SEARCH · PubMed Health

Results for “artificial intelligence”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 595 records · Page 33Linked to original sources

PubMed1996

Validation of a knowledge-based boundary detection algorithm: a multicenter study.

A completely operator-independent boundary detection algorithm for multigated blood pool (MGBP) studies has been evaluated at four medical centers. The knowledge-based boundary detector (KBBD) algorithm is nondeterministic, utilizing a priori domain knowledge in the form of rule sets for the localization of cardiac chambers and image features, providing a case-by-case method for the identification and boundary definition of the left ventricle (LV). The nondeterministic algorithm employs multiple processing pathways, where KBBD rules have been designed for conventional (CONV) imaging geometries (nominal 45 degrees LAO, nonzoom) as well as for highly zoomed and/or caudally tilted (ZOOM) studies. The resultant ejection fractions (LVEF) from the KBBD program have been compared with the standard LVEF calculations in 253 total cases in four institutions, 157 utilizing CONV geometry and 96 utilizing ZOOM geometries. The criteria for success was a KBBD boundary adequately defined over the LV as judged by an experienced observer, and the correlation of KBBD LVEFs to the standard calculation of LVEFs for the institution. The overall success rate for all institutions combined was 99.2%, with an overall correlation coefficient of r=0.95 (P<0.001). The individual success rates and EF correlations (r), for CONV and ZOOM geometers were: 98%, r=0.93 (CONV) and 100%, r=0.95 (ZOOM). The KBBD algorithm can be adapted to varying clinical situations, employing automatic processing using artificial intelligence, with performance close to that of a human operator.

Algorithms↗

PubMed2006

Genetics and diagnostic refinement.

For many psychiatric conditions it is speculated that, rather than being single disease entities, they are a set of several disorders sharing clinical features but having (partly) different underlying causes. The possibility of measuring genetic variation on a large scale has given researchers new hope of identifying these disease subtypes that may differ with respect to prognosis, course, and response to treatment. However, although a considerable number of articles have been published suggesting that we may even be on the verge of making genotype-based diagnoses, the reality is that we do not have a good answer to even the most basic question of how measured genes could best be used to refine diagnostic categories. In this article, we show that for common psychiatric disorders, it may not be possible to simply look for similar genetic profiles in groups of patients. Instead, we propose a model assuming that genotypes affect phenotypes through more or less coherent etiological systems or pathogenic processes and argue that these etiological systems may provide a more fruitful basis for defining disease subtypes. Several examples from the literature that support the face validity of different aspects of our model are given. Finally, we argue that, given our limited knowledge of disease etiology, the use of discovery-oriented techniques requiring extensive data collection and (artificial) intelligent computer searches may be imperative, and discuss the prospect of model-based diagnosis to classify etiologically different disease subtypes.

Artificial Intelligence↗

PubMed1992

Automation in manned spaceflight.

With the ever increasing complexity and use of advanced technologies in the development of equipment and experiments in spaceflight, the possibility offers itself to automating repetitious or very sensitive operations. The implementation of such automation lends itself well to teleoperations and the eventual introduction of artificial intelligence. In this paper the criteria for introducing automation are discussed, and its impacts examined. New problems such as command and control are discussed, with some guidelines suggested.

Artificial Intelligence↗

PubMed2002

Why the future of architecture doesn't need us.

The information age has ushered in a well-documented revolution in design and production over the past decade. So far these changes mostly have affected our ability to envision and illustrate new forms, but soon the entire artificial environment may be restructured. Emerging technologies such as nanoscience and artificial intelligence may not only restructure the physical world--they may also completely alter our understandings of the world and of ourselves. Traditional standards of architectural theory may become altogether irrelevant.

Architecture↗

PubMed1987

Using the computer to optimize human performance in health care delivery. The pathologist as medical information specialist.

The demands for information retrieval, processing, and synthesis placed on all providers of health care have increased dramatically in the last several decades. Although systems have been developed to capture charge-related data in support of cost reimbursement, there has been a conspicuous lack of attention paid to information tools to directly enhance the delivery of patient care. The termination of cost reimbursement, together with an increasing recognition of the problems inherent in current manual record-keeping systems, is creating a significant new focus on medical information. This change in focus requires a shift in systems orientation away from financial and departmentally centered systems and toward patient-centered approaches. There is thus increasing recognition of the need for a physician-level medical information specialist to serve as an institution's chief information officer, assuming responsibility for the collection, manipulation, and availability of all patient care-related data. By virtue of training, typical experience, hospital presence, and a noncompetitive position with the hospital's medical staff, the pathologist is uniquely suited for this position. To effectively perform this role, a variety of new specialized data management tools are becoming available. Integrated information systems, patient care management by exception, decision support tools, and, in the future, "artificial intelligence" assists can all be expected to become staples of pathology practice, especially impacting those pathologists who choose to be responsive to the new practice milieu of medical information science.

Artificial Intelligence↗

PubMed1995

Information, intelligence, and interface: the pillars of a successful medical information system.

This paper addresses three key issues facing developers of clinical and/or research medical information systems. 1. INFORMATION. The basic function of every database is to store information about the phenomenon under investigation. There are many ways to organize information in a computer; however only a few will prove optimal for any real life situation. Computer Science theory has developed several approaches to database structure, with relational theory leading in popularity among end users [8]. Strict conformance to the rules of relational database design rewards the user with consistent data and flexible access to that data. A properly defined database structure minimizes redundancy i.e.,multiple storage of the same information. Redundancy introduces problems when updating a database, since the repeated value has to be updated in all locations--missing even a single value corrupts the whole database, and incorrect reports are produced [8]. To avoid such problems, relational theory offers a formal mechanism for determining the number and content of data files. These files not only preserve the conceptual schema of the application domain, but allow a virtually unlimited number of reports to be efficiently generated. 2. INTELLIGENCE. Flexible access enables the user to harvest additional value from collected data. This value is usually gained via reports defined at the time of database design. Although these reports are indispensable, with proper tools more information can be extracted from the database. For example, machine learning, a sub-discipline of artificial intelligence, has been successfully used to extract knowledge from databases of varying size by uncovering a correlation among fields and records[1-6, 9]. This knowledge, represented in the form of decision trees, production rules, and probabilistic networks, clearly adds a flavor of intelligence to the data collection and manipulation system. 3. INTERFACE. Despite the obvious importance of collecting data and extracting knowledge, current systems often impede these processes. Problems stem from the lack of user friendliness and functionality. To overcome these problems, several features of a successful human-computer interface have been identified [7], including the following "golden" rules of dialog design [7]: consistency, use of shortcuts for frequent users, informative feedback, organized sequence of actions, simple error handling, easy reversal of actions, user-oriented focus of control, and reduced short-term memory load. To this list of rules, we added visual representation of both data and query results, since our experience has demonstrated that users react much more positively to visual rather than textual information. In our design of the Orthopaedic Trauma Registry--under development at the Carolinas Medical Center--we have made every effort to follow the above rules. The results were rewarding--the end users actually not only want to use the product, but also to participate in its development.

Artificial Intelligence↗

PubMed2001

Medical decision support via the internet: PROforma and Solo.

This paper describes the development and application of an integrated technology to support the authoring of intelligent medical knowledge services, such as decision and guideline support, and disseminate them over the Internet. Decision support and guideline enactment are provided by the PROforma technology which is described in detail elsewhere. Solo is a communications infrastructure that supports the delivery of PROforma services over the Internet using a web browser. The PROforma-Solo technology brings together techniques from knowledge engineering and artificial intelligence with software engineering and the Internet to flexibly support decision making and patient management at the point of care. A variety of clinical applications have been implemented and are briefly described.

Artificial Intelligence↗

PubMed1991

The future of laboratory automation.

Among the many factors that will define the laboratory of the future are the development of advanced computer communications systems, artificial intelligence, robotic systems, and material storage and retrieval systems. This article examines some of these factors and challenges current automation justification procedures in light of the greater competitive environment of today.

Artificial Intelligence↗

PubMed2004

Some trends in microscope image processing.

The present review tries to identify some trends among the multitude of ways followed by image processing developments in the field of microscopy. Nine topics were selected. They cover the fields of: signal processing, statistical analysis, artificial intelligence, three-dimensional microscopy, multidimensional microscopy, multimodality microscopy, theory, simulation and multidisciplinarity. A specific topic is dedicated to a trend towards semi-automation instead of full automation in image processing.

Artificial Intelligence↗

PubMed2001

A new concept toward computer-aided medical diagnosis--a prototype implementation addressing pulmonary diseases.

The original concept that led to the structuring of a computer-based medical decision support system (DSS) that is able to support a physician's diagnosis is introduced in this paper. The concept's implementation modeled a generic DSS, the core of which are an integrated knowledge/information base (KIB) along with the inference properties of a data evaluator. The KIB encapsulates the necessary medical knowledge and experience in the form of rules and constraints, preemptive tasks, and actual patients' clinical data. The data evaluator handles approved medical subjective and objective criteria for assessing the KIB's data. The data evaluator incorporates a medical standard data gathering and decision process, structured upon the principles of the clinical differential diagnosis methodology and has been integrated in the system by means of both algorithmic and artificial intelligence techniques. The novel model and the resulted computer-based package have been extensively tested under the Pulmonary Department, University Regional Hospital Patras, Patras, Greece.

Artificial Intelligence↗

PubMed2002

[The computer aided-therapy system of tumor thermal-treatment instrument using HIFU technology].

Tumor thermal-treatment instrument is a newly developed medical instrument using HIFU technology. On the basis of a brief introduction of the system structure, this paper emphasizes the computer aided-therapy system applying a lot of computer technologies such as digital signal processing, digital signal communication computer aided design, artificial intelligence and database management system. Finally a concise therapy process using computer aided-therapy system is also introduced.

Artificial Intelligence↗

PubMed2003

Modelling the world in real time: how robots engineer information.

Programming robots and other autonomous systems to interact with the world in real time is bringing into sharp focus general questions about representation, inference and understanding. These artificial agents use digital computation to interpret the data gleaned from sensors and produce decisions and actions to guide their future behaviour. In a physical system, however, finite computational resources unavoidably impose the need to approximate and make selective use of the information available to reach prompt deductions. Recent research has led to widespread adoption of the methodology of Bayesian inference, which provides the absolute framework to understand this process fully via modelling as informed, fully acknowledged approximation. The performance of modern systems has improved greatly on the heuristic methods of the early days of artificial intelligence. We discuss the general problem of real-time inference and computation, and draw on examples from recent research in computer vision and robotics: specifically visual tracking and simultaneous localization and mapping.

Artificial Intelligence↗

PubMed2005

An integrated computer supported acquisition, handling, and characterization system for pigmented skin lesions in dermatological images.

This paper describes an integrated prototype computer-based system for the characterization of skin digital images. The first stage includes an image acquisition arrangement designed for capturing skin images, under reproducible conditions. The system processes the captured images and performs unsupervised image segmentation and image registration utilizing an efficient algorithm based on the log-polar transform of the images' Fourier spectrum. Border- and color-based features, extracted from the digital images of skin lesions, were used to construct a classification module for the recognition of malignant melanoma versus dysplastic nevus. Different methods, drawn from the fields of artificial intelligence (neural networks) and statistical modeling (discriminant analysis), were used in order to find the best classification rules and to compare the results of different approaches to the problem.

Algorithms↗

PubMedDate not supplied

Webifying a patient interview support application.

This paper reports on the software engineering challenges, and resultant benefits experienced, in porting an interactive, knowledge-based system from Microsoft Windows to the World Wide Web for evaluation purposes. The Patients Interview Support Application (PISA) is a program intended for operation by a non-expert clerk to interview an ambulatory primary care patient. The PISA code had to be re-written substantially to address the 'connectionless' nature of Web dialog and to work in terms of dynamically generated HTML forms; however, it was possible to avoid any revision of the central knowledge-base or inference engine. The resultant Web environment attracted thought-provoking and detailed feedback from users, indicating that significant attention can be obtained from the global community by mounting an interactive system on the Web. Specific enhancements to the PISA's artificial intelligence are suggested by user reaction. A future global health informatics 'marketplace' with a multidue of Web-based system components available for composition of health information systems is envisioned.

Artificial Intelligence↗

PubMed1989

Heuristic determination of relevant diagnostic procedures in a medical expert system for gynecology.

Many professions including medicine have standard operating procedures for the performance of their tasks. In the construction of expert systems, knowledge engineers have exploited this fact in devising heuristic rules that mimic the standard practice among such personnel (i.e., experts). This article suggests that the expert system designer should not stop at the level of the standard operating procedure heuristic but should instead investigate the reasons that the standard procedures have become standard. Because the experts in a field often do not understand the reasons for the standard operating procedures of their profession, this effort not only rewards the system designer but the expert as well. Because medical training does not always emphasize the logical reasoning underlying certain standard operating procedures, the ability to perform this reasoning is especially important in medicine. Further, a medical expert system for consultation or education would make a valuable impact by incorporating such knowledge and inference rules. This article investigates the development of a computerized medical expert system that applies the principles of artificial intelligence by limiting the number of questions and tests to find the solution for an ill-defined complex problem. Finally, we describe a logic program that tests the basic ideas.

Artificial Intelligence↗

PubMed1999

Artificial neural network-aided image analysis system for cell counting.

BACKGROUND: In histological preparations containing debris and synthetic materials, it is difficult to automate cell counting using standard image analysis tools, i.e., systems that rely on boundary contours, histogram thresholding, etc. In an attempt to mimic manual cell recognition, an automated cell counter was constructed using a combination of artificial intelligence and standard image analysis methods. METHODS: Artificial neural network (ANN) methods were applied on digitized microscopy fields without pre-ANN feature extraction. A three-layer feed-forward network with extensive weight sharing in the first hidden layer was employed and trained on 1,830 examples using the error back-propagation algorithm on a Power Macintosh 7300/180 desktop computer. The optimal number of hidden neurons was determined and the trained system was validated by comparison with blinded human counts. System performance at 50x and lO0x magnification was evaluated. RESULTS: The correlation index at 100x magnification neared person-to-person variability, while 50x magnification was not useful. The system was approximately six times faster than an experienced human. CONCLUSIONS: ANN-based automated cell counting in noisy histological preparations is feasible. Consistent histology and computer power are crucial for system performance. The system provides several benefits, such as speed of analysis and consistency, and frees up personnel for other tasks.

Cell Count↗

PubMed1996

Knowledge-based systems, artificial neural networks and pattern recognition: applications to biotechnological processes.

Recent years have witnessed the increasing application of artificial intelligence techniques, specifically, knowledge-based systems, artificial neural networks, and pattern recognition, to biotechnological processes. Although progress has been made in simple control applications, more work is needed to establish the advantages of these techniques for industrial process control, for diagnosis/monitoring, and to upgrade the information content of historical data.

Biotechnology↗

PubMed2000

Diagnosis of breast cancer using elastic-scattering spectroscopy: preliminary clinical results.

We report on the first stages of a clinical study designed to test elastic-scattering spectroscopy, mediated by fiberoptic probes, for three specific clinical applications in breast-tissue diagnosis: (1) a transdermal-needle (interstitial) measurement for instant diagnosis with minimal invasiveness similar to fine-needle aspiration but with sensitivity to a larger tissue volume, (2) a hand-held diagnostic probe for use in assessing tumor/resection margins during open surgery, and (3) use of the same probe for real-time assessment of the "sentinel" node during surgery to determine the presence or absence of tumor (metastatic). Preliminary results from in vivo measurements on 31 women are encouraging. Optical spectra were measured on 72 histology sites in breast tissue, and 54 histology sites in sentinel nodes. Two different artificial intelligence methods of spectral classification were studied. Artificial neural networks yielded sensitivities of 69% and 58%, and specificities of 85% and 93%, for breast tissue and sentinel nodes, respectively. Hierarchical cluster analysis yielded sensitivities of 67% and 91%, and specificities of 79% and 77%, for breast tissue and sentinel nodes, respectively. These values are expected to improve as the data sets continue to grow and more sophisticated data preprocessing is employed. The study will enroll up to 400 patients over the next two years.

Adenocarcinoma↗