Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “artificial intelligence”

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 1,621 records · Page 90Linked to original sources
PubMed1995

Control theory as a conceptual framework for intensive care monitoring.

Monitoring patients hospitalized in hemato-oncology departments to undergo clinical protocols of therapy is a complex task. The main difficulty arises in the management of the oncology protocol as well as in the management of critical episodes of acute illness which frequently occur due to high toxicity of the used antimitotics. This problem of controlling a patient's condition can be conceptualized within the control theory paradigm as the task of controlling a process whose state changes over time and can deviate unacceptably from a normal range. Upon request of a French clinical department of hemato-oncology, we developed an intelligent patient monitor named SEPIA to assist clinicians in this task. Following the control theory analogy at the level of knowledge bases design, we have modeled the medical knowledge as control information to represent the medical actions, and state information is used as feedback control to characterize the patient's state. After a general presentation of SEPIA, the analogies between control theory actors and SEPIA's components are specified. The article then focuses on state variables representation. The data reduction process, activated as new data are given to the system, is described. A simulated running session is finally presented to illustrate the whole reasoning process.

Algorithms↗
PubMedDate not supplied

Neural networks in radiology: an introduction and evaluation in a signal detection task.

Neural networks are a computer architecture, implementable in software or hardware, that allow an entirely new approach to the computerized perception of data. These so-called connectionist models are inspired by what is known about the architecture of biological neurons, in which the "intelligence" or processing capability of the network is a result of the interconnection strengths between large arrays of nonlinear processing nodes. Neural networks are described and then are used to analyze the common radiological problem of pattern recognition on a noisy background. Classical signal detection theory is used to compare network performance against that of human observers, using computer-generated sets of very simple "nodules." The neural network performed with better accuracy, relative to human observer performance, in the detection of this elementary test object. Although these results may not scale up with more complex images, the favorable performance of neural networks at this level suggests that further investigation is warranted.

Artificial Intelligence↗
PubMed1999

Dynamic and static approaches to clinical data mining.

In sequential diagnosis, the usefulness of a test can be assessed only in the context of a chosen diagnostic strategy, and depends on the evidence provided by previous test results. Choosing the most useful test at each stage of the evidence-gathering process therefore requires a dynamic approach to data analysis. An implementation of such an approach in an intelligent program for sequential diagnosis based on the evidence-gathering strategies used by doctors is described. On the other hand, a static approach to data analysis is appropriate in the discovery of knowledge required, for example, to explain or justify a diagnosis by identifying the most important findings, both positive and negative, on which the diagnosis is based. An algorithm for the discovery of features which always provide evidence in favour of, or against, a diagnosis selected by the data miner is presented. Dominance relationships among features in the data set are also discovered such that if one feature dominates another, it always provides more evidence in favour of the diagnosis, or less evidence against it.

Abdominal Pain↗
PubMed2004

Universal electronic health record MUDR.

One of the important research tasks of the European Centre for Medical Informatics, Statistics and Epidemiology - Cardio (EuroMISE Centre - Cardio) is the applied research in the field of electronic health record design including electronic medical guidelines and intelligent systems for data mining and decision support. The research in the field of data storage and data acquisition was inspired by several European projects and standards, mostly by the I4C and TripleC projects. Based on experience gathered during cooperation in the TripleC project we have proposed a description of a flexible information storage model. The motivation for this effort was the large variability of the set of collected features in different departments - including temporal variability. Therefore, a dynamically extensible and modifiable structure of items is needed. In our model we use two basic structures called the knowledge base and data files. The main function of the knowledge base is to express the hierarchy of collectable features - medical concepts, their characteristics and relations among them. The data files structure is used to store the patient's data itself. These two structures can be described using graph theory expressions. Based on this model, a three-layer system architecture named "Multimedia Distributed Record" (MUDR) has been proposed and implemented. During the implementation, modern technologies such as Web Services, SOAP and XML were used. For the practical usage of EHR MUDR, an intelligent application called MUDRc (MUDR Client) was created. It enables physicians to use EHR MUDR in a flexible way. During the development process, maximum emphasis was placed on user-friendliness and comfortable usage of this application. Several methods of data entry can be used: pre-defined forms, direct entry into the tree data structure of the EHR MUDR, or automatic unstructured free-text report parsing and data retrieval. The system enables fast and simple importing and exporting of data as well. The system integrates modern multimedia formats (X-ray photos, sonography and other pictures, video-sequences, audio records) as well as progressive methods of decision support systems realized by medical guidelines and other modules.

Artificial Intelligence↗
PubMed2006

Temporal abstraction in intelligent clinical data analysis: a survey.

OBJECTIVE: Intelligent clinical data analysis systems require precise qualitative descriptions of data to enable effective and context sensitive interpretation to take place. Temporal abstraction (TA) provides the means to achieve such descriptions, which can then be used as input to a reasoning engine where they are evaluated against a knowledge base to arrive at possible clinical hypotheses. This paper surveys previous research into the development of intelligent clinical data analysis systems that incorporate TA mechanisms and presents research synergies and trends across the research reviewed, especially those associated with the multi-dimensional nature of real-time patient data streams. The motivation for this survey is case study based research into the development of an intelligent real-time, high-frequency patient monitoring system to provide detection of temporal patterns within multiple patient data streams. RESULTS: The survey was based on factors that are of importance to broaden research into temporal abstraction and on characteristics we believe will assume an increasing level of importance for future clinical IDA systems. These factors were: aspects of the data that is abstracted such as source domain and sample frequency, complexity available within abstracted patterns, dimensionality of the TA and data environment and the knowledge and reasoning underpinning TA processes. CONCLUSION: It is evident from the review that for intelligent clinical data analysis systems to progress into the future where clinical environments are becoming increasingly data-intensive, the ability for managing multi-dimensional aspects of data at high observation and sample frequencies must be provided. Also, the detection of complex patterns within patient data requires higher levels of TA than are presently available. The conflicting matters of computational tractability and temporal reasoning within a real-time environment present a non-trivial problem for investigation in regard to these matters. Finally, to be able to fully exploit the value of learning new knowledge from stored clinical data through data mining and enable its application to data abstraction, the fusion of data mining and TA processes becomes a necessity.

Artificial Intelligence↗
PubMedDate not supplied

Brain-based devices for the study of nervous systems and the development of intelligent machines.

The simultaneous study of brain function at all levels of organization is difficult to undertake with current experimental tools. Present day electrophysiology only allows the recording of at most hundreds of neurons while an animal is performing a behavioral task. Because of this limitation and the sheer complexity of the nervous system, computational modeling has become essential in developing theories of brain function. Accordingly, our group has constructed a series of brain-based devices (BBDs), that is, physical devices with simulated nervous systems that guide behavior, to serve as a heuristic for testing theories of brain function. Unlike animal models, BBDs permit analysis of activity at all levels of the nervous system as the device behaves in its environment. Although the principal focus of developing BBDs has been to test theories of brain function, this type of modeling may also provide a basis for robotic design and practical applications.

Artificial Intelligence↗
PubMed1997

Evaluation of a medical diagnosis system using simulator test scenarios.

This paper describes an informal but systematic method for how to test and verify a knowledge-based system in a large open-ended medical target domain. The system used is Guardian, an intelligent system for monitoring and diagnosis of post-cardiac surgery patients in an intensive-care unit. The knowledge base is tested and verified by running the system on a series of realistic test scenarios, both with an embedded simulator and with an external simulation system. The same scenarios are presented to human test subjects, making it possible to compare and analyze the performance of the knowledge-based system with that of human physicians. The use of simulators instead of clinical data also means that it is possible to test crucial scenarios which occur seldom in medical practice. Our results show that a system like Guardian might indeed be useful in medical care.

Artificial Intelligence↗
PubMed2004

AutoTutor: a tutor with dialogue in natural language.

AutoTutor is a learning environment that tutors students by holding a conversation in natural language. AutoTutor has been developed for Newtonian qualitative physics and computer literacy. Its design was inspired by explanation-based constructivist theories of learning, intelligent tutoring systems that adaptively respond to student knowledge, and empirical research on dialogue patterns in tutorial discourse. AutoTutor presents challenging problems (formulated as questions) from a curriculum script and then engages in mixed initiative dialogue that guides the student in building an answer. It provides the student with positive, neutral, or negative feedback on the student's typed responses, pumps the student for more information, prompts the student to fill in missing words, gives hints, fills in missing information with assertions, identifies and corrects erroneous ideas, answers the student's questions, and summarizes answers. AutoTutor has produced learning gains of approximately .70 sigma for deep levels of comprehension.

Algorithms↗
PubMed1991

A specialized framework for Medical Diagnostic Knowledge Based Systems.

To have a knowledge based system (KBS) exhibiting an intelligent behavior, it must be endowed even with knowledge able to represent the expert's strategies, other than with domain knowledge. The elicitation task is inherently difficult for strategic knowledge, because strategy is often tacit, and, even when it has been made explicit, it is not an easy task to describe it in a form that may be directly translated and implemented into a program. This paper describes a Specialized Framework for Medical Diagnostic Knowledge Based Systems able to help an expert in the process of building KBSs in a medical domain. The framework is based on an epistemological model of diagnostic reasoning which has proved to be helpful in describing the diagnostic process in terms of the tasks by which it is composed of.

Artificial Intelligence↗
PubMed1996

A Dutch medical language processor.

This paper describes the current state of a medical language processor for Dutch. The goal is to implement a language specific front-end compatible with some existing applications that aim at the intelligent extraction and processing of information from patient discharge summaries. A complete chain for processing and understanding Dutch medical documents will be the ultimate result. The text focuses mainly on the language specific aspects of the language processing chain. Evaluation results of the already functioning components are given as well as an outline for future developments and enhancements. A short theoretical background is provided (cf. also [1-3]: Rossi Mori et al., Proc. SCAMC 90, 1990, pp. 185-189; Wingert, in: Informatics and Medicine, an advanced course, Springer-Verlag. 1977, pp. 579-646; Wingert, Proc. MEDINFO 80, 1980, pp. 1321-1331) before the description of each component in order to familiarise the non-experienced reader with the basic notions of computational linguistics.

Artificial Intelligence↗
PubMed2005

Automated mapping of local radiology terms to LOINC.

We developed an automated tool, called the Intelligent Mapper (IM), to improve the efficiency and consistency of mapping local terms to LOINC. We evaluated IM's performance in mapping diagnostic radiology report terms from two hospitals to LOINC by comparing IM's term rankings to a manually established gold standard. Using a CPT-based restriction, for terms with a LOINC code match, IM ranked the correct LOINC code first in 90% of our development set terms, and in 87% of our test set terms. The CPT-based restriction significantly improved IM's ability to identify correct LOINC codes. We have made IM freely available, with the aim of reducing the effort required to integrate disparate systems and helping move us towards the goal of interoperable health information exchange.

Artificial Intelligence↗
PubMed2000

The future of bedside monitoring.

Today's intensivists are provided with more information than ever before, yet current monitors present data from multiple sources in a relatively raw form with virtually no intelligent data integration and processing. In the next century, technological advances in miniaturization, biosensors and computer processing, coupled with an improved understanding of critical illnesses at the molecular level, will lead to the development of a new generation of monitors. Monitoring will move from the traditional macroscopic invasive approach to a noninvasive, molecular analysis of evolving critical disease processes. It is likely that disturbances in homeostasis will become known immediately or before they would otherwise be manifest clinically. Nanotechnology will permit monitoring of critical changes in the intracellular environment or the by-products of cellular metabolism and signal messaging. This article discusses monitoring technologies that hold promise for further development in the next century and point out techniques likely to be abandoned.

Artificial Intelligence↗
PubMed1996

An intelligent system for the diagnosis of complex images.

An intelligent system suitable to perform a computer aided diagnosis of complex images should have a knowledge base containing all information related both to the images to be interpreted and to their symbolic description. In this paper, a system able to classify unknown medical digital images into four classes is proposed (searched pathology recognized, searched pathology absent, different pathology from the searched one recognized, unknown pathology). A main component of this system is a knowledge base that, startling from information deduced from sample images, can be processed to create synthetic reference models that, in turn, permit the interpretation of real scenes. The system has been tested on digitized plain film of the thorax, in order to perform a computer-aided diagnosis of pneumothorax cases.

Artificial Intelligence↗
PubMed2005

Qualitative map learning based on covisibility of objects.

Autonomous map construction is one of the most fundamental and significant issues in intelligent mobile robot research. While a variety of map construction methods have been proposed, most require some quantitative measurements of the environment and a mechanism of precise self-localization. This paper proposes a novel map construction method using only qualitative information about "how often two objects are observed simultaneously." This method is based on heuristics--"closely located objects are likely to be seen simultaneously more often than distant objects" and a well-known multivariate data analysis technique-multidimensional scaling. A significant feature of this method is that it requires neither quantitative sensor measurements nor information about the robot's own position. Simulation and experimental results demonstrated that this method is sufficiently practical for capturing a qualitative spatial relationship among identifiable landmark objects rapidly.

Algorithms↗
PubMed2002

Body Area Network BAN--a key infrastructure element for patient-centered medical applications.

The Body Area Network (BAN) concept enables wireless communication between several miniaturized, intelligent Body Sensor (or actor) Units (BSU) and a single Body Central Unit (BCU) worn at the human body. A separate wireless transmission link from the BCU to a network access point--using different technology--provides for online access to BAN data via usual network infrastructure. BAN is expected to become a basic infrastructure element for service-based electronic health assistance: By integrating patient-attached sensors and control of mobile dedicated actor units, the range of medical workflow can be extended by wireless patient monitoring and therapy support. Beyond clinical use, professional disease management environments, and private personal health assistance scenarios (without financial reimbursement by health agencies/insurance companies), BAN enables a wide range of health care applications and related services.

Artificial Intelligence↗
PubMed2005

[Study on intelligent system of hyper-spectral data gathering based on GPS in farm machinery].

In order to meet the precision agriculture needs that highly dense and overall farmland information is gathered, this system uses Visual Basic and Map-Objects to carry on integration of GPS, GIS and RS. On the one hand, the system can provide the space seat attribute of high precision for the spectral data gathered by way of integration GPS, and realizes integration in spectrum data gathering, orientation and storage. On the other hand, by way of integrated GIS, the system has realized the function of visualizing analysis and management of the spectrum data, displaying real-time trace of moving point, providing some related attribute of the moving point in map layers, and calculating crop derivative spectra and crop vegetation index NDVI etc. The sufficient information is put forward for expert system and decision support system of precision agriculture.

Agriculture↗
PubMed2005

SVD-based optimal filtering for noise reduction in dual microphone hearing aids: a real time implementation and perceptual evaluation.

In this paper, the first real-time implementation and perceptual evaluation of a singular value decomposition (SVD)-based optimal filtering technique for noise reduction in a dual microphone behind-the-ear (BTE) hearing aid is presented. This evaluation was carried out for a speech weighted noise and multitalker babble, for single and multiple jammer sound source scenarios. Two basic microphone configurations in the hearing aid were used. The SVD-based optimal filtering technique was compared against an adaptive beamformer, which is known to give significant improvements in speech intelligibility in noisy environment. The optimal filtering technique works without assumptions about a speaker position, unlike the two-stage adaptive beamformer. However this strategy needs a robust voice activity detector (VAD). A method to improve the performance of the VAD was presented and evaluated physically. By connecting the VAD to the output of the noise reduction algorithms, a good discrimination between the speech-and-noise periods and the noise-only periods of the signals was obtained. The perceptual experiments demonstrated that the SVD-based optimal filtering technique could perform as well as the adaptive beamformer in a single noise source scenario, i.e., the ideal scenario for the latter technique, and could outperform the adaptive beamformer in multiple noise source scenarios.

Adult↗
PubMed2005

Intelligent initialization of resource allocating RBF networks.

In any neural network system, proper parameter initialization reduces training time and effort, and generally leads to compact modeling of the process under examination, i.e. less complex network structures and better generalization. However, in cases of multi-dimensional data, parameter initialization is both difficult and time consuming. In the proposed scheme a novel, multi-dimensional, unsupervised clustering method is used to properly initialize neural network architectures, focusing on resource allocating networks (RAN); both the hidden and output layer parameters are determined by the output of the clustering process, without the need for any user interference. The main contribution of this work is that the proposed approach leads to network structures that are compact, efficient and achieve best classification results, without the need for manual selection of suitable initial network parameters. The efficiency of the proposed method has been tested on several classes of publicly available data, such as iris, Wisconsin and ionosphere data.

Algorithms↗