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 1,747 records · Page 97Linked to original sources
PubMed1991

Neural network analysis of serial cardiac enzyme data. A clinical application of artificial machine intelligence.

There has been a recent resurgence of interest in the study and application of computerized neural networks within the broad field of artificial intelligence. These "intelligent machines" are modeled after biological nervous systems and are fundamentally different from the many computerized expert systems that previously have been introduced as clinical decision-making aids. The authors describe a neural network designed and trained to predict the probability of acute myocardial infarction (AMI) based on the analysis of paired sets of cardiac enzymes. The neural network predicted 24 of 24 (100%) AMIs and 27 of 29 (93%) No-AMIs when compared with a pathologist's interpretation of the patient's laboratory data (P less than 0.000001). The authors attempted to validate the network's diagnoses by two independent methods. When compared with echocardiogram and EKG for diagnosis of AMI, the neural network agreed with the cardiologist's interpretation in 12 of 14 (86%) AMIs and 1 of 3 (33%) No-AMIs, but the correlation was not statistically significant. Using autopsy outcome for validation, the neural network agreed with the anatomic evidence in 24 of 26 (92%) AMIs and 4 of 6 (67%) No-AMIs (P = 0.001). The authors conclude that neural networks can be successfully applied to the analysis of cardiac enzyme data and suggest that broader applications exist within the domain of clinical decision support.

Amyloidosis↗
PubMedDate not supplied

Motor speech impairment in a case of childhood basilar artery stroke: treatment directions derived from physiological and perceptual assessment.

The perceptual and physiological characteristics of the speech of a nine year old child who suffered a basilar artery stroke at the age of five years were investigated using a battery of perceptual and physiological instrumental measures. Perceptual tests administered included the Frenchay Dysarthria Assessment, a perceptual analysis of a speech sample based on a reading of the Grandfather Passage and a phonetic intelligibility test. Instrumental procedures included: spirometric and kinematic analysis of speech breathing; electroglottographic evaluation of laryngeal function, nasometric assessment of velopharyngeal function and evaluation of lip and tongue function using pressure transducers. Physiological assessment indicated the most severe deficits to be in the respiratory and velopharyngeal sub-systems with significant deficits in the articulatory sub-system, all of which resulted in severely reduced intelligibility. These results were compared and contrasted with the subject's performance on the perceptual assessment battery. In a number of instances the physiological assessments were able to identify deficits in the functioning of components of the speech production apparatus either not evidenced by the perceptual assessments or where the findings of the various perceptual assessments were contradictory. The resulting comprehensive profile of the child's dysarthria demonstrated the value of using an assessment battery comprised of both physiological and perceptual methods. In particular, the need to include instrumental analysis of the functioning of the various subcomponents of the speech production apparatus in the assessment battery when defining the treatment priorities for children with acquired dysarthria is highlighted. Treatment priorities determined on the basis of both the perceptual and physiological assessments for the present CVA case are discussed.

Basilar Artery↗
PubMed1991

Managing Medical Logic Modules.

A key element of IAIMS development at the Columbia Presbyterian Medical Center (CPMC) is the Medical Logic Module (MLM), designed to provide decision support to clinical users. A standard has been established for MLMs, and a number of institutions have agreed in principle to share them. At CPMC, MLMs are under development and MLMs from other institutions are being reviewed. The Columbia Health Sciences Library has developed a management system for MLMs which supports both internal development and sharing of MLMs among institutions. This paper describes the elements of the MLM management system.

Artificial Intelligence↗
PubMed1993

Database techniques for biological materials & methods.

The Biological sciences produce an enormous research literature every year. Research papers are highly structured documents whose content is not captured using the traditional techniques of information retrieval: keywords and flat text. This is especially true of the Materials & Methods section of experimental papers. A great deal of highly structured information is packed into this section. It involves logical and temporal sequences of operations that combine and operate on materials using various instruments and depending on many parameters. We are designing and implementing databases that will allow this complex knowledge to be represented, stored in object-oriented databases and retrieved. We are developing an application of this technology called the Laboratory Notebook. This application is a software system that will contain personal laboratory information as well as have access to databases of Materials & Methods sections drawn from the literature.

Artificial Intelligence↗
PubMed2005

Alaryngeal speech aid using an intra-oral electrolarynx and a miniature fingertip switch.

We developed and evaluated an intra-oral electrolaryngeal speech aid system for those who could not acquire common alaryngeal speech or for early post-surgery speech rehabilitation. Our system consisted of a denture-base intra-oral vibrator, a wireless miniature fingertip switch and a controller. To produce natural speech, the fingertip switch produced binary commands of voicing and accent and the controller implemented the pitch generation model using the commands. We first estimated the intelligibility of consonant-vowel syllables produced by our system. We then obtained the feedback about the system from the Japanese users on the basis of their daily life use, and evaluated the possibility and acceptability as an alaryngeal speech aid. Although the users were less satisfied at the intra-oral electrolarynx, the intelligibility of the intra-oral electrolarygeal speech was comparable to that of transcervical electrolaryngeal speech, and most of them were willing to employ it if they lost their current electrolaryngeal speech. According to the feedbacks from the users, a completely wire-free system and less eye-catching designs would make the prosthesis more acceptable. These results placed the intra-oral electrolarynx as a useful option of alaryngeal speech aids and encouraged the further development of the intra-oral electrolarynx.

Aged↗
PubMed2004

The role of networks and artificial intelligence in nanotechnology design and analysis.

Techniques with their origins in artificial intelligence have had a great impact on many areas of biomedicine. Expert-based systems have been used to develop computer-assisted decision aids. Neural networks have been used extensively in disease classification and more recently in many bioinformatics applications including genomics and drug design. Network theory in general has proved useful in modeling all aspects of biomedicine from healthcare organizational structure to biochemical pathways. These methods show promise in applications involving nanotechnology both in the design phase and in interpretation of system functioning.

Artificial Intelligence↗
PubMed1982

The heat resistance of a ceramic identification device.

Identification of human remains by the teeth is a widely accepted forensic procedure. At present the principle dental technique used for identification of the dead is the post-mortem comparison method which involves a comparison of post-mortem dental findings and any available ante-mortem records. This study describes the results of an in vitro incineration investigation testing the heat resistance qualities of metallic intelligence data encoded on microchips comprising part of the Dentify system of identification. Detailed optical and scanning electron microscopic findings show that despite some alteration when exposed to high temperatures the metallic intelligence data itself remains clearly decipherable after exposure to a temperature of 1000 degrees C.

Ceramics↗
PubMed2005

Constructing Czechoslovakia: the meaning of "intelligence" in Czechoslovak educational discourse, 1900-1939.

Before World War II, Czechoslovakia went through its constituting process, including the development of an educational system. We made an analysis of Czechoslovak discussions about educational uses of intelligence tests from a discourse-theoretic and social constructionist perspective. In particular, we examined which connotations became associated with the concept "intelligence" in educational scientific publications about possible educational uses of the newly introduced tests in the years 1900-1939. Results substantiate the inextricable entwining of the meaning of "intelligence" with the unique characteristics of the historical situation in Czechoslovakia before World War II.

Attitude↗
PubMedDate not supplied

Using the ID3 algorithm to find discrepant diagnoses from laboratory databases of thyroid patients.

Rare cases are a central problem when an expert system is constructed from example cases with machine learning techniques. It is difficult to make a decision support system (DSS) to cover all possible clinical cases. An inductive learning program can be used to construct an expert system for detecting cases that differ from routine cases. The ID3 algorithm and the pessimistic pruning algorithm were tested in this study: a DSS was built directly from the data of patient records. A decision tree was generated, and the cases misclassified by the decision tree as compared with the classifications of a clinician were listed on a checklist, which formed the feedback to the clinician. In clinical situations about 5-10% of functional thyroid disorders may be misclassified. At this error level, the method found over 90% of the errors with a specificity of 95%. In simple medical classification tasks this dynamic self-learning system can be used to create a DSS that can assist in the quality control of clinical decision making.

Adult↗
PubMed1995

An object-oriented model for the integration of knowledge-based systems.

This paper discusses functional integration, data integration, and knowledge integration as basic problems concerning the integration of knowledge-based systems into a hospital information system. A system model for an integrated knowledge-based system is introduced. Object-oriented models for the systems meta-database, patient database, and knowledge-base are presented. It is expected that the reader is familiar with the basic concepts of the object-oriented approach.

Artificial Intelligence↗
PubMed2006

Intelligent semantic interoperability: Integrating knowledge, terminology and information models to support stroke care.

INTRODUCTION: Electronic patient record (EPR) systems for the continuity of care for stroke patient are under development. These systems are based on standards such as for clinical practice, vocabularies, and the HL7 information model. PROBLEM STATEMENT: In order to achieve intelligent semantic interoperability, knowledge about evidence based patient care, vocabulary and information models need to be integrated. METHODOLOGY: A format was developed in which the clinical knowledge, clinical terminology, and standard information models are integrated as specification for the technical implementation of electronic health systems and electronic messages. This format is verified by clinicians and technicians. RESULTS: The document structure consists of meta-information such as version control and changes, purpose of the clinical content, evidence from the literature, variables and values, terminology used, guidelines for application and interpretation, HL7 message models, coding, and technical data specification. Further, XML message excerpts, archetypes and screen designs are developed from these documents to facilitate implementation. CONCLUSION: The combination of these aspects in one document creates valuable content for intelligent semantic interoperability by means of development of messages and systems.

Continuity of Patient Care↗
PubMed2005

Getting to the point: developing IT for the sharp end of healthcare.

Healthcare demonstrates the same properties of risk, complexity, uncertainty, dynamic change, and time-pressure as other high hazard sectors including aviation, nuclear power generation, the military, and transportation. Unlike those sectors, healthcare has particular traits that make it unique such as wide variability, ad hoc configuration, evanescence, resource constraints, and governmental and professional regulation. While healthcare's blunt (management) end is more easily understood, the sharp (operator) end is more difficult to research the closer one gets to the sharp end's point. Understanding sharp end practice and cognitive work can improve computer-based systems resilience, which is the ability to perform despite change and challenges. Research into actual practice at the sharp end of healthcare will provide the basis to understand how IT can support clinical practice. That understanding can be used to develop computer-based systems that will act as team players, able to support both individual and distributed cognitive work at healthcare's sharp end.

Artificial Intelligence↗
PubMed1994

Visual, auditory, and somatosensorial evoked potentials in early and late treated adolescents with phenylketonuria.

Pattern reversal visual, auditory, and somatosensorial evoked potentials were recorded in two groups of phenylketonuric (PKU) adolescents after protracted exposition to high concentrations of phenylalanine following diet discontinuation. The first group consisted of 11 early treated (before age 3 months) PKU patients (ET-PKU); the second group consisted of 11 late detected (after age 8 months), symptomatic, PKU subjects (LT-PKU). Despite the relevant lag between the two groups in mental development and neurological status, no clear-cut difference in evoked potentials could be detected. Only the wave I latency of the brainstem auditory evoked potentials (BAEPs) was significantly shorter in ET- versus LT-PKU children. The P100 latency, I-V interpeak latency (IPL), and I-III IPL seem to discriminate the less severe form of PKU (ET-PKU type 3) from the most severe forms, ET-PKU type 1 plus 2 and LT-PKU. No correlations were found between clinical, biochemical, and neurophysiological parameters. The present data suggest that evoked potentials technique is of limited sensitivity in detecting central nervous system (CNS) alterations in PKU adolescents after diet discontinuation.

Adolescent↗
PubMed1995

The OpenLabs approach to clinical laboratory computing.

This paper describes the architectural infrastructure to support a number of advanced functionalties for the clinical laboratory developed by OpenLabs. This infrastructure is based on an open distributed computing platform. A brief overview is given of the advanced functionalities provided by the OpenLabs modules through the novel application of knowledge-based systems, databases, and telematics; we also describe the communications architecture which allows these modules to interoperate with each other and with existing Laboratory Information Systems and instruments. The OpenLabs approach to the provision of generic interfaces to such existing systems is described, together with the OpenLabs Service Manager which supports the automated management of the laboratory in this distributed computing environment.

Artificial Intelligence↗
PubMedDate not supplied

Metareasoning and meta-level learning in a hybrid knowledge-based architecture.

Ahybrid knowledge-based architecture integrates different problem solvers for the same (sub)task through a control unit operating at a meta-level, the metareasoner, which coordinates the use of, and the communication between, the different problem solvers. A problem solver is defined to be an association between a knowledge intensive (sub)task, an inference mechanism and a knowledge domain view operated by the inference mechanism in order to perform the (sub)task. Important issues in a hybrid system are the metareasoning and learning aspects. Metareasoning encompasses the functions performed by the metareasoner, while learning reflects the ability of the system to evolve on the basis of its experiences in problem solving. Learning occurs at different levels, learning at the meta-level and learning at the level of the specific problem solvers. Meta-level learning reflects the ability of the metareasoner to improve the overall performance of the hybrid system by improving the efficiency of meta-level tasks. Meta-level tasks include the initial planning of problem solving strategies and the dynamic adaptation of chosen strategies depending on new events occurring dynamically during problem solving. In this paper we concentrate on metareasoning and meta-level learning in the context of a hybrid architecture. The theoretical arguments presented in the paper are demonstrated in practice through a hybrid knowledge-based prototype system for the domain of breast cancer histopathology.

Algorithms↗
PubMedDate not supplied

Human meaning of medical informatics: reflections on its future and trends.

The philosophy underlying medical informatics, and indeed information systems in general, is discussed. The need for integrating concepts is considered, and particular emphasis is placed on the avoidance of fragmentation and overspecialization. Human and artificial intelligence are compared and contrasted. It is shown that human intellectual activity cannot be reduced to a set of formal computations. The main emphasis of this paper is that the unique properties of human intelligence should not be devalued or ignored in attempts to promote machine systems in unappropriate areas.

Artificial Intelligence↗
PubMed1994

Information integration in a decision support system.

Electronic medical records pose a challenge because of the complex types of data which are included. Decision support systems must be able to deal effectively with these data types. In the expert system demonstrated here, a diversity of data types are included. These data are processed by three different methods. However, the different methods of processing are transparent to the user. An overall rule-based interface integrates the different methods into one comprehensive system.

Artificial Intelligence↗
PubMed1995

Problems of knowledge acquisition automation in medical expert systems.

Certain problems exist in the automation of knowledge acquisition (identification of phenomena, their description, formalization and coding), for medical diagnosis, therapy and scientific investigations. Issues concern the comparison of various approaches and their ability to be implemented and utilized.

Artificial Intelligence↗