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 37 records · Page 2Linked to original sources
PubMed1991

Some observations on the development of a 'scoring system' in an expert system for prediction of ovulation.

As part of the construction of an expert system for the diagnosis of infertility we have developed a scoring system for the identification of conditions which can interfere with ovulation. The scores were obtained from a group of clinicians, and the arithmetic means of these scores were used in the actual system. Correlation between the scores obtained from individual clinicians was very poor (r = 0.345 +/- 0.134). Correlation improved when groups of clinicians were compared. Thus scores derived from a group of clinicians will reflect more reliably the 'general medical opinion'. Scores derived from the opinion of clinicians should be regarded with caution until probabilities or weighting factors derived from real clinical data become available.

Expert Systems↗
PubMed1990

Expertise: the basis for expert system development.

Expert systems in nursing are developed with traditional knowledge engineering techniques. These techniques focus on the behavior and logic of the expert, not qualities of expertise. Expertise has been described but not explained. This article proposes a theoretical framework for the study of expertise that can be used to facilitate the development of expert systems.

Clinical Competence↗
PubMed1992

[Contribution of expert systems in clinical practice: apropos of the Penelope experience, an expert system in assisted diagnosis and therapy of ovarian adenocarcinoma].

An expert system (ES) for Diagnosis and Therapy of ovarian adenocarcinoma has been developed at the Institut Gustave-Roussy. From surgical and histological results, clinical examination and additional investigative reports, the system presents a synthesis and then determines the stage of the disease. The system than proposes therapeutic indications adapted to the characteristics of the illness and of the patient, and edits a report at the end of the ES consultation. This experience allowed us to specify the field of ES applications in oncology. As tools for diagnosis and therapy, they cannot act as a substitute for the know-how of the physician, as too many medical decisions remain difficult to formalize in the ES. On the other hand the use of artificial intelligence techniques appears to be useful for establishing coherent data bases, which are necessary pre-requisites for clinical research in oncology. The integration of the system in the Hospital Information System is the guarantee of its use in current clinical practice.

Adenocarcinoma↗
PubMed1997

A comparative study of nursing diagnosis systems using neural networks and expert systems.

With the growing need in the field, the application of computers in nursing has been frequently studied with the aim of improving the quality of nursing care in Korea. However, the development of useful clinical programs has not received adequate attention. The aim of this study is to compare two Nursing Diagnosis Systems-one involving a Neural Network and one involving an Expert System. The simulated output of each Nursing Diagnosis System was compared with the judgement of the researcher and of two professors of nursing. The misdiagnosis rate of the Nursing Diagnosis System using the Neural Network was nine percent, while the Nursing Diagnosis System using Expert System showed consistency with the three experts in every aspect. The result of this study demonstrated the feasibility of the use of an expert system based Nursing Diagnosis System as another nursing tool.

Diagnosis, Computer-Assisted↗
PubMed1994

Image analysis and categorization of ventilation-perfusion scans for the diagnosis of pulmonary embolism using an expert system.

UNLABELLED: An expert system was developed that interprets ventilation-perfusion lung scans. The use of such scans for suspected pulmonary embolism is ideal for computer-assisted diagnosis by expert systems. The data are digital, only a single disease entity is diagnosed or excluded, and well-established diagnostic criteria already exist for visual interpretation that can be easily integrated into an expert system. METHODS: This expert system is divided into two modules. The first module is responsible for image analysis. Analysis was performed on the eight standard perfusion images and on single-breath, equilibrium and 3-min washout ventilation images. Each image was analyzed for the presence of regional perfusion or ventilation defects, as determined by pixel values that fell 2.2 s.d. below the mean (or above the mean in the case of washout images) compared with a database of normal studies. The defect size, segment involved and number of defects were determined. Ventilation and perfusion images were then compared to determine whether defects were matched or mismatched. The second program module applied the modified Biello's criteria to the data and categorized the scan as normal to low, intermediate or high probability. RESULTS: A total of 80 patients were prospectively studied. An 81% (65 of 80) correlation was obtained when the results of the expert system were compared with visual interpretations made by three experienced nuclear medicine physicians. CONCLUSION: This study shows that the interpretation of ventilation-perfusion lung scans by an expert system is possible. The technique holds the promise of reducing interobserver variability and assisting less experienced observers in the interpretation of such scans.

Expert Systems↗
PubMed2001

Potential impact of the VITEK 2 system and the Advanced Expert System on the clinical laboratory of a university-based hospital.

A study was designed to assess the impact of the VITEK 2 automated system and the Advanced Expert System (AES) on the clinical laboratory of a typical university-based hospital. A total of 259 consecutive, nonduplicate isolates of Enterobacteriaceae members, Pseudomonas aeruginosa, and Staphylococcus aureus were collected and tested by the VITEK 2 system for identification and antimicrobial susceptibility testing, and the results were analyzed by the AES. The results were also analyzed by a human expert and compared to the AES analyses. Among the 259 isolates included in this study, 245 (94.6%) were definitively identified by VITEK 2, requiring little input from laboratory staff. For 194 (74.9%) isolates, no inconsistencies between the identification of the strain and the antimicrobial susceptibility determined by VITEK 2 were detected by the AES. Thus, no input from laboratory staff was required for these strains. The AES suggested one or more corrections to results obtained with 65 strains to remove inconsistencies. The human expert thought that most of these corrections were appropriate and that some resulted from a failure of the VITEK 2 system to detect certain forms of resistance. Antimicrobial phenotypes assigned to the strains by the AES for beta-lactams, aminoglycosides, quinolones, macrolides, tetracyclines, and glycopeptides were similar to those assigned by the human expert for 95.7 to 100% of strains. These results indicate that the VITEK 2 system and AES can provide accurate information in tests for most of the clinical isolates examined and remove the need for human analysis of results for many. Certain problems were identified in the study that should be remediable with further work on the software supporting the AES.

Anti-Bacterial Agents↗
PubMed1987

Computerized decision support: beyond expert systems.

While expert systems hold great promise for decision support, currently available software packages, called decision-modelling programs, provide clinicians with analytical assistance for resolving difficult decisions. This paper describes the two general classes of computerized decision-modelling programs (decision tree analysis and multiple criteria models), and illustrates the descriptions with examples of commercially available packages. Decision tree analysis is useful when the selection of a present action (for example, a treatment) depends on some outcome in the future (i.e. the occurrence of side effects). Multiple criteria models help clinicians when the choice of action depends on satisfying many criteria simultaneously.

Artificial Intelligence↗
PubMed1999

[Expert systems in pulmonology].

Expert systems are software systems that can successfully compare to human experts. Their purpose is mostly advisory. Besides, they give explanation and advices to human experts when performing certain tasks. They are intelligent information systems, and are capable to explain and justify their conclusions. Knowledge systems are smaller software systems, and are usually less successful than human experts. Main reasons for expert systems development in medicine are: need for justification of decisions, need for enhancing performances in many uncertain relations; need for explaining of decision making process++ etc. One of the reasons of developing knowledge-based systems was that conventional statistic formalisms have not provided satisfactory solutions in medical decision making (MDM). Also, today, the relations between cases and conclusions are not universally valid. So, few causes can provide the same conclusion. Besides, data are not necessarily absolutely accurate. The area of applying expert systems is very wide: diagnosis, prognosis, education, managing etc. Basic structure of expert system consists of: knowledge, data base, inferring mechanism, explaining mechanism and user-interface. In this paper we presented several expert systems which are actually used in practice, especially in internal disciplines: Internist, Mycin, Onkocyn, DXplain.

Expert Systems↗
PubMed1999

[Expert systems in medicine].

Expert systems are software systems developed using different techniques of artificial intelligence that can act parallel to the "human" experts. The main role is consultative These are intelligent information systems that use more then 2000 different rules and that are capable to explain their decisions. Databases of such systems can contain huge number of data about different diseases and therapy modalities. In development of Medical Expert systems the rule of human experts is crucial. The teams of such experts are developing expert system considering the changes in medicine. Several modes of work are available. Consultation mode is used in cases when the diagnosis and treatment is uncertain. The human enter data about symptoms and signs of some medical disorder and computer creates a list of possible diagnosis and additional diagnostic test. Therapy for condition is also suggested. Simulation mode can simulate virtual patient and allows students and doctors to learn mode about some medical conditions. Some expert system as HEPAT can make "Decision Tree" for new-born jaundice. Similar expert system will be available in future for other fields in medicine. Some of expert systems are described in article.

Expert Systems↗
PubMedDate not supplied

Knowledge engineering of expert systems for nursing.

Expert system technology and its derivatives will be core components of future health care information systems. Nursing presently lacks sufficient knowledge engineering resources to develop and implement expert system technology productively. In this article, knowledge engineering and its implications for nursing are described.

Artificial Intelligence↗
PubMed1987

Human versus machine: a comparison of a computer 'expert system' with human experts in the diagnosis of vaginal discharge.

A model system has been designed which generates 'cases' of vaginal discharge. Each such case is presented to a human for diagnosis, and this is then compared with a computer diagnosis using two forms of Bayes' theorem. Six subjects (2 medical; 4 non-medical) participated in the trial and each examined 100 successive 'cases'. When the humans had forewarning of the trial and full access to the knowledge-base their performance was superior to that of Bayes' theorem using positive features only and equivalent to that using both positive and negative features. When the trial was repeated without forewarning the human performance was markedly inferior to that of the machine. It is concluded: that human and computer-aided diagnosis can be of approximately equal efficiency for complex and non-definitive data; that the imperfections of human memory give an obvious potential advantage to the machine in this type of situation.

Computer Simulation↗
PubMedDate not supplied

Use of neural networks in medical expert systems.

A prototype Expert System, able to assist gynaecologists in diagnosing and classifying cancer of the neck of the womb is designed and implemented. The system is implemented using NeuroShell, an Expert System Building Tool, based on Neural Networks. A neural model, which predicts the possible outcomes of colposcopy and biopsy, based on Pap test results, as well as on information from the patient record, is developed. Such a system is a very useful tool for physicians both as a training tool as well as a forecasting system, while it also has the capability of incorporating new knowledge, provided by each new case it is presented with. Furthermore, a number of different implementations are provided in order to evaluate a comparative study of their performance.

Artificial Intelligence↗
PubMed2003

Structure-activity relationship study of a diverse set of estrogen receptor ligands (I) using MultiCASE expert system.

The MultiCASE expert system was used to construct a quantitative structure-activity relationship model to screen chemicals with estrogen receptor (ER) binding potential. Structures and ER binding data of 313 chemicals were used as inputs to train the expert system. The training data set covers inactive, weak as well as very powerful ER binders and represents a variety of chemical compounds. Substructural features associated with ER binding activity (biophores) and features that prevent receptor binding (biophobes) were identified. Although a single phenolic hydroxyl group was found to be the most important biophore responsible for the estrogenic activity of most of the chemicals, MultiCASE also identified other biophores and structural features that modulate the activity of the chemicals. Furthermore, the findings supported our previous hypothesis that a 6 A distant descriptor may describe a ligand-binding site on an ER. Quantitative structure-activity relationship models for the chemicals associated with each biophore were constructed as part of the expert system and can be used to predict the activity of new chemicals. The model was cross validated via 10 x 10%-off tests, giving an average concordance of 84.04%.

Animals↗
PubMed1993

[Detection of the phenotypes of resistance of enterobacteriaceae to aminoglycosides with ATB Plus Expert System].

ATB Plus Expert (Biomérieux SA) is an expert system which has been developed to perform an interpretative reading of ATB susceptibility tests. The system was tested on the results obtained for 217 strains of enterobacteriaceae. These strains were selected in order to cover a maximum of bacterial species and resistance mechanisms. The isolates were tested on rapid ATB E, rapid ATB G-, rapid ATB Ur, ATB G- and ATB Ur strips. In parallel, a disc diffusion susceptibility test was performed with 5 discs of aminoglycosides (kanamycin, gentamicin, tobramycin, netilmicin, amikacin) and the interpretation was carried out according to the criteria usually followed. Of the 217 strains tested, 122 showed a resistance phenotype. Only the rapid ATB E strips included kanamycin and allowed the detection of APH(3') phenotypes. Amikacin was not included in the ATB Ur strip, consequently it was impossible to discriminate AAC(3)-II and AAC(6') + AAC(3)-I phenotypes. 12 strains did not grow within 5 hours using the rapid ATB methodology. Not taking into account the problems previously encountered, different phenotypes between the 6 susceptibility tests were found for 16 strains. In 5 cases the expert system detected an anomaly instead of the correct phenotype, and in 3 cases of unknown phenotypes, the answers were variable. In the other cases, the main difficulty was the detection of the isolated resistance to gentamicin (AAC(3)-I phenotype). The expert system automatically corrects the susceptibility test result according to the phenotype observed.

Amikacin↗
PubMed1993

Using ILIAD system shell to create an expert system for differential diagnosis of renal masses.

Differential diagnosis of renal masses is an important and difficult process. A renal mass diagnostic system (RMDS) developed by using the ILIAD expert system shell has been created for diagnostic consultations and patient simulations. Seventy-two cases of renal mass have been tested on this system and the diagnostic accuracy was compared to that of residents. The overall diagnostic accuracy (75%) for renal masses is significantly better than second-year urological residents (60%) and not worse than urological chief residents (71%). The expert system also displays the cost of the diagnostic procedures so that the user can choose the most cost-effective diagnostic process. We conclude that this powerful renal mass diagnosis system developed by using ILIAD system shell can be used as a teaching, self-training and clinical tool for urological residents.

Artificial Intelligence↗
PubMed1992

Analysis of criteria for grading bladder cancer in urine cytological tumor diagnosis by means of an expert system.

An inductive expert system was used for the analysis of criteria for grading bladder carcinoma in urine cytological tumor diagnosis. This analysis seems necessary in order to provide a better standardization of grading and to avoid tumor grades, which are rather inhomogeneous with respect to morphology and prognosis. The analysis of the database by the inductive system shows a considerable variation of the cytomorphology of different bladder carcinomas graded as G2 tumors, whereas G1 and G3 tumors are more homogeneous groups respectively. Especially nuclear morphological criteria are important features for the detection of highly differentiated carcinomas, whereas nucleolar features might be helpful to assess the proliferative nature of the carcinoma. The future goal of avoiding a grading system with prognostically inhomogeneous tumor grades seems possible when using an inductive expert system for consultation.

Carcinoma, Transitional Cell↗
PubMedDate not supplied

Expert systems: a classical introduction.

Expert systems are providing a means of solving complex problems that previously defied automation efforts. This paper explains what an expert system is and how one operates. Following a brief description of expert systems, the nature of computer problem-solving and the role of knowledge in that activity are discussed. A typical expert system architecture and common knowledge representation schemes are then described. Finally, the operation of a simple, rule-based expert system is illustrated.

Artificial Intelligence↗