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 91 records · Page 5Linked to original sources

PubMed1993

Stepwise development of a clinical expert system in rheumatology.

The evaluation of computer expert systems, a promising diagnostic tool for future application in clinical medicine, is of great importance. We present here the evaluation of our expert system, "RHEUMA". It is stressed, that repeated retrospective testing and updating of an expert system and its subsequent repeated assessment in clinical use and surroundings is mandatory. This increases the diagnostic accuracy of the system. For our system this is demonstrated under three separate conditions. In the first study the information available for the computer system (mainframe) came from medical histories only. Here an error rate of about 25%--similar to that of physicians themselves using the same information--was observed in 358 outpatients, compared to the final diagnoses of physicians also relying solely on information from medical histories. In a second step a completely new system on a personal computer was developed with all relevant diagnostic information. The error rate of this system (0.4%) was much too optimistic because the knowledge base was changed during the study, affecting about 30% of the 282 prospectively recruited outpatients. In a third step the efficacy of the expert system was tested in an additional hospital without the diagnostic involvement of the first testing clinic. The error rate of the system without changing the knowledge base reached 11% in 51 outpatients in this rheumatology clinic. This result reflects the diagnostic accuracy of the system today. Its ability to specify the same diagnoses which clinical experts reached approached 90%. Considerable time is needed for such prospective testing, with repeated updating of the knowledge base--in our case for both the two systems and field studies of 2 years each.(ABSTRACT TRUNCATED AT 250 WORDS)

Computers↗

PubMed2002

Improving the nitrogen removal efficiency of an A2/O based WWTP by using an on-line knowledge based expert system.

The results obtained using an expert system to control an activated sludge process involving nutrient removal are reported. The study was conducted at a pilot plant using an Anaerobic/Anoxic/Oxic (A2/O) scheme for which a distributed control system was specially developed. The system allows various expert operational approaches to be developed with a view to minimize nitrogen levels in the outlet while using the minimum amount of energy. The proposed distributed control system is supervised by a Knowledge Based Expert System (KBES) constructed with G2 (a tool for expert system development) and permits the on-line implementation of every operating strategy of the experimental system. A set of experiments involving variable loads and flow-rates was carried out. It revealed that the amount of removed nitrogen could be increased by 11% compared to the usual operating conditions. This increase resulted in a decrease in the amount of total nitrogen and ammonium nitrogen in the outlet by 49% and 64%, respectively. These improvements were achieved with little energy cost because the performance of the treatment plant was optimised using operating rules implemented in real time.

Artificial Intelligence↗

PubMed1999

An expert system intervention for smoking cessation.

The Pathways to Change system (PTC) is an expert system intervention for smoking cessation. Assessments are performed either by mail or by a telephone interview and each smoker receives a three- to four-page report that provides individualized recommendations matched to the individual's needs and readiness-to-change. The Transtheoretical Model of Change provides the theoretical basis for the expert system. Four different studies have demonstrated the efficacy of this intervention in a general population, with cessation rates of 22 to 26%. Furthermore, the difference between the groups was larger at each follow-up assessment point, indicating that the effects of the treatment increased long after the end of treatment. The studies involved two proactively recruited samples, demonstrating that a large proportion (85.3% and 82.5%) of the population of smokers could be successfully recruited into a smoking cessation program. Expert system interventions have the potential to have an extremely high impact on a total population of smokers.

Computer-Assisted Instruction↗

PubMed1990

A diagnostic expert system for colonic lesions.

The diagnostic expert system for colonic lesions (DESCL) was designed to discriminate colonic adenoma and adenocarcinoma from normal colonic tissue. Although it was originally developed for use in conjunction with a machine vision analytic system, the DESCL has evolved into a teaching tool and a model for conceptual machine learning. The expert system is table driven and consists of a shell and a knowledge base. The latter comprises a series of architectural and cytologic observations and a quantitative estimate of diagnostic importance relating these observations to diagnostic outcome. In a validation study of 100 colonic lesions, the expert system achieved a success rate of 98%. It has the flexibility to allow individual pathologists to "customize" the knowledge base to suit their diagnostic criteria.

Adenocarcinoma↗

PubMed1992

RXPERT: a prototype expert system for formulary decision making.

OBJECTIVE: RXPERT, a prototype, computer-based, expert system that models the decision-making processes for an ambulatory (non-hospital) formulary, is described as an example of how expert systems may be used to support pharmacy decision making. Basic information about expert-system technology is provided through this example. BACKGROUND: Computer-assisted decision making is becoming an important and accepted aspect of complex, health-related decisions. Because expert-system support may become an integral component of future, complex, pharmacy decision making, it is important for pharmacists to become familiar with this technology and its possibilities for supporting pharmacy decisions. METHOD: Expert systems offer the potential advantages of making the human decision-making process explicit, more consistent, easily duplicated in many locations simultaneously, and easy to update and document. Although an expert system is seldom intended to replace human decision makers, it can provide valuable support for complex, multivariable decisions. Typical knowledge-acquisition and knowledge-engineering techniques, as well as the characteristics and structure of expert systems, are described, relative to the development of the RXPERT prototype. CONCLUSIONS: Although RXPERT is not yet in use, the process for using an expert system to support an individual committee member's personal assessment of a drug product is described. Decision-support expert systems are potentially useful to pharmacists in complex decision-making tasks.

Canada↗

PubMed1992

Design of an expert system and its application to dermatopathology.

Expert systems are computer programs which use inference and knowledge to solve problems which usually require the expertise of a human specialist. This paper examines the application of expert systems to histopathology and explains their construction by describing the design of an expert system 'dermdx', intended to aid in the interpretation and diagnosis of biopsies of inflammatory diseases of the skin. The system consists of an expert shell, which performs the inference, and a rule-base, which contains the knowledge with which the system operates. The system can be easily updated or adapted to other tasks.

Computer Systems↗

PubMed1993

Computer-designed expert systems for breast cytology diagnosis.

Three expert systems have been developed to diagnose from nine scalar values visually assigned to epithelial cells obtained by breast fine needle aspiration. These expert systems achieved up to 0.98 sensitivity and 0.97 specificity. When applied to 804 breast masses, the clinical sensitivity was 0.98 and specificity was 0.93 (exclusive of the 0.04 unsatisfactory aspirates). Cancers can be missed physically during the aspiration process; thus, some clinically suspicious masses were biopsied despite benign cytology. This contributed to the difference between the expert system and clinical specificities.

Algorithms↗

PubMed1998

Comparison between diagnoses of human experts and a neurotologic expert system.

The decision-making ability of a recently developed neurotologic expert system was compared with the diagnoses of six physicians. Five of the physicians were residents and one was a specialist in the field of otolaryngology. The test patients were randomly selected from vertiginous patients referred to an otolaryngology clinic. The expert system and the physicians first had identical information on patient history, symptoms, and tests. During the second phase of the study the physicians were allowed to use the full medical records. The correct diagnoses were certified by an experienced specialist in neurotology. The expert system did better in decision-making when both the expert system and the physicians had identical information on patients. However, when the physicians were allowed to use patient's complete medical records, they surpassed the expert system. The expert system diagnosed 65% of the cases, while the physicians first diagnosed 54% of the cases, and then with complete information, 69% of the cases. From the patients' medical records, the physicians obtained information on the time perspective of the symptoms and the progression of the disease. These aspects will be used to further improve the expert system.

Adult↗

PubMed1997

Application of a case-based expert system to orthodontic diagnosis and treatment planning.

Expert systems are being utilised increasingly in medical fields for the purposes of assisting diagnosis and treatment planning. A case-based system is a particular type of expert system that uses a store of previously treated cases to provide the knowledge for solving new problems. The aim of this study was to investigate the application of this methodology in the field of orthodontic diagnosis and treatment planning. Using a limited group of features, a case-base of 300 cases was entered into a case-based expert system shell. A test set of 30 consecutive cases was then used to test the diagnostic capacity of the system. The computer-generated treatment plan matched the actual treatment plan in 24 of the 30 cases. The system was also tested for its capacity to handle unusual cases. The system has useful potential.

Case-Control Studies↗

PubMed1987

Evaluating medical expert systems.

Approximately 90% of all computerized medical expert systems have not been evaluated in clinical environments. This paper: identifies the principal methods used to assess the performance of medical expert systems in both laboratory and clinical settings, describes the different research strategies used in the evaluation of medical expert systems at different development stages, and discusses past evaluation efforts in relationship to future applications of different decision support technologies and expert systems in health care.

Cardiology↗

PubMed1990

Evaluating a perimetric expert system: experience with Octosmart.

When evaluating expert systems to be used in clinical perimetry, various aspects of their performance as compared with that of human interpreters must be considered. In this investigation, the results produced by the new Octosmart diagnostic program have been compared with the performance of three interpreters with various amounts of experience in visual field analysis. The evaluations were based on 27 visual fields with glaucomatous damage, which had been examined with the Octopus program G1. It is shown that in borderline cases (i.e., neither clearly normal nor clearly pathological) where strict statistical criteria must be employed in order to distinguish between possible pathology and artifacts, the "personal styles" of human interpreters, more than standardized decision criteria, implicitly guide the decision process, resulting in unpredictable, non-standardized interindividual differences. A standardized expert system, based on constant, explicit, and logical criteria is therefore considered to be superior to unaided human interpretation. It is pointed out that the influence of the implicit decision criteria of human interpreters must be controlled carefully if expert systems are to be evaluated with reference to human interpreters.

Analysis of Variance↗

PubMed1990

Computer-aided diagnosis of breast aspirates via expert systems.

Two computer-driven expert systems trained to correctly diagnose 369 fine needle aspirates of the breast on the basis of nine cytologic descriptive parameters were tested on 70 newly obtained aspirates (57 benign and 13 malignant). The system generated by multisurface pattern separation misclassified one malignant test sample (i.e., one false negative) while the system generated by a connectionist algorithm (neural network) misclassified two benign test samples (i.e., two false positives). A decision tree misclassified three of the benign test samples (i.e., three false positives). These expert systems aid in the cytologic diagnosis of breast aspirates and can serve as models for other applications.

Algorithms↗

PubMed1994

Validation of the medical expert system RENOIR.

RENOIR is an expert system developed to assist the diagnosis of 37 diseases of connective tissue and inflammatory arthropathies. Precise diagnosis of rheumatic diseases implies great uncertainty and there is no gold standard with which to compare the expert system output. To overcome this problem a set of clinical cases was submitted to RENOIR and its diagnoses were compared with those of clinicians. Medical records of 81 patients with rheumatic diseases were interpreted by RENOIR and by 12 clinicians at three different expertise levels in rheumatology. Distances between the likelihoods of the 37 considered diseases provided by clinicians and RENOIR were computed as a disagreement measure. Mahalanobis distance was used to correct the collinearity between the possibilities of each pair of diseases. Using the resulting matrices of distances between experts, cluster analyses were carried out to classify RENOIR among human experts. Greater differences between RENOIR and clinicians than among clinicians themselves were not found.

Cluster Analysis↗

PubMedDate not supplied

Feasibility of physician-developed expert systems.

The authors developed an experimental domain-independent "expert system generator" intended for direct use by physicians. They then undertook a four-year study to determine whether physicians could use such a system effectively. During this period they taught the use of the expert system generator to 70 medical students, who utilized it to build two small medical expert systems. At the conclusion of the course, students were examined on decision-making concepts and completed anonymous questionnaires. Performance scores, a composite of test and project grades, were calculated for each student. There was no significant association between previous computer experience and performance score. Thirty-two of 47 students responding felt the expert system generator was easy to use; 15 felt it was of moderate difficulty. Forty-three of 47 thought it a useful teaching aid. These data support the conclusion that physicians can learn to use domain-independent software to implement medical expert systems directly, without a knowledge engineer as an intermediary.

Artificial Intelligence↗

PubMedDate not supplied

Knowledge based expert systems for medical diagnosis.

Knowledge based expert systems' have been developed in the last decade for many different applications by adopting artificial intelligence techniques. The paper discusses the main characteristics of the expert systems devoted to medical diagnosis (knowledge representation, explanation capability, inexact reasoning) and addresses some of the limitations (mainly system validation and knowledge acquisition). Finally the paper sketches the overall organization of an expert system devoted to the evaluation of liver function.

Artificial Intelligence↗

PubMed1995

An interactive patient information and education system (Medical HouseCall) based on a physician expert system (Iliad).

Informed patients are better equipped to participate in their own health care decisions. We present Medical HouseCall (TM), a consumer expert system and medical information guide, derived in part from a diagnostic and treatment software used by physicians (Iliad). HouseCall(TM) generates a differential diagnosis based on the user symptoms and medical history. HouseCall(TM) also provides alerts for potentially harmful drug interactions, allows for the recording of personal medical history, and offers extensive but easy-to-read information about a variety of medical topics. Focus group evaluations of HouseCall (TM) have demonstrated the program's ease of use, as well as an appreciation of technology that can be used at home to investigate and understand health issues and participate in solving medical problems.

Attitude to Computers↗

PubMed2005

DXplain: Patterns of Use of a Mature Expert System.

DXplain is an expert system designed to suggest a set of diseases that are associated with a set of clinical findings entered by a health student or practitioner. It has been widely used for almost 20 years, during which time many new functions and capabilities have been added. We discuss the ways in which different classes of user interact with the system and which functions are most commonly used.

Data Collection↗

PubMedDate not supplied

Application of expert systems analysis to interpretation of fatal cases involving amitriptyline.

Part I. Expert 4: The object of this study was to investigate the applicability of commercially available expert system shells to interpretation in forensic toxicology. Amitriptyline toxicology was selected as a pilot trial. Blood and tissue concentrations of amitriptyline and nortriptyline in fatal and nonfatal amitriptyline cases from the literature and from the Registry of Human Toxicology databank were entered into the expert system shell Expert 4 (Rivers, Elsevier). The statistical evaluation routines of the shell were used to search for patterns in the data. Successive changes in the data base were made to test for the influence of the data base on the conclusions. Finally the data base was refined, based on the evaluations, to strengthen the probabilities of the conclusions. The refined database was coupled with the Expert 4 inference engine to infer unknown parameters in the cases. The results of the expert system analysis were compared to known values and published expert opinions. The ratio of amitriptyline/nortriptyline and tissue levels of nortriptyline were found to be the most significant measures for interpretation of effect and time since ingestion. Part II. Computer Induction of Rules: Blood and tissue concentrations of amitriptyline and nortriptyline in fatal and nonfatal amitriptyline cases from the literature and from the Registry of Human Toxicology databank were entered into the expert system shell BEAGLE, (Forsyth, Machine Learning Research, Ltd.). The automatic rule induction routines of the shell were used to search for patterns in the data. The program expressed these patterns as numerical predictions or Boolean logic rules. The results were compared to those obtained with the Expert 4 (Rivers, Elsevier) using the same case knowledge base.(ABSTRACT TRUNCATED AT 250 WORDS)

Amitriptyline↗