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 1,135 records · Page 63Linked to original sources

PubMedDate not supplied

A decision support system for phosphorus management at a watershed scale.

Phosphorus (P) is one of the main nutrients controlling algal production in aquatic systems. Proper management of P in agricultural production systems can greatly enhance our ability to combat pollution of aquatic environments. To address this issue, a decision support system (DSS) consisting of the Maryland Phosphorus Index (PI), diagnosis expert system (ES), prescription ES, and a nonpoint-source pollution model, Ground Water Loading Effects of Agricultural Management Systems (GLEAMS), was developed and applied to an agricultural watershed in southern Sweden. This system can identify critical source areas (CSAs) regarding phosphorus losses within the watershed, make a diagnosis of probable causes, prescribe the most appropriate best management practices (BMPs), and test the environmental effects of the applied BMPs. The PI calculations identified small parts of the watershed as CSAs. Only 10.4% of the total watershed area in 1995 and 5.2% of the total watershed area in 1996 were classed as "high potential P movement." Four probable causes (high P level in soil, excessive P fertilization, stream proximity, and subsurface drainage) and three BMPs (riparian buffer strips, reduced P fertilizer application, and P fertilizer incorporation) were identified by a diagnosis and prescription expert system. The GLEAMS simulations conducted for one selected CSA field for a 24-yr period showed that the recommended BMP reduced runoff P losses by 55% and sediment P losses by 71%, if applied from the first year. Results showed that using DSS may enable us to select a proper BMP implementation strategy and to realize the beneficial effect of BMPs on a long-term basis.

Agriculture↗

PubMed1995

Database for vertigo.

An interactive database has been developed to assist the diagnostic procedure for vertigo and to store the data. The database offers a possibility to split and reunite the collected information when needed. It contains detailed information about a patient's history, symptoms, and findings in otoneurologic, audiologic, and imaging tests. The symptoms are classified into sets of questions on vertigo (including postural instability), hearing loss and tinnitus, and provoking factors. Confounding disorders are screened. The otoneurologic tests involve saccades, smooth pursuit, posturography, and a caloric test. In addition, findings from specific antibody tests, clinical neurotologic tests, magnetic resonance imaging, brain stem audiometry, and electrocochleography are included. The input information can be applied to workups for vertigo in an expert system called ONE. The database assists its user in that the input of information is easy. If not only can be used for diagnostic purposes but is also beneficial for research, and in combination with the expert system, it provides a tutorial guide for medical students.

Anxiety↗

PubMed1994

A knowledge acquisition tool in analytical pathology based on multi-media relational database.

The need for a knowledge based expert system for efficient decision making in the field of pathology has been well accepted. To build the knowledge-base for such an expert system is a painstaking task. This work is an attempt to provide the pathologists a powerful and user-friendly tool that will help them in the process of building the knowledge-base for medical diagnosis by closely looking at the specimen images and their extracted feature values. The tool is based on multi-media relational database and software like VAX Rally (4GL), ILIAD and SAS to provide a wide-range comparative study between feature data and image data; and also their statistical analysis.

Artificial Intelligence↗

PubMed2006

Identification and separation of DNA mixtures using peak area information.

We introduce a new methodology, based upon probabilistic expert systems, for analysing forensic identification problems involving DNA mixture traces using quantitative peak area information. Peak area is modelled with conditional Gaussian distributions. The expert system can be used for ascertaining whether individuals, whose profiles have been measured, have contributed to the mixture. It can also be used to predict DNA profiles of unknown contributors by separating the mixture into its individual components. The potential of our probabilistic methodology is illustrated on case data examples and compared with alternative approaches. The advantages are that identification and separation issues can be handled in a unified way within a single probabilistic model and the uncertainty associated with the analysis is quantified. Further work, required to bring the methodology to a point where it could be applied to the routine analysis of casework, is discussed.

DNA↗

PubMed1995

Computer assisted data collection in vestibular disorders.

We have developed an interactive database for vertigo than can be used to assist in the diagnostic procedure and to store the data in a form of a database. The database offers the possibility to split and reunite the collected information in a desired way. The database contains detailed information about patient history, symptoms and findings in neurotological, audiological and imaging tests. The symptoms are classified into three sets of questions: vertigo (including postural instability), hearing loss and tinnitus, and provoking factors. Confounding disorders are screened. The neurotological tests involve saccades, smooth pursuit, posturography and caloric test. In addition, findings in specified antibody testing, clinical neurotological tests. MRI, brain stem audiometry and electrocochleography are included. The input information can be applied in an expert system ONE for vertigo work-up. The database is user-friendly. Besides diagnostic purposes the database is excellent for research purposes, and combined with the expert system it works as a tutorial guide for medical students.

Artificial Intelligence↗

PubMed1998

Automatic classification of transiently evoked otoacoustic emissions using an artificial neural network.

The increasing use of transiently evoked otoacoustic emissions (TEOAE) in large neonatal hearing screening programmes makes a standardized method of response classification desirable. Until now methods have been either subjective or based on arbitrary response characteristics. This study takes an expert system approach to standardize the subjective judgements of an experienced scorer. The method that is developed comprises three stages. First, it transforms TEOAEs from waveforms in the time domain into a simplified parameter set. Second, the parameter set is classified by an artificial neural network that has been taught on a large database TEOAE waveforms and corresponding expert scores. Third, additional fuzzy logic rules automatically detect probable artefacts in the waveforms and synchronized spontaneous emission components. In this way, the knowledge of the experienced scorer is encapsulated in the expert system software and thereafter can be accessed by non-experts. Teaching and evaluation of the neural network was based on TEOAEs from a database totalling 2190 neonatal hearing screening tests. The database was divided into learning and test groups with 820 and 1370 waveforms respectively. From each recorded waveform a set of 12 parameters was calculated, representing signal static and dynamic properties. The artifical network was taught with parameter sets of only the learning groups. Reproduction of the human scorer classification by the neural net in the learning group showed a sensitivity for detecting screen fails of 99.3% (299 from 301 failed results on subjective scoring) and a specificity for detecting screen passes of 81.1% (421 of 519 pass results). To quantify the post hoc performance of the net (generalization), the test group was then presented to the network input. Sensitivity was 99.4% (474 from 477) and specificity was 87.3% (780 from 893). To check the efficiency of the classification method, a second learning group was selected out of the previous test group, and the previous learning group was used as the test group. Repeating learning and test procedures yielded 99.3% sensitivity and 80.7% specificity for reproduction, and 99.4% sensitivity and 86.7% specificity for generalization. In all respects, performance was better than for a previously optimized method based simply on cross-correlation between replicate non-linear waveforms. It is concluded that classification methods based on neural networks show promise for application to large neonatal screening programmes utilizing TEOAEs.

Artificial Intelligence↗

PubMed1992

Inductive learning of thyroid functional states using the ID3 algorithm. The effect of poor examples on the learning result.

The ID3 algorithm for inductive learning was tested using preclassified material for patients suspected to have a thyroid illness. Classification followed a rule-based expert system for the diagnosis of thyroid function. Thus, the knowledge to be learned was limited to the rules existing in the knowledge base of that expert system. The learning capability of the ID3 algorithm was tested with an unselected learning material (with some inherent missing data) and with a selected learning material (no missing data). The selected learning material was a subgroup which formed a part of the unselected learning material. When the number of learning cases was increased, the accuracy of the program improved. When the learning material was large enough, an increase in the learning material did not improve the results further. A better learning result was achieved with the selected learning material not including missing data as compared to unselected learning material. With this material we demonstrate a weakness in the ID3 algorithm: it can not find available information from good example cases if we add poor examples to the data.

Algorithms↗

PubMed2003

Set theory in diagnostic reasoning.

BACKGROUND: Regarding diagnostic reasoning, the currently taught Bayesian theory is a form of hypothetical-deduction reasoning. Using set theory, we offer syllogism reasoning instead of hypothetical-deductive reasoning and establish an online diagnostic expert system model based on this diagnostic methodology. METHODS: Concepts of set theory were employed to demonstrate diagnostic reasoning. ASP, Vbscript and Microsoft Access were used to establish the expert system and data of 50 cases from Shanghai pulmonary hospital were put into the program to test its efficiency. CONCLUSION: Diagnostic procedure is type of syllogism rather than hypothetical-deductive reasoning.

Cluster Analysis↗

PubMed1997

An algorithm for assessing intraoperative mean arterial pressure lability.

BACKGROUND: Intraoperative blood pressure lability may be related to risk factors, hypovolemia, light anesthesia, and morbid outcomes, but the measurements of lability in previous studies have been limited by imprecise and infrequent data collection methods. Computerized intraoperative data acquisition systems have provided an opportunity to readdress the issue of intraoperative blood pressure lability with more abundant and precise data. This study sought to derive and validate an algorithm (expert system) to measure mean arterial pressure (MAP) lability. METHODS: Two hundred thirty-nine computerized anesthesis records were reviewed retrospectively. Three anesthesiologists separately rated MAP as very stable, average, or very labile. The parameters of a computer algorithm that measured the change of median MAP between consecutive 2-min epochs were optimized to achieve the best possible agreement among the anesthesiologists. The algorithm was then validated on 229 additional anesthesia records. RESULTS: The proportion of consecutive 2-min epochs in which the absolute value of the fractional change of median MAP exceeded 0.06 (i.e., 6%) correlated strongly with the anesthesiologists' ratings (r = 0.78; P < 0.0001). The optimal sensitivity and specificity of the algorithm for detecting MAP lability were 98% and 59%, respectively. CONCLUSIONS: One potential application of expert systems to anesthesia practice is a "smart alarm" to detect blood pressure lability. It may also provide a better tool to assess the relation between lability and outcome than has been available previously.

Algorithms↗

PubMed1999

Interactive versus noninteractive interventions and dose-response relationships for stage-matched smoking cessation programs in a managed care setting.

This study compared interactive and noninteractive smoking cessation interventions for a population of smokers who were all members of 1 division of a managed care company. In addition, it examined whether a dose-response relationship existed. Screening was completed for 19,236 members who were contacted by telephone or mail. Of the 4,653 who were identified as smokers, 85.3% were enrolled. A 2 Intervention (interactive or noninteractive) x 4 Contacts (1, 2, 3, or 6 contacts) x 4 Occasions (0, 6, 12, and 18 months) design was used. The interactive intervention was stage-matched expert-system reports plus manuals; the noninteractive intervention was stage-matched manuals. Contact occurred in 1 of 4 series (1, 2, 3 or 6 contacts) at 3-month intervals. The expert system outperformed the stage-matched manuals, but there was no clear dose-response relationship for either intervention.

Adult↗

PubMed1991

Expert control of the arterial blood pressure during surgery.

During and after many surgical procedures the patient's arterial blood pressure must be artificially decreased to a lower than normal level. Although there are alternatives, infusion of the drug sodium nitroprusside (SNP) is frequently the preferred technique to achieve this controlled hypotension. The fast action of the drug and the danger of a too low pressure make manual control of the SNP infusion flow rate, even if done by an expert, a difficult and demanding task. This is mainly due to an occasional large unpredictable variability over time of the patient's sensitivity to SNP, and to the fact that a multitude of other factors also influence the arterial pressure. Due to these and several other causes, current automatic controllers cannot handle all cases equally well. A new expert system based SNP controller was designed to perform well for all patients, regardless of their characteristics. It monitors and adjusts its own performance, employing a number of heuristics derived from a careful study of the properties of the arterial pressure signal, the effects of SNP and other clinical provocations on the arterial pressure, and the ways in which expert clinicians manually manage the SNP infusion. Expert systems technology allows the new controller to access and employ this type of expert medical knowledge, resulting in expert-level performance. The controller was tested on 30 patients undergoing cardiac surgery, both before, during and after bypass. It was safe, needed little attention, and performed well in all cases.

Animals↗

PubMed1989

The diagnostic pattern in histopathology.

Defining in precise detail the diagnostic clues used by histopathologists to arrive at a diagnosis is a difficult process; however, better analytic understanding of this process is a prerequisite for the design of diagnostic expert systems. Such systems offer the potential for consistency and setting standards in the diagnostic evaluation of difficult situations. Diagnostic clues as offered by the image represent two-dimensional information. Their description is entered into the knowledge base of an aspect system, however, in the form of a description, which is one-dimensional. Preserving all of the two-dimensional dependence structure in this conversion is a fundamental problem. Use of the description to generate simulated imagery tests whether or not the two-dimensional dependence structure of a given tissue architecture has been adequately represented in the analytic description. This analytic description would then be entered into the knowledge base of an expert system.

Communication↗

PubMed1997

[Computer-assisted smoking cessation].

Though the prevalence of cigarette smoking has declined it still remains the leading cause of premature death from chronic disease. In the prevention of tobacco associated disease the promotion of smoking cessation is a key strategy. This article presents a smoking cessation program based on the transtheoretical model, an empirical model distinguishing five stages of behavioral change. Specific interventions are matched to the current stage of change. Smokers in the intervention program repeatedly fill in questionnaires about their smoking habits, attitudes and strategies in the smoking cessation process. The individual questionnaires are analyzed by a computerized expert system which creates letters with comments on the smoking cessation process and suggestions for further steps from a pool of feedback paragraphs. A further component of the program are five stage-matched brochures. The efficacy of the expert system and its potential impact on Public Health are discussed.

Artificial Intelligence↗

PubMed1996

Worldwide analysis and collection centre for data on syndromic genetic hearing loss: a new proposal.

The remarkable number of syndromic genetic hearing loss (about 150), the extreme variety of clinical signs that can be associated with the hearing loss, and the different possible combinations make the diagnosis od syndromic genetic hearing loss sometimes very difficult and motivated the development of an expert system (G-DEAFNEX). A collection centre is proposed: to act as a referral centre, for patients with suspected syndromic genetic hearing loss, that aids the diagnostic procedure; to act as a centre for the collection of data on patients with known syndromic genetic hearing loss; to collaborate with Hearing International in a worldwide epidemiological study on syndromic genetic hearing loss; to refine the G-DEAFNEX expert system.

Diagnosis, Computer-Assisted↗

PubMed1992

[Use of the Adinfer diagnostic system in a study of somatic disorders in general practice].

Somatic complaints are very common in general medical practice. They are not identified as psychic disorders and are treated symptomatically. We explore two kind of problems: 1. methodological problems such as the instruments to use to examine somatic complaints (it is evident that a checklist does not give the best results with suggestible patients); and 2. the relationships between somatic complaints and psychic disorders such as anxiety, depression and somatoform disorders. Psychiatric nosology is by no means clear and includes many diagnoses from "hysteria" to "hypochondria" or "psychosomatic", "somatization". In this study, we compare the symptoms collected by general practitioners, and their clinical diagnoses to those obtained by an automatic DSM-III diagnostic program. Adinfer was modified so that three DSM decision trees were systematically scanned: depressive, anxiety and somatoform disorders. This allows for an epidemiological study of somatic complaints and their relationship to depression and anxiety. The subjects' score on rating scales for anxiety and depression are compared with the diagnoses made by the expert system. We discuss the significance of somatic symptoms, the DSM classes and the value of expert systems in epidemiological studies.

Adult↗

PubMed2002

ECVAM's activities on computer modelling and integrated testing.

This paper introduces the basic concepts of quantitative structure-activity relationship (QSAR), expert system and integrated testing strategy, and explains how the analogy between QSARs and prediction models leads naturally to criteria for the validation of QSARs. ECVAM's in-house research programme on QSAR modelling and integrated testing is summarised, along with plans for the validation of QSAR models and expert system rulebases at the European Union level.

Animal Testing Alternatives↗

PubMedDate not supplied

[An expert clinical diagnosis system for the support of the primary consultation].

In Brazil, as in other Latin American countries, there was a sharp increase in the number of medical schools in the past 20 years. The result was a steep increase in the number of physicians. These professionals are in many cases, however, poorly trained. As a consequence, public, as well as private health services, are exposed to professionals of great diversity of qualification. Few effective solutions have been proposed for this health services management problem. This paper presents a potential solution. It exposes preliminary results of field tests of an Expert System based on the first author's (Rozenbojm) three decades of experiences as a clinician, and medical residency advisor. The system was developed using ESE IBM Expert Systems language and a mainframe hardware. It was designed to support diagnosis based only in anamnesis and physical examination data, without lab or X ray support. Its original purpose was to increase the primary care physician's diagnostic and therapeutic accuracy. An initial test with specialist panels (endocrinology, cardiology, nephrology, G.O., gastroenterology, pediatrics and pneumology) revealed spell out a diagnostic and therapeutic concordance rate over 95 percent (based on real everyday practice cases brought by the specialists). A second test was performed in a private Health Care Network, at primary care level. In this case, concordance rate was over 83 percent in diagnostic aspects and 95 percent in the clinical orientation aspects. This expert system may be very useful for Health Services providing, first encounter standardization, medical graduate basic education and cost containment. The next proposed steps includes transcription of the software for personal computer utilization and an evaluation of its economic impacts.

Adult↗

PubMed1989

Knowledge engineering for clinical consultation programs: modeling the application area.

Developers of computer-based decision-support tools frequently adopt either pattern recognition or artificial intelligence techniques as the basis for their programs. Because these developers often choose to accentuate the differences between these alternative approaches, the more fundamental similarities are frequently overlooked. The principal challenge in the creation of any clinical consultation program - regardless of the methodology that is used - lies in creating a computational model of the application domain. The difficulty in generating such a model manifests itself in symptoms that workers in the expert systems community have labeled "the knowledge-acquisition bottleneck" and "the problem of brittleness". This paper explores these two symptoms and shows how the development of consultation programs based on pattern-recognition techniques is subject to analogous difficulties. The expert systems and pattern recognition communities must recognize that they face similar challenges, and must unite to develop methods that assist with the process of building of models of complex application tasks.

Decision Support Techniques↗