Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Intelligent Systems”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9Linked to original sources
PubMed1996

An expert diagnostic system based on neural networks and image analysis techniques in the field of automated cytogenetics.

In this study, we introduce an expert system for intelligent chromosome recognition and classification based on artificial neural networks (ANN) and features obtained by automated image analysis techniques. A microscope equipped with a CCTV camera, integrated with an IBM-PC compatible computer environment including a frame grabber, is used for image data acquisition. Features of the chromosomes are obtained directly from the digital chromosome images. Two new algorithms for automated object detection and object skeletonizing constitute the basis of the feature extraction phase which constructs the components of the input vector to the ANN part of the system. This first version of our intelligent diagnostic system uses a trained unsupervised neural network structure and an original rule-based classification algorithm to find a karyotyped form of randomly distributed chromosomes over a complete metaphase. We investigate the effects of network parameters on the classification performance and discuss the adaptability and flexibility of the neural system in order to reach a structure giving an output including information about both structural and numerical abnormalities. Moreover, the classification performances of neural and rule-based system are compared for each class of chromosome.

Algorithms↗
PubMed1989

Self-organisation and living systems: Is DNA an 'artificial intelligence'?

There seems little doubt that the maintenance and development of living systems is crucially dependent on an internal organisation of monumental complexity--particularly in higher living species. It is suggested that current thinking--particularly relating to the role of DNA in the total process cannot explain the underlying mechanisms and that a radical rethinking will be necessary. To this end it is proposed that DNA has a unique molecular electronic structure enabling it to operate as a computer analogue system for the highly efficient storage of information and as a type of artificial intelligence through which the information is translated and implemented to organise and control all aspects of the construction and activity of living systems.

Artificial Intelligence↗
PubMed1987

Validation of the pediatric speech intelligibility test in children with central nervous system lesions.

The pediatric speech intelligibility (PSI) test was administered to 21 children with a variety of documented central nervous system (CNS) lesions. Ages ranged from 3 to 8 years. PSI test results demonstrated both high sensitivity and high specificity. Results were consistently (1) abnormal in children with lesions in areas of the brain important for auditory function (CNS auditory disorders) and (2) normal in children with lesions in areas anatomically remote from auditory nuclei and pathways (nonauditory CNS disorders).

Auditory Threshold↗
PubMed1992

An intelligent computer-assisted instruction system designed for rural health workers in developing countries.

This paper describes an intelligent computer-assisted instruction system that was designed for rural health workers in developing countries. This system, called Consult-EAO, includes an expert module and a coaching module. The expert module, which is derived from the knowledge-based decision support system Tropicaid, covers most of medical practice in developing countries. It allows for the creation of outpatient simulations without the help of a teacher. The student may practice his knowledge by solving problems with these simulations. The system gives some initial facts and controls the simulation during the session by guiding the student toward the most efficient decisions. All student answers are analyzed and, if necessary, criticized. The messages are adapted to the situation due to the pedagogical rules of the coaching module. This system runs on PC-compatible computer.

Computer Simulation↗
PubMed1992

Diagnosis of periodontitis by physical measurement: interpretation from episodic disease hypothesis.

Physical measurements including the evaluation of probing depth, bleeding on probing, tooth mobility, and inflammation form the basis for most periodontal diagnostics in use today. The interpretation of these observations and the methods available for their measurement, however, have begun to change significantly. The episodic disease activity concept has done much to implement these changes. Observation of episodic attachment loss has been correlated with parallel radiographic changes, alteration in levels of probable pathogens, and changes in inflammatory mediator levels. The failure of pocket depth, suppuration, and bleeding on probing to predict episodic attachment loss has been given plausible explanations and enhanced meanings. Although attachment loss by a continuous process cannot be excluded in some disease conditions, the hypothesis of periodontal disease progression by episodic activity supplements and expands understanding of the disease process. Interest in periodontal diagnostics has accelerated in the last decade. As a parallel development, the technology of small computers has decreased in cost and increased in sophistication. The combination of these factors has created an environment for the development of intelligent diagnostic systems. Four commercially available systems and two systems under development are described. The systems, which measure pocket depth, pocket depth or attachment level, tooth mobility, and pocket temperature, all utilize computer processing of measurements. The result is to provide a simplified and more meaningful presentation of diagnostic information. As intelligent diagnostic systems prove themselves, some of these instruments are likely to become common to dental practice. The promise of more accurate identification of areas of the mouth that are diseased can increase both the efficiency and effectiveness of periodontal therapy.

Humans↗
PubMed1989

A knowledge-based information system for monitoring drug levels.

The expert system shell SMR has been enhanced to include information system routines for designing data screens and providing facilities for data entry, storage, retrieval, queries and descriptive statistics. The data for inference making is abstracted from the data base record and inserted into a data array to which the knowledge base is applied to derive the appropriate advice and comments. The enhanced system has been used to develop an intelligent information system for monitoring serum drug levels which includes evaluation of temporal changes and production of specialized printed reports. The module for digoxin has been fully developed and validated. To demonstrate the extension to other drugs a module for phenytoin was constructed with only a rudimentary knowledge base. Data from the request forms together with the S-digoxin results are entered into the data base by the department secretary. The day's results are then reviewed by the clinical pharmacologist. For each case, previous results may be displayed and are taken into account by the system in the decision process. The knowledge base is applied to the data to formulate an evaluative comment on the report returned to the requestor. The report includes a semi-graphic presentation of the current and previous results and either the system's interpretation or one entered by the pharmacologist if he does not agree with it. The pharmacologist's comment is also recorded in the data base for future retrieval, analysis and possible updating of the knowledge base. The system is now undergoing testing and evaluation under routine operations in the clinical pharmacology service. It is a prototype for other applications in both laboratory and clinical medicine currently under development at Uppsala University Hospital. This system may thus provide a vehicle for a more intensive penetration of knowledge-based systems in practical medical applications.

Data Interpretation, Statistical↗
PubMed1980

Adding information and intelligence to a family practice data system.

A critical test of any data system is its relevance; more simply, reports must present what users want. At MCV, the current system is a direct response to expressed user demands (corroborated by results of a survey of British general practitioners). That is, resident and physicians are interested in workload rates, such as visits/patient, and a delineation of diagnoses by frequency. Applications of these reports are organizational, comparative, and educational. The ultimate goal of data systems in family practice is the production of intelligence about health and health affairs: clearly, this is valuable in patient care, research, and education. Methods outlined above will contribute to achieving this end by adding information and intelligence to data systems.

Data Collection↗
PubMed1994

A knowledge-based alarm system for monitoring cardiac operated patients--assessment of clinical performance.

An intelligent alarm system for the postoperative monitoring of cardiac surgery patients, which did not require any manual data entries, was tested in two phases. A clinician monitored at bedside the patients' recovery and verified clinically abnormal physiological states. After the first test with ten patients, the system's rulebase was upgraded and then tested with an additional 15 patients. The alarm system employed two PC/ATs and was programmed to give notice of four pathological states (hyperdynamic state, hypovolemic state, hypoventilation and left ventricular failure) at two levels of urgency (alarm and alert levels). The monitoring lasted 5.4 +/- 1.7 hours per patient (mean +/- S.D.), totalling 134.7 hours. The system alarmed 27 times during the first and 73 times during the second phase of the testing. The sensitivity of the alarms was 100% in both phases, and the specificities increased from 20.0% to 73.9% and from 59.1% to 70.0% for the alarms and the alerts, respectively. This computerized decision support system based exclusively on data available in the automatically collected data base had a low false positive rate and gave early warnings about pathological states in the homogeneous group of adult postoperative cardiac patients.

Adult↗
PubMed1995

Computational intelligence for laboratory information systems.

Non-linear models, such as given by neural networks and fuzzy logic, have established a good reputation for medical data analysis as computational and logical counterparts to statistical methods. Whereas multilayer perceptrons perform well with large data sets, a combination of neural learning together with fuzzy logical network interpretations provides a network reduction well suited for smaller data sets. The aim of this paper is to present an approach to neural fuzzy systems data analysis and knowledge acquisition in laboratory information systems. We also describe a software system, DiagaiD, which provides an analysis and development workbench involving laboratory data.

Clinical Laboratory Information Systems↗
PubMedDate not supplied

Sleep Expert--an intelligent medical decision support system for sleep disorders.

A new type of associative knowledge-based decision support system (Sleep Expert) for the diagnosis and classification of sleep disorders is described. Sleep Expert is based on the International Classification of Sleep Disorders (1990). The programming system used was KnowledgePro (Windows), a high-level language that integrates object-oriented programming, hypertext and expert system technologies. Sleep Expert is an interactive program composed of 288 separate integrated submodules and 264 text files. The program includes eight reasoning questions about symptoms setting the limits for the diagnosis subset. The user obtains a list of possible diagnoses on the screen where he/she can examine their criteria. The program has been written in such a form that the user can freely associate and can move forwards and backwards. Detailed information is included in hypertext.

Diagnosis, Computer-Assisted↗
PubMed1994

An intelligent Computer-Assisted Instruction system for clinical case teaching.

The use of computers in the field of medical education is common. Our purpose is to present a Computer-Assisted Instruction system which has been developed over ten years at the University of Compiègne and the University of Rennes Medical School. This system can be used to help the student to solve clinical cases by analyzing and critiquing their answers and by using a knowledge base which has been previously structured in a rule network. It is an intelligent Computer-Assisted Instruction system comprising an author module, a pedagogical module and a student module. The CAI system can be used as a simulation model for any type of diagnostic or therapeutic problem. In this paper we present the author and pedagogical module which have been built using our previous work on intelligent computer-assisted instruction systems.

Artificial Intelligence↗
PubMed1982

Origins of anthropoid intelligence IV. Role of prefrontal system in delayed alternation and spatial reversal learning in a conservative eutherian (Paraechinus hypomelas).

A conservative eutherian mammal (the hedgehog, Paraechinus hypomelas) was tested on delayed alternation performance and spatial reversal learning before and after ablations of the prefrontal cortex. The anatomical results show that the cortical focus of the projections of the medial dorsal nucleus, the prefrontal cortex, does not include the neocortex on the dorsal convexity of the hedgehog's frontal lobe but, instead, the perirhinal and pregenual neocortex immediately surrounding the frontal convexity. The behavioral results show that normal performance of hedgehogs on these two behavioral tests depends upon the integrity of their prefrontal cortex, but not on the integrity of their frontal convexity or olfactory bulbs. The similarity in the results obtained from prefrontal hedgehogs and a divergent variety of other species with prefrontal ablations indicates that the role of the prefrontal system in the abilities measured by these two tests is at least as old as Eutheria and, thus, probably imposed persistent constraints on subsequent evolutionary modifications of the prefrontal system.

Animals↗
PubMed1987

Computer technology: state of the art and future trends.

Computer technology and, more broadly, information technology, are bringing about a fundamental transformation in our society from an industrial economy to an information economy. A review of the short history and present state of information technology identifies two major undercurrents: the miniaturization of computer components, which has produced a millionfold increase in the complexity possible in a single chip of silicon, and the integration of four previously separate areas of information technology: computation, communication, databases and the user interface. Microelectronics, computer networks, data storage and user amenities are the basic technologies that support these four areas and stimulate their progress. Future trends in speech recognition, voice synthesis, artificial intelligence, expert systems, computational imaging and scientific workstations are also examined.

Artificial Intelligence↗
PubMed1993

Hypothalamic-pituitary-adrenal axis function in children with attention-deficit hyperactivity disorder.

Examined hypothalamic-pituitary-adrenal axis (HPA axis) function in 30 children with attention-deficit hyperactivity disorder (ADHD) by measuring the diurnal variation and response to the dexamethasone suppression test (DST) of saliva cortisol. Normal diurnal saliva cortisol rhythm was found in only 43.3% of the ADHD children. DST showed suppression in 46.7% of the ADHD children. An abnormal diurnal rhythm and nonsuppression to the DST were more frequent in the severely hyperactive group than in the mildly were more frequent in the severely hyperactive group than in the mildly hyperactive group of children with ADHD. These results suggest abnormalities in HPA axis function in some children with ADHD, especially those exhibiting severe hyperactivity.

Attention Deficit Disorder with Hyperactivity↗
PubMed1996

Strange hemodynamic attractor parameter with 1/R total artificial heart automatic control algorithm.

To evaluate the automatic control algorithm of the total artificial heart (TAH) as an entity, and not just as parts, a non-linear mathematical analyzing technique including chaos theory was utilized. Chronic experiments on the biventricular bypass type artificial heart implantation were performed in healthy adult goats after the natural ventricles were removed. Hemodynamic time series data were recorded under the awake standing condition with TAH 1/R and fixed driving. Time series data were recorded on a magnetic tape and analyzed on a personal computer system with an A-D converter. Using the nonlinear mathematical technique, the time series data were embedded into the phase space and the Lyapunov numerical method was carried out for the quantitative evaluation of the sensitive dependence on the initial condition of the reconstructed attractor. Calculation of the largest Lyapunov exponents suggested that the reconstructed attractor of the left pump output during TAH 1/R control was a larger dimensional strange attractor, a characteristic pattern of deterministic chaos. A total system indicating chaotic dynamics was thought to be a flexible and intelligent control system. Thus, our results suggest that 1/R TAH control may be suitable for the biventricular assist type total artificial heart.

Algorithms↗