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 865 records · Page 48Linked to original sources
PubMed2004

Functional genomic hypothesis generation and experimentation by a robot scientist.

The question of whether it is possible to automate the scientific process is of both great theoretical interest and increasing practical importance because, in many scientific areas, data are being generated much faster than they can be effectively analysed. We describe a physically implemented robotic system that applies techniques from artificial intelligence to carry out cycles of scientific experimentation. The system automatically originates hypotheses to explain observations, devises experiments to test these hypotheses, physically runs the experiments using a laboratory robot, interprets the results to falsify hypotheses inconsistent with the data, and then repeats the cycle. Here we apply the system to the determination of gene function using deletion mutants of yeast (Saccharomyces cerevisiae) and auxotrophic growth experiments. We built and tested a detailed logical model (involving genes, proteins and metabolites) of the aromatic amino acid synthesis pathway. In biological experiments that automatically reconstruct parts of this model, we show that an intelligent experiment selection strategy is competitive with human performance and significantly outperforms, with a cost decrease of 3-fold and 100-fold (respectively), both cheapest and random-experiment selection.

Algorithms↗
PubMed1993

[Development of intelligent DDS technologies].

Recently, biologically active therapeutic peptides have been artificially synthesized by genetic engineering techniques. These peptides are easily degraded under physiological conditions and also encounter absorption problems due to their high molecular weight. Hence, they cannot be utilized effectively in conventional dosage forms. For such active agents, new types of DDS must be developed to deliver the drug effectively to the target site (targeted, site-specific delivery) and release drug when drug is required (temporal control) in addition to conventional rate-controlling systems. To realize such drug release systems, it is important to construct a system where drug itself senses an environmental stimuli and responds to appropriately control drug release. Such systems are described as "intelligent DDS", as distinguished from conventional DDS.

Drug Delivery Systems↗
PubMed1993

Designing a connectionist network supercomputer.

This paper describes an effort at UC Berkeley and the International Computer Science Institute to develop a supercomputer for artificial neural network applications. Our perspective has been strongly influenced by earlier experiences with the construction and use of a simpler machine. In particular, we have observed Amdahl's Law in action in our designs and those of others. These observations inspire attention to many factors beyond fast multiply-accumulate arithmetic. We describe a number of these factors along with rough expressions for their influence and then give the applications targets, machine goals and the system architecture for the machine we are currently designing.

Algorithms↗
PubMed1997

[Expert systems in risk assessment. Risk or opportunity?].

Experts underwriting systems in the risk selection of individual life insurance have a high place value and are, in future, indispensable in the daily underwriting process. The chance to reduce drastically dual operations enables the insurance companies to make more cost-efficient underwriting decisions. The rapidly advancing technology develops not only new dimensions for individualism and for providing customer service but also for a fast underwriting process which is of great benefit to the insurers who are up against stiff competition. The qualified underwriter and the physician will be relieved of standard work and have more time in investing their knowledge and know-how in the underwriting process which calls for an absolutely individual reflection. New activities are inevitably ahead of this group of persons: Maintenance and attendance of the experts system! A task with which the quality of such a system stands and falls. We are expectant to see what the future has in store for this field.

Artificial Intelligence↗
PubMed1989

Microcomputer based differential diagnosis of dysmorphic syndromes.

Dysmorphic syndromes are characterized by associations of physical abnormalities depending in its diagnosis on the recognition of a particular pattern. Because of their multiplicity, the rarity of some of them, and the frequency of new reports, computerized data bases have proved useful as powerful tools assisting in the differential diagnosis. The role of artificial intelligence methods, in particular Expert Systems, as promising tools in helping physicians to perform a clinical diagnosis is underlined. Using a high level computer language presently used in the artificial intelligence field (Prolog), a microcomputer based system for the differential diagnosis of dysmorphic syndromes is described. Its capabilities and simplicity of use, derived from an efficient and attractive computer interface, are underlined. The need of performance assessment by evaluating its accuracy and usefulness before its introduction into genetic clinical practice is stressed. Finally, for the completeness of the knowledge base, the need of cooperation between international centers is emphasized.

Congenital Abnormalities↗
PubMed2003

Medical telematics in disaster response.

INTRODUCTION: Every year many disasters cause thousands of injuries, deaths, refugees. Depending on the kind of disaster (train/plane accident, flood, earthquake) not only an acute emergency medicine treatment but also general and family medicine and hospital treatment have to be safeguarded over a longer time-period in the disaster area. PROBLEM: Regarding to a lot of organizations, institutions and disaster teams taking part in the disaster assistance is there any lack of work or data flow in the medical treatment? METHODS: From the ODRA flood 1997, the high speed train crash in ESCHEDE 1998, the DANUBE flood 1999 and the ELBE flood in 2002 experience reports were collected. They were analysed with emphasis on data and work flow in the medical treatment and its command system: Standardised command structure? Communication problems? Used communication lines? Language problems? Medical Intelligence distribution? Use of Patient Tracking System? Triage problems? RESULTS: The use of spoken radio communication causes transmission mistakes or misunderstandings and radio-overload and need connection-set-up-time for each call. Manual distribution of same data for many receivers using different communication lines causes a time shift in the up-to-date-information. Language problems during the ODRA flood between German and Polish people led to longer reaction times. Up-to-date triage results as well as up-to-date transportation and hospital information are necessary for medical evacuation. Compared with other reports about these disasters the quality of disaster management depends on the quality of communication and information. CONCLUSION: The use of health telematics in disaster response helps to cope with the scenario. Modern technologies provide support for building up medical aid although the normal infrastructure is destroyed. To cope with disaster scenarios there are some telematic tools which can be used:--Computer-based Command and Control System--Telemedical support --Data-ressources-network /Medical Intelligence. A further study is recommended to evaluate the real impact of using these telematic tools in a disaster.

Disaster Planning↗
PubMed1989

Clinical expert systems versus linear models: do we really have to choose?

This article deals with decision subsystems at the level of the organism. In recent years there has been debate as to whether linear models or clinical expert systems make clinical decisions more effectively. Previous articles in this journal have favored linear models. This article argues the opposite case. We show that expert systems are not necessarily more expensive or less accurate than linear models and that, in theory at least, they can perform many tasks that are beyond the scope of linear models. Indeed, while a linear model may serve as a subsystem of a human or computer expert system, an expert system cannot be seen as a subsystem of a linear model. We conclude that clinical expert systems and linear models are not interchangeable and users should not be forced to choose between them.

Artificial Intelligence↗
PubMed2002

In-vehicle communication systems: the safety aspect.

Communication and information technology are developing very rapidly at present. At the same time, the number of older drivers is increasing. When designing systems for elderly drivers, it has been shown that: (1) simplifying a task reduces performance differences between old and young; and (2) the optimization of onboard systems (better legibility and intelligibility of the information, simplified dialogue) in relation to the abilities of elderly drivers benefits the rest of the user population. Elderly people do not automatically reject new information and assistance technologies especially when the systems are user friendly. However, the ergonomics of these new technologies must be studied, with particular attention to the specific needs of the elderly, in order not to marginalize them

Aged↗
PubMedDate not supplied

Views of young people using augmentative and alternative communication systems.

Children with physical impairments who cannot use intelligible speech are often recommended augmentative and alternative communication (AAC) systems. In England and Wales, it is usually the job of speech and language therapists to support development in AAC skills. This paper reports findings from discussion with children and young people who use AAC systems concerning their attitudes and opinions towards the organization of speech and language therapy, the role of the speech and language therapist in school and issues concerned with AAC systems themselves. Six young adults and 17 children from London education authorities were interviewed on a one-to-one basis and in focus groups. Children were interviewed who had a communication aid incorporating at least 20 symbols and/or pictures and/or written words, language understanding at the two-word level and above, i.e. they demonstrated understanding of adult requests with at least two information carrying words. For children using communication aids, it is conceivable that their communication systems do not contain appropriate symbol vocabulary to express complex ideas, opinions and feelings. Consequently, a symbol-based interview tool was designed to allow children to express complex issues through visual means. Most children interviewed reported that their AAC system was useful to them. Further analysis of opinions revealed that negative attitudes towards AAC systems were primarily associated with operational issues (technical skills required to operate an AAC system) and issues of self-image/identity, and to some degree, with a lack of perceived benefit in interaction. In apparent contrast to therapists' preferred models of working, children and young people identified a preference for therapy organized on a one-to-one basis targeting linguistic and operational skills. It is suggested that more acceptable and individualized design of AAC systems could have implications for their use in school and other contexts. The value of service users' views in service planning and evaluation are discussed.

Adult↗
PubMed2000

A neural network architecture for visual selection.

This article describes a parallel neural net architecture for efficient and robust visual selection in generic gray-level images. Objects are represented through flexible star-type planar arrangements of binary local features which are in turn star-type planar arrangements of oriented edges. Candidate locations are detected over a range of scales and other deformations, using a generalized Hough transform. The flexibility of the arrangements provides the required invariance. Training involves selecting a small number of stable local features from a predefined pool, which are well localized on registered examples of the object. Training therefore requires only small data sets. The parallel architecture is constructed so that the Hough transform associated with any object can be implemented without creating or modifying any connections. The different object representations are learned and stored in a central module. When one of these representations is evoked, it "primes" the appropriate layers in the network so that the corresponding Hough transform is computed. Analogies between the different layers in the network and those in the visual system are discussed. Furthermore, the model can be used to explain certain experiments on visual selection reported in the literature.

Algorithms↗
PubMed1991

Prospects of expert systems in psychiatric diagnostics.

The paper deals in particular with the theoretical foundations of introducing computer technology and techniques into psychiatric diagnostics. It is done from the aspect of present expert systems of the type FEL-EXPERT, PCE expert, CODEX, etc., as well as from the aspect of a prospect for the future in connection with the development of systems of the so called artificial intelligence.

Expert Systems↗
PubMed1998

Cooperative knowledge evolution: a construction-integration approach to knowledge discovery in medicine.

In this paper, we perform a cognitive analysis of knowledge discovery processes. As a result of this analysis, the construction-integration theory is proposed as a general framework for developing cooperative knowledge evolution systems. We thus suggest that for the acquisition of new domain knowledge in medicine, one should first construct pluralistic views on a given topic which may contain inconsistencies as well as redundancies. Only thereafter does this knowledge become consolidated into a situation-specific circumscription and the early inconsistencies become eliminated. As a proof for the viability of such knowledge acquisition processes in medicine, we present the IDEAS system, which can be used for the intelligent documentation of adverse events in clinical studies. This system provides a better documentation of the side-effects of medical drugs. Thereby, knowledge evolution occurs by achieving consistent explanations in increasingly larger contexts (i.e., more cases and more pharmaceutical substrates). Finally, it is shown how prototypes, model-based approaches and cooperative knowledge evolution systems can be distinguished as different classes of knowledge-based systems.

Artificial Intelligence↗
PubMed1998

[Our challenge in Kagoshima University Hospital--development of more useful clinical laboratory].

In 1995, we newly developed a clinical laboratory system equipped with an expert system, which was named HIPOCLATES (Hospital Intelligent POwers of Clinical Laboratory Automation Technology with Expert System). Since this system includes an expert system, we have been able to support diagnostic and therapeutic procedure in clinics and begin developing a "zonal verification method" and "early-stage DIC diagnosis support system". The former is one of the individual quality control methods and we have attempted to develop a test assurance system in HIPOCLATES using this method. The latter system is to diagnosis DIC in the early phase. Here, we introduce the detail of our project using HIPOCLATES. Following the introduction HIPOCLATES, we attempted to develop a highly integrated system in physiological examinations, and succeeded in establishment PLATON (Physiological LAboratory TOtal Network system) in 1997. Thereafter, we planned a graphic reporting system named GALIREO (Graphic Assistant Laboratory Informational REport Operating system). In GALIREO, we attempted to connect the Department of Clinical Laboratory, Ultrasonic waves test room, Fiberscope test room, Department of Pathology and Surgical center by computer network. Developing these computer network system in our clinical laboratory we want to create electronic medical record linking with THINK (HIS in our hospital). We plan to make these expert system and electronic medical record available to clinical staff via a network to realize evidence-based medicine (EBM) and utilize these to support treatment and education.

Clinical Laboratory Information Systems↗
PubMed1995

[The use of the microcomputer in selecting the basic cause of death].

The article begins with a discussion of some mortality statistics issues, problems encountered in the manual selection of underlying cause of death, and also the increasing need for information on associated causes. These circumstances led the National Center for Health Statistics to develop the computerized ACME System, which has been in use in São Paulo State since 1983. The ACME System's requirement of a mainframe computer, as well as other operational limitations, has prevented its installation throughout the country. In order to standardize and improve the quality of mortality data in Brazil, the Informatics Department of the Ministry of Health's National Health Foundation and the World Health Organization (WHO) Collaborating Center for the Classification of Diseases in Portuguese developed the microcomputer-based Underlying Cause Selection System (SCB) in 1993. This is an expert system that employs artificial intelligence techniques to reproduce the reasoning of a coder in selecting the underlying cause of death, according to the rules and provisions of the Ninth Revision of the International Classification of Diseases. The SCB has a very user-friendly interface, occupies 2.6 megabytes of hard disk space, and can run on any 386 or higher XT or AT computer. In addition to selecting the underlying cause of death, the system stores data on associated conditions.

Artificial Intelligence↗