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 1,423 records · Page 79Linked to original sources
PubMed1998

Implantable control, telemetry, and solar energy system in the moving actuator type total artificial heart.

The moving actuator type total artificial heart (TAH) developed in the Seoul National University has numerous design improvements based upon the digital signal processor (DSP). These improvements include the implantability of all electronics, an automatic control algorithm, and extension of the battery run-time in connection with an amorphous silicon solar system (SS). The implantable electronics consist of the motor drive, main processor, intelligent Li ion battery management (LIBM) based upon the DSP, telemetry system, and transcutaneous energy transmission (TET) system. Major changes in the implantable electronics include decreasing the temperature rise by over 21 degrees C on the motor drive, volume reduction (40 x 55 x 33 mm, 7 cell assembly) of the battery pack using a Li ion (3.6 V/cell, 900 mA.h), and improvement of the battery run-time (over 40 min) while providing the cardiac output (CO) of 5 L/min at 100 mm Hg afterload when the external battery for testing is connected with the SS (2.5 W, 192.192, 1 kg) for the external battery recharge or the partial TAH drive. The phase locked loop (PLL) based telemetry system was implemented to improve stability and the error correction DSP algorithm programmed to achieve high accuracy. A field focused light emitting diode (LED) was used to obtain low light scattering along the propagation path, similar to the optical property of the laser and miniature sized, mounted on the pancake type TET coils. The TET operating resonance frequency was self tuned in a range of 360 to 410 kHz to provide enough power even at high afterloads. An automatic cardiac output regulation algorithm was developed based on interventricular pressure analysis and carried out in several animal experiments successfully. All electronics have been evaluated in vitro and in vivo and prepared for implantation of the TAH. Substantial progress has been made in designing a completely implantable TAH at the preclinical stage.

Algorithms↗
PubMed1998

Personal Active Noise Reduction with integrated Speech Communication devices: development and assessment.

Active noise reduction is a successful addition to passive eardefenders for improvement of the sound attenuation at low frequencies. Assessment methods are discussed, focused on subjective and objective attenuation measurements, stability, and on high noise level applications. Active noise reduction systems are suitable for integration with an intercom. For this purpose the intelligibility in combination with environmental noise is evaluated. Development of a system includes the acoustical design, the feedback amplifier, and the speech input facility. An example of such a development is discussed. Finally the performance of some commercial systems and a laboratory prototype are compared.

Journal Article↗
PubMed1995

Using belief networks to enhance sharing of medical knowledge between sites with variations in data accuracy.

Differences in data definition between sites are a known obstacle to sharing of reminder-system rule sets. We identify another data characteristic--data accuracy--with implications for sharing. We reviewed the literature on data accuracy and found reports of high error rates for many data classes used by reminder systems (e.g., problem lists). The accuracy of other, equally important, data classes had not been characterized. Wide variations in accuracy between sites has been observed, suggesting that such differences may pose a previously unrecognized barrier to sharing of reminder rules. We propose a belief-network model for encoding reminder rules that explicitly models site-specific data accuracy and we discuss how encoding knowledge in this format may lower the cost and effort required to share reminder rules between sites.

Artificial Intelligence↗
PubMed2004

A patterned approach for linking knowledge-based systems to external resources.

Knowledge-based systems (KBSs) have been developed and used in industry and government as assistance systems, voting partner systems, and embedded applications. As web-based systems change the face of software implementations, these closed, internal KBSs need to be integrated into multicomponent applications that provide updated and extensible services. Therefore, KBSs must be adapted to an environment in which data and control are exchanged with external processes and resources; complementing other participating systems or using them to refine its own results. This integration can be a daunting task. If improperly done, it can result in an inefficient and unmanageable composite application. One approach to simplifying this task is the use of architectural patterns for integration. These patterns are assembled from functional entities that resolve component interoperability conflicts. In this paper, we describe an architectural pattern called the Knowledge Director pattern, which directs the integration of a closed KBS into a broader application environment.

Artificial Intelligence↗
PubMed1991

A model for critiquing based on automated medical records.

We describe the design of a critiquing system, HyperCritic, that relies on automated medical records for its data input. The purpose of the system is to advise general practitioners who are treating patients who have hypertension. HyperCritic has access to the data stored in a primary-care information system that supports a fully automated medical record. Hyper-Critic relies on data in the automated medical record to critique the management of hypertensive patients, avoiding a consultation-style interaction with the user. The first step in the critiquing process involves the interpretation of the medical record in an attempt to discover the physician's actions and decisions. After detecting the relevant events in the medical record, HyperCritic views the task of critiquing as the assignment of critiquing statements to these patient-specific events. Critiquing statements are defined as recommendations involving one or more suggestions for possible modifications in the actions of the physician. The core of the model underlying HyperCritic is that the process of generating the critiquing statements is viewed as the application of a limited set of abstract critiquing tasks. We distinguish four categories of critiquing tasks: preparation tasks, selection tasks, monitoring tasks, and responding tasks. The execution of these critiquing tasks requires specific medical factual knowledge. This factual knowledge is separated from the critiquing tasks and is stored in a medical fact base. The principal advantage demonstrated by HyperCritic is the adaption of a domain-independent critiquing structure. We show how this domain-independent critiquing structure can be used to facilitate knowledge acquisition and maintenance of the system.

Artificial Intelligence↗
PubMed2005

Evaluation of biomedical text-mining systems: lessons learned from information retrieval.

Biomedical text-mining systems have great promise for improving the efficiency and productivity of biomedical researchers. However, such systems are still not in routine use. One impediment to their development is the lack of systematic and rigorous evaluation, comparable to the approaches developed for information retrieval systems. The developers of text-mining systems need to improve both test collections for system-oriented evaluation and undertake user-oriented evaluations to determine the most effective use of their systems for their intended audience.

Algorithms↗
PubMed2000

Comparison of two knowledge bases on the detection of drug-drug interactions.

This paper describes a drug ordering decision support system that helps with the prevention of adverse drug events by detecting drug-drug interactions in drug orders. The architecture of the system was devised in order to facilitate its use attached to physician order entry systems. The described model focuses in issues related to knowledge base maintenance and integration with external systems. Finally, a retrospective study was performed. Two knowledge bases, developed by different academic centers, were used to detect drug-drug interactions in a dataset with 37,237 drug prescriptions. The study concludes that the proposed knowledge base architecture enables content from other knowledge sources to be easily transferred and adapted to its structure. The study also suggests a method that can be used on the evaluation and refinement of the content of drug knowledge bases.

Artificial Intelligence↗
PubMed1993

ColiGene: object-centered representation for the study of E coli gene expressivity by sequence analysis.

ColiGene is an object-centered knowledge base for the study of gene expressivity in Escherichia coli by DNA sequence analysis. This system was developed with the knowledge base management system SHIRKA. Objects represented in ColiGene are biological structures such as genes or regulatory signals. They are organized in a hierarchical structure of classes, subclasses and instances. Navigation through the knowledge base and the building of queries are made using a graphical interface. The base is coupled with the data base ACNUC which structures a specialized collection of sequences: EcoSeq. Several tools are also associated to ColiGene, either for sequence analysis or for a more general purpose. Some biological results have been obtained using ColiGene which are summarized here.

Artificial Intelligence↗
PubMed2003

Computer-assisted diagnosis system in digestive endoscopy.

The purpose of this paper is to present an intelligent atlas of indexed endoscopic lesions that could be used in computer-assisted diagnosis as reference data. The development of such a system requires a mix of medical and engineering skills for analyzing and reproducing the cognitive processes that underlie the medical decision-making process. The analysis of both endoscopists experience and endoscopic terminologies developed by professional associations shows that diagnostic reasoning in digestive endoscopy uses a scene-object approach. The objects correspond to the endoscopic findings and the medical context of examination and the scene to the endoscopic diagnosis. According to expert assessment, the classes of endoscopic findings and diagnoses, their primitive characteristics (or indices), and their relationships have been listed. Each class describes an endoscopic finding or diagnosis in an intensive way. The retrieval method is based on a similarity metric that estimates the membership value of the case under investigation and the prototype of the class. A simulation test with randomized objects demonstrates a good classification of endoscopic findings. The correct class is the unique response in 68% of the tested objects, the first of multiple responses in 28%. Four descriptors are shown to be of major importance in the classification algorithm: anatomic location, shape, color, and relief. At the present time, the application database contains approximately 150 endoscopic images and is accessible via Internet. Experiments are in progress with endoscopists for the validation of the system and for the understanding of the similarity between images. The next step will integrate the system in a learning tool for junior endoscopists.

Algorithms↗
PubMedDate not supplied

Design of a computer-assisted programme supporting the selection and clinical management of patients referred for liver transplantation.

The paper describes the knowledge-base of the expert system OLT 1, developed to support medical decision-making in patients referred for liver transplantation. The paper goes through the real clinical problems, and describes both structural (organization of the domain knowledge) and functional aspects (reasoning algorithm and strategies for clinical decision). According to the programme, patients referred to Liver Transplant Centres may be enrolled and ranked in the waiting list, included in a stand-by list for treatment and re-evaluation, or discharged. All decisions are made on the basis of well-assessed and objective criteria.

Aged↗
PubMed1995

Coding systems and controlled vocabularies for hospital information systems.

Modern healthcare information systems are requested to support an increasing interaction among professionals (inside and across the borders of the hospital) and a growing integration of specialised tasks (provision of care, reimbursement, document retrieval, optimisation of resource use, clinical audit, etc.). Coding systems were conceived and optimised independently for various specific purposes. They are now facing each other and thus conflicting into this new environment; the solution will be in a more application-independent representation of concepts. Developments are going towards three complementary directions: (i) to separate different functions about the management of terms and concepts, and thus to produce more specialised software components; (ii) to develop a new class of software which is able to manage terminological diversity without imposing uniformity; and (iii) to enhance reusability of concepts, and facilitate a spontaneous convergence among controlled vocabularies.

Artificial Intelligence↗
PubMed2001

Hybrid expert system for decision supporting in the medical area: complexity and cognitive computing.

This paper proposes a hybrid expert system (HES) to minimise some complexity problems pervasive to the artificial intelligence such as: the knowledge elicitation process, known as the bottleneck of expert systems; the model choice for knowledge representation to code human reasoning; the number of neurons in the hidden layer and the topology used in the connectionist approach; the difficulty to obtain the explanation on how the network arrived to a conclusion. Two algorithms applied to developing of HES are also suggested. One of them is used to train the fuzzy neural network and the other to obtain explanations on how the fuzzy neural network attained a conclusion. To overcome these difficulties the cognitive computing was integrated to the developed system. A case study is presented (e.g. epileptic crisis) with the problem definition and simulations. Results are also discussed.

Algorithms↗
PubMed1997

A decision-driven design of a decision support system in anesthesia.

We present a new approach to the design of a decision support system (DSS) in anesthesia which converts the available data to relevant information. Instead of a patient-driven design (patient modelling), we use a decision-driven design (anesthetist modelling). This approach results in a system consisting of three stages. First, the incoming data is validated to ensure reliable further processing for both DSS and anesthetist. Second, the validated data is analyzed to detect patterns that could trigger the anesthetist's response. Finally, from these patterns a strategic selection is made and offered to the anesthetist as information relevant for the decision that has to be made in the current context. Results show that this approach is feasible, but further evaluation is necessary before practical application is possible.

Algorithms↗
PubMed1996

Database and knowledge base integration in decision support systems.

Since decision support systems (DSS) in medicine often are linked to clinical databases it is important to find methods that facilitate the work for DSS developers to implement database queries in the knowledge base (KB). This paper presents a method for linking clinical databases to a KB with Arden Syntax modules. The method is based on a query meta database including templates for SQL queries. During knowledge module authoring the medical expert only refers to a code in the query meta database. Our method uses standard tools so it can be implemented on different platforms and linked to different clinical databases.

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↗
PubMed2006

Multicue HMM-UKF for real-time contour tracking.

We propose an HMM model for contour detection based on multiple visual cues in spatial domain and improve it by joint probabilistic matching to reduce background clutter. It is further integrated with unscented Kalman filter to exploit object dynamics in nonlinear systems for robust contour tracking.

Algorithms↗
PubMed2000

From a urinalysis strategy to an evaluated urine protein expert system.

Urine single protein analysis has developed into a routine method for the screening and monitoring of kidney diseases. In order to support clinical decision making by an interpretative report, a urine protein expert system (UPES) has been developed. Based on a database containing more than 500 excretion patterns, a modular knowledge base was extracted in production rules and implemented in a modern expert system shell. The resulting interpretation system has been thoroughly verified and validated. After the need of interpretation of the complex findings had been documented in a survey, its usability in routine and its knowledge representation was evaluated in 11 hospitals. A user conference confirmed a high quality level of the reports proposed by UPES. It revealed that the problem of automatic data transfer as well as the common definition of diagnostic terms by laboratorians and clinicians play a crucial role for the use of knowledge-based systems in laboratory medicine.

Artificial Intelligence↗
PubMed2005

Integrating relevance feedback techniques for image retrieval using reinforcement learning.

Relevance feedback (RF) is an interactive process which refines the retrievals to a particular query by utilizing the user's feedback on previously retrieved results. Most researchers strive to develop new RF techniques and ignore the advantages of existing ones. In this paper, we propose an image relevance reinforcement learning (IRRL) model for integrating existing RF techniques in a content-based image retrieval system. Various integration schemes are presented and a long-term shared memory is used to exploit the retrieval experience from multiple users. Also, a concept digesting method is proposed to reduce the complexity of storage demand. The experimental results manifest that the integration of multiple RF approaches gives better retrieval performance than using one RF technique alone, and that the sharing of relevance knowledge between multiple query sessions significantly improves the performance. Further, the storage demand is significantly reduced by the concept digesting technique. This shows the scalability of the proposed model with the increasing-size of database.

Algorithms↗