tedious calculations. Running 24 hours a day, a specific feature of the computer is that depending on unequivocal software programmes it does neither forget or alter commands and information. Computer programmes imitating human thinking and information processing are called expert or knowledge based systems. These are especially useful when multiple possible combinations of data make a given task very complex. This review presents several systems used in different medical disciplines to describe fundamental ideas, different problem-solving methods, techniques and possible working fields including anaesthesia. It is made clear why computers have found widespread use in all administrative areas. In contrast, no system comparable in potency has been developed for use in clinical medicine in spite of 25 years of research in expert systems. This review starts with a definition of expert knowledge and the appropriate transformation of this knowledge to the computer. In addition, a general survey about the structure of expert systems and a state of the art in some current problem solving methods is given. Additional aspects and restrictions including technical, psychological and legal problems which seem to be unimportant from the outside but are essential for the development of expert systems are presented.

Anesthesia↗
PubMed1990

Fuzzy Logic for medical expert systems.

The use of linguistic approximation enables knowledge to be represented in a more meaningful way and this is especially important in medical domain as it involves a lot of subjective decision making; Fuzzy Logic, introduced by Zadeh, has the ability to represent this imprecise expression. In this paper, an alternative approach of Fuzzy Logic in handling the approximate reasoning in expert systems will be described. The approach does not use the General Modus Ponen on the compositional rule of inference, but instead it uses a collection of rules to specify the properties of the inference (in making decision). An example of medical domain is described as its application.

Diagnosis, Computer-Assisted↗
PubMed1987

Pharmacokinetics and expert systems as aids for risk assessment in reproductive toxicology.

A minimal approach to risk assessment in reproductive toxicology involves four components: hazard identification, hazard characterization, exposure characterization, and risk characterization. In practice, risk assessment in reproductive toxicology has been reduced to arbitrary safety factors or mathematical models of the dose-response relationship. These approaches obscure biological differences across species rather than using this important and frequently accessible information. Two approaches that are formally capable of using biologically relevant information (pharmacokinetics and expert system shells) are explored as aids to risk assessment in reproductive toxicology.

Animals↗
PubMed1988

An expert system for the early detection of melanoma using knowledge-based image analysis.

Melanoma is the most lethal skin cancer; however, nearly all patients can be saved and cured by early detection and prompt surgical treatment. It has been demonstrated that the major diagnostic and prognostic parameters of melanoma are the vertical thickness, three-dimensional (3D) size and shape, and color of the lesion. The other characteristic features of early melanoma are irregularities in the boundary of the lesion and the appearance of nonuniform pigmentation (with a variety of color). During early stages of development of the melanoma, the changes in these parameters are very difficult to assess since no good tool exists for measuring them in situ and analyzing them for malignancy. A novel optical instrument called the "Nevoscope" has been developed to obtain multiple views of the transilluminated skin lesion from several angles. These views have been used to measure the thickness and 3D size of the skin lesion without excision. A knowledge-based image analysis and interpretation system is being developed to analyze images of the skin lesion for a set of diagnostic and prognostic features: thickness, 3D size, color and margin, boundary and surface characteristics. This analysis combined with the patient's history, such as occurrence of melanoma or dysplastic nevi in the family, life style, skin type, etc., is used by the knowledge-based expert system to detect early or potentially malignant lesions. The diagnostic and prognostic knowledge bases for the early detection of melanoma are being developed with the help of expert dermatologists and published case studies.

Algorithms↗
PubMed1988

Intelligent computer-based assessment and psychotherapy. An expert system for sexual dysfunction.

New and converging developments in the areas of artificial intelligence, intelligent tutoring systems, and cognitive therapy have made possible a new approach to computer-assisted assessment and psychotherapy. This new approach combines the capacity for intelligent therapeutic dialogue with the presentation of individualized therapeutic interventions. Previous attempts at computerized psychotherapy are reviewed to highlight a newly developed rule-based expert system, Sexpert, which assesses and treats sexual dysfunction. Preliminary observations concerning couples' reaction to and acceptance of Sexpert are presented.

Artificial Intelligence↗
PubMed1994

Automated construction of genetic linkage maps using an expert system (MultiMap): a human genome linkage map.

High-resolution genetic linkage maps are indispensable for positional cloning of disease genes. Current procedures for map construction, although aided considerably by many existing computer programs, require extensive user-intervention at each of many repetitive steps. This is time consuming, labour intensive and increases the chance of error. We have developed an expert system computer program, MultiMap, which automates this step-by-step procedure. MultiMap is based on a novel map construction algorithm and allows investigator control of marker locus characteristics, such as informativeness, scorability or distance to nearest neighbours. We used MultiMap to construct a human genetic map at an average resolution of 6 cM, using published genotypes at 1266 microsatellite markers, and further extended this map by adding 397 VNTR and polymorphic gene markers.

Algorithms↗
PubMedDate not supplied

Development of an expert system for haemodynamic monitoring: computerized symbolization of on-line monitoring data.

The development of intelligent alarm systems for intensive care benefits from the transformation of data from a quantitative to a qualitative mode. We constructed a computerized algorithm for the symbolization of on-line monitoring data of heart rate, systemic arterial, pulmonary arterial and central venous pressures, as well as central and peripheral temperatures. We tested the ability of the algorithm to symbolize the levels of the parameters and to detect significant long-term trends in ten adult patients admitted to the intensive care unit after cardiac surgery. The estimations of an experienced clinician were taken as the 'gold standard'. The symbolization of the levels of the monitored parameters was in agreement with the clinician in 99.4% of the estimations. The algorithm detected 93.0% of the trends correctly and also estimated their reliability. The clinician considered its estimations to be accurate in 96.2% of cases. On the other hand, the clinician considered unreliable 2.4% of all the trends detected and classified as reliable by the algorithm. The computerized algorithm for the symbolization of real-time monitoring data performed efficiently enough for its further use in expert systems for intelligent monitoring.

Algorithms↗
PubMed1996

Implementation in an expert system of a selection rationale for purification processes for recombinant proteins.

This work presents the development of an expert system for selecting the best sequence of operations for the downstream processing of proteins. The core of the discussion is how the rationale for the selection of a sequence of processes for purification was developed. It consists of a system that compares extensive data on the product to be purified and on the main contaminant proteins found in the expression system to be used (e.g. E. coli). Definitions of parameters that translate (i) the rules employed in separations and (ii) the selection between high-resolution purification operations (chromatography) using the databases of properties of proteins in a rational quantitative manner to guide the selection are described. After each separation step, there is a reduction in the amount of contaminant proteins. The amount of each "contaminant" eliminated is determined using an algorithm developed for this purpose, based on simplified interpretations of chromatograms, that indicates the new concentrations after each step. The number of steps must be sufficient to achieve a defined level of purity. The comparison of the concentration of the product after the separation with the defined level of purity indicates whether an additional step is necessary.

Bacterial Proteins↗
PubMed1989

Automatic speech recognition--can it improve the man-machine interface in medical expert systems?

Computer-aided medical diagnosis has existed for two decades, but has not yet attained widespread acceptance among physicians. It is proposed that automatic speech recognition may be a significant factor in the eventual acceptance of the technology by the medical profession. The current state-of-the-art of automatic speech recognition is briefly surveyed, and problems with the technology are discussed. A potential natural language interface with DIAG, an expert system for aiding in dermatologic diagnosis, is described. A system that has been developed for accepting input of body parts in freestyle format is presented as a prototype for a natural language interface with an automatic speech recognition device.

Diagnosis, Computer-Assisted↗
PubMed1995

A scheme for the interpretation of primary and secondary disturbances of plasma and urinary amino acid profiles. A possible way to an expert system.

A general scheme for the interpretation of primary and secondary abnormalities of plasma and urine amino acid concentrations is described. The key steps of this scheme are: analytical assessment of the measurements, comparison of results obtained with the reference values expressed in absolute and/or relative concentrations and identification of abnormally increased ninhydrin-positive compounds. The interpretation of results takes account of the various abnormalities induced by drugs or diet. The origins of these abnormalities are ordered by their frequency. A part of the proposed scheme is now computerized as the first step in the development of an expert system.

Amino Acid Metabolism, Inborn Errors↗
PubMed1989

On the way to expert systems. Comparing DSM-III computer diagnoses with CATEGO (ICD) diagnoses in depressive and schizophrenic patients.

Operationalized diagnostics deal with the standardized assessment of psychiatric symptoms as well as diagnostic criteria. As a diagnostic system based on criteria, the DSM-III was chosen to identify operationalized diagnoses based on the Present State Examination (PSE-9) and some additional DSM-III specific items. By relating PSE symptoms to the diagnostic criteria of DSM-III, an easily applicable expert system leading to DSM-III diagnoses was developed. In two samples of 30 schizophrenic and 51 depressive patients the DSM-III computer diagnoses are contrasted with the ICD-8 diagnoses of the PSE/CATEGO system. In defining a "case", only minimal differences between the two computer programs were found. In the sample of schizophrenics, CATEGO led to 114 (81%) diagnoses and the DSM-III program to 112 (79%) diagnoses; for the depressive patients 43% cases were identified by CATEGO and 45% by the DSM-III algorithm. Comparing the diagnosis of "acute schizophrenic disorders", both programs arrived at similar percentages. (CATEGO: 51%; DSM-III: 57%). However, CATEGO is limited to two different subtypes (295.2 and 295.3), whereas the DSM-III program covers the total range of possible schizophrenic subtypes. Furthermore, the DSM-III program identified residual subtypes of schizophrenia in 23% of the diagnostic decisions. In the short-term course of the schizophrenic patients, CATEGO identified 27%-43% with affective diagnoses with high stability per cross-section. Using the DSM-III algorithm affective diagnoses were rather rare (maximum of 17%), marking unstable changes from acute to residual states of the psychosis.(ABSTRACT TRUNCATED AT 250 WORDS)

Algorithms↗