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 937 records · Page 52Linked to original sources
PubMed1989

Expert systems and the pancreatic cancer problem: decision support in the pre-operative diagnosis.

In this paper, after reviewing the main issue in artificial intelligence, decision support systems, medical decision-making, expert systems and some of their applications in medicine, we focus on the diagnostic aspect of pancreatic cancer. We briefly examine the most significant applications both from the oncological and from the diagnostic point of view. We discuss the medical problems mentioning incidence and mortality, aetiological factors and diagnosis, considering the roles of surgery and adjuvant therapies. Finally we justify the decision to develop an expert system in such a medical domain and discuss the SPES (Surgical Pancreatic Expert System) project, its parts dealing with the different medical phases of pancreatic cancer diagnosis and therapy: pre-operative, intra-operative and adjuvant therapies. In particular we discuss diagnostic aspects of pancreatic cancer disease, pointing out the aims of the project, methodologies, tools used and future developments.

Decision Support Techniques↗
PubMed1989

Automatic detection of gait events: a case study using inductive learning techniques.

One of the problems which occurs in the development of a control system for functional electrical stimulation of the lower limbs is to detect accurately specific events within the gait cycle. We present a method for the classification of phases of the gait cycle using the artificial intelligence technique of inductive learning. Both the terminology of inductive learning and the algorithm used for the analyses are fully explained. Given a set of examples of sensor data from the gait events that are to be detected, the inductive learning algorithm is able to produce a decision tree (or set of rules) which classify the data using a minimum number of sensors. The nature of the redundancy of the sensor set is examined by progressively removing combinations of sensors and noting the effect on both the size of the decision trees produced and their classification accuracy on 'unseen' testing data. Since the algorithm is able to calculate which sensors are more important (informative), comparisons with the intuitive appreciation of sensor importance of five researchers in the fields were made, revealing that those sensors which appear intuitively most informative may, in fact, provide the least information. Comparison results with the standard statistical classification technique of linear discriminant analysis are also presented, showing the relative simplicity of the inductively derived rules together with their good classification accuracy. In addition to the control of FES, such techniques are also applicable to automatic gait analysis and the construction of expert systems for diagnosis of gait pathologies.

Algorithms↗
PubMed1986

Microcomputers as aids in Gottschalk-Gleser rating.

Different types of errors during the various steps of Gottschalk-Gleser content analysis of speech samples are discussed. Several attempts have been made in the past to avoid error by using computer programs to categorize verbal material. Although these systems offer the advantage of increasing reliability to a maximum, validity is a problem. More recent approaches, which use artificial intelligence methods of language understanding by computer, show promise. However, these computer systems will have to be further developed before they can perform at the same level as human raters. For this reason, an alternative approach is presented which only relies on computers in a limited way: All steps of Gottschalk-Gleser content analysis are performed with a collection of programs on a small 8-bit microcomputer: transcription, scoring, storage, and computation of scores. The different steps of using this system are described, and it is argued that a significant reduction of error, both random and systematic, can be achieved through this system.

Computers↗
PubMed1985

Health and medical software related to computer user satisfaction: an interactive online expert system using diagnostic audit trails through telecommunication networks.

The selection of a health and medical software (HMS) system is a complicated process. The overall satisfaction derived from a system depends on many variables. This study analyzes the influence of HMS predictor variables on overall satisfaction as determined by multiple regression. The null hypothesis, that multiple correlation coefficient is zero, is rejected. Th alternative hypothesis is accepted. This study confirms the theories that suggest that HMS ease of operation, independent variables, technical support troubleshooting, and reliability of computer are the major determinations of overall computer user satisfaction. The factors identified were used in the design of an HMS expert system based on artificial intelligence (ESAI).

Computers↗
PubMedDate not supplied

Ten years of medical informatics. Introduction.

The discussions of the Tenth Anniversary of the Symposium on Computer Applications in Medical Care (SCAMC) are summarized. Eight different subject areas are addressed: Medical informatics and medical education; Decision making, medical artificial intelligence, modelling and simulations; Image processing, 3-D graphics, and computer networks; Reimbursement policy, legal and regulatory issues; Encoding and representation of medical meaning; Ambulatory medical records systems; Hospital information systems; and Software environments for developing medical information systems. The activities of the 10th SCAMC consisted of Tutorials, Panel Discussions, a Plenary Session, Scientific Demonstrations, and an International Student Paper Competition in Medical Informatics.

Computer Communication Networks↗
PubMedDate not supplied

An object-based architecture for biomedical expert database systems.

Objects play a major role in both database and artificial intelligence research. In this paper, we present a novel architecture for expert database systems that introduces an object-based interface between relational databases and expert systems. We exploit a semantic model of the database structure to map relations automatically into object templates, where each template can be a complex combination of join and projection operations. Moreover, we arrange the templates into object networks that represent different views of the same database. Separate processes instantiate those templates using data from the base relations, cache the resulting instances in main memory, navigate through a given network's objects, and update the database according to changes made at the object layer. In the context of an immunologic-research application, we demonstrate the capabilities of a prototype implementation of the architecture. The resulting model provides enhanced tools for database structuring and manipulation. In addition, this architecture supports efficient bidirectional communication between database and expert systems through the shared object layer.

Database Management Systems↗
PubMed1989

The principles and prototyping of a knowledge-based diabetes management system.

This paper describes the principles and prototyping of a computer-based system being developed to assist in the management of diabetes mellitus. Unlike other approaches based upon mathematical modelling or the use of computer algorithms, this system adopts one derived from artificial intelligence, seeking to incorporate the dynamics of glucose and insulin in a manner which reflects their clinical importance. The resultant logical model (qualitative algebra) defines the relationships between changes in insulin dose and site and time of injection and glycaemic response. In this manner the computer-based system, implemented in Prolog, can be used to provide advice concerning insulin therapy by means of making qualitative predictions of patient outcome of blood glucose profile resulting from alternative insulin regimens.

Blood Glucose↗
PubMed1989

GENPRO: automatic generation of Prolog clause files for knowledge-based systems in the biomedical sciences.

With the increasing interest in using knowledge-based approaches for protein structure prediction and modelling, there is a requirement for general techniques to convert molecular biological data into structures that can be interpreted by artificial intelligence programming languages (e.g. Prolog). We describe here an interactive program that generates files in Prolog clausal form from the most commonly distributed protein structural data collections. The program is flexible and enables a variety of clause structures to be defined by the user through a general schema definition system. Our method can be extended to include other types of molecular biological database or those containing non-structural information, thus providing a uniform framework for handling the increasing volume of data available to knowledge-based systems in biomedicine.

Database Management Systems↗
PubMed1995

Computerized measurement of the content analysis of natural language for use in biomedical and neuropsychiatric research.

Over several decades, the senior author, with various colleagues, has developed an objective method of measuring the magnitude of commonly useful and pertinent neuropsychiatric and neuropsychological dimensions from the content and form analysis of verbal behavior and natural language. Extensive reliability and validation studies using this method have been published involving English, German, Spanish and many other languages, and which confirm that these Content Analysis Scales can be reliably scored cross-culturally and have construct validity. The validated measures include the Anxiety Scale (and six subscales), the Hostility Outward Scale (and two subscales), the Hostility In Scale, the Ambivalent Hostility Scale, the Social Alienation-Personal Disorganization Scale, the Cognitive Impairment Scale, the Depression Scale (and seven subscales), and the Hope Scale. Here, the authors report the development of artificial intelligence (LISP based) software that can reliably score these Content Analysis Scales, whose achievement facilitates the application of these measures to biomedical and neuropsychiatric research.

Diagnosis, Computer-Assisted↗
PubMed1994

An approach for treating the uncertainties in the impact of climate change.

Past accumulated data supported by the predictions of climate models suggest that our world is getting warmer. Scientists are trying to construct mathematical models of both climate and crop systems to identify what types of climate changes could constitute a significant risk or benefit for agriculture. However, due to the many uncertainties regarding these models, it is impossible to make unequivocal predictions. At present, almost all the research in this area is carried out without considering the uncertain nature of the problem. The approach outlined here attempts to find a way to deal with the above uncertainty problem. Artificial intelligence techniques are being developed with the aim of performing inferences based on uncertain information. In our method, causal graphs are used for explicit representation of the relationships between climatic factors and yield. Probabilities are used to express the uncertainties associated with these links, and Bayes' theorem is applied to deal with uncertainty reasonings. This approach has the additional advantage of allowing the prediction to be readily updated as results from improved climate and crop models become available. These opportunities are being evaluated initially by using the model for potato growth developed at the Scottish Crop Research Institute.

Journal Article↗
PubMed1989

Towards an artificial brain.

Three components of a brain model operating on neuromolecular computing principles are described. The first component comprises neurons whose input-output behavior is controlled by significant internal dynamics. Models of discrete enzymatic neurons, reaction-diffusion neurons operating on the basis of the cyclic nucleotide cascade, and neurons controlled by cytoskeletal dynamics are described. The second component of the model is an evolutionary learning algorithm which is used to mold the behavior of enzyme-driven neurons or small networks of these neurons for specific function, usually pattern recognition or target seeking tasks. The evolutionary learning algorithm may be interpreted either as representing the mechanism of variation and natural selection acting on a phylogenetic time scale, or as a conceivable ontogenetic adaptation mechanism. The third component of the model is a memory manipulation scheme, called the reference neuron scheme. In principle it is capable of orchestrating a repertoire of enzyme-driven neurons for coherent function. The existing implementations, however, utilize simple neurons without internal dynamics. Spatial navigation and simple game playing (using tic-tac-toe) provide the task environments that have been used to study the properties of the reference neuron model. A memory-based evolutionary learning algorithm has been developed that can assign credit to the individual neurons in a network. It has been run on standard benchmark tasks, and appears to be quite effective both for conventional neural nets and for networks of discrete enzymatic neurons. The models have the character of artificial worlds in that they map the hierarchy of processes in the brain (at the molecular, neuronal, and network levels), provide a task environment, and use this relatively self-contained setup to develop and evaluate learning and adaptation algorithms.

Artificial Intelligence↗
PubMed1992

Neural computing in discovering RNA interactions.

High-order RNA structures are involved in regulating many biological processes; various algorithms have been designed to predict them. Experimental methods to probe such structures and to decipher the results are tedious. Artificial intelligence and the neural network approach can support the process of discovering RNA structures. Secondary structures of RNA molecules are probed by autoradiographing gels, separating end-labeled fragments generated by base-specific RNases. This process is performed in both conditions, denaturing (for sequencing purposes) and native. The resultant autoradiograms are scanned using line-detection techniques to identify the fragments by comparing the lines with those obtained by 'alkaline ladders'. The identified paired bases are treated by either one of two methods to find the foldings which are consistent with the RNases' 'cutting' rules. One exploits the maximum independent set algorithm; the other, the planarization algorithm. They require, respectively, n and n2 processing elements, where n is the number of base pairs. The state of the system usually converges to the near-optimum solution within about 500 iteration steps, where each processing element implements the McCulloch-Pitts binary neuron. Our simulator, based on the proposed algorithm, discovered a new structure in a sequence of 38 bases, which is more stable than that formerly proposed.

Algorithms↗
PubMed1994

Patterns in the complementary determining regions of immunoglobulins (CDRs).

An analysis of the frequency of use of amino acids on the CDR-1 and CDR-2 of 1500 immunoglobulins showed that the frequencies of amino acids in different positions could be fitted by two types of distribution. For some positions the frequencies were fitted by an inverse power law and for other positions by an exponential distribution. In order to see whether the more frequently used amino acids for specific positions had physicochemical properties or attributes in common, they were clustered using an algorithm normally applied to artificial intelligence problems. It was found that the amino acids in those positions fitted by the inverse power law have similar hydrophobicity and volume, which are commonly attributes of amino acids in structural positions. Thus, if these positions are critical to maintaining the structural features of the CDR domains, the rest of the positions should be either properly involved in the recognition process or irrelevant. The frequencies of amino acids in these recognition positions were fitted by the exponential law, and it was found by the clustering analysis that these amino acids share properties of a more general type, such as capability of forming hydrogen bonds, polarity, etc. This suggests that at least part of the recognition mechanism requires general properties rather than specific amino acids. Amino acids sharing the required attributes for each one of these positions are then used with random frequency.

Algorithms↗
PubMed1996

The effects of variable biome distribution on global climate.

In projecting climatic adjustments to anthropogenically elevated atmospheric carbon dioxide, most global climate models fix biome distribution to current geographic conditions. Previous biome maps either remain unchanging or shift without taking into account climatic feedbacks such as radiation and temperature. We develop a model that examines the albedo-related effects of biome distribution on global temperature. The model was tested on historical biome changes since 1860 and the results fit both the observed temperature trend and order of magnitude change. The model is then used to generate an optimized future biome distribution that minimizes projected greenhouse effects on global temperature. Because of the complexity of this combinatorial search, an artificial intelligence method, the genetic algorithm, was employed. The method is to adjust biome areas subject to a constant global temperature and total surface area constraint. For regulating global temperature, oceans are found to dominate continental biomes. Algal beds are significant radiative levers as are other carbon intensive biomes including estuaries and tropical deciduous forests. To hold global temperature constant over the next 70 years this simulation requires that deserts decrease and forested areas increase. The effect of biome change on global temperature is revealed as a significant forecasting factor.

Algorithms↗
PubMed1984

Multivariate statistical classification of noisy images (randomly oriented biological macromolecules).

Multivariate Statistical Analysis (MSA) methods have recently been introduced for analyzing images of biological macromolecules [Van Heel and Frank, Ultramicroscopy 6 (1981) 187]. With these techniques, the significant characteristics of each molecular image can be expressed in merely 2 to 8 factorial coordinate values rather than in the typical 64 X 64 = 4096 pixel grey values that originally described the image. This very large reduction in total amount of data facilitates the understanding of the general behavior of a set of molecular images in terms of classes or of general trends in the data set. The (artificial) intelligence of the procedure, however, lies in the decision-making or classification phase. The theory and philosophy of multivariate statistical classification are reviewed using generalized metrics. Problem-dependent classification rationales are proposed. A set of computer-generated "randomly oriented molecular images" are used to test the classification schemes. This model experiment is a step towards 3D structure analysis of macromolecules based on large numbers of (noisy) electron microscopical images of randomly oriented biological macromolecules.

Animals↗
PubMed1989

Automatic selection of macromolecules from electron micrographs by component labelling and symbolic processing.

A new solution to the problem of extracting images of individual biological macromolecules from electron micrographs is described. There are three distinct steps in the process. The initial stage of low-level image processing consists of noise suppression and edge detection. An intermediate stage of component labelling and feature computation bridges the gap between the iconic (low-level) processing and the final phase of symbolic (high-level) processing. Simple symbolic objects (bounding boxes) are derived from the edges, and are easily represented and manipulated in the decision-making process. The efficacy of the algorithm is demonstrated using electron micrographs of ribosomes and ribosomal subunits. The hierarchical nature of the analysis embodies a reduction in the amount of data and a change in its nature. Initially, thousands of pixels of continuous gray levels must be dealt with. After component labelling, there are fewer than a hundred bounding boxes whose manipulation can easily be defined and articulated by an expert. The software package that has been written can thus serve as a basis for applying artificial intelligence methodologies to analysis of electron micrographs.

Algorithms↗
PubMed1994

The tetrad and hexad: maximum beam separation as a starting point for noncoplanar 3D treatment planning: prostate cancer as a test case.

PURPOSE: In contrast to computer optimized three-dimensional (3D) treatment planning, we have used maximally separated, noncoplanar beams as the starting point for 3D treatment planning of prostate cancer to maximize the rate of dose fall off from the target volume and minimize dose to surrounding tissues. MATERIALS AND METHODS: A planar four-field plan, a planar six-field plan, a tetrad plan, and a hexad plan are analyzed using a 3D treatment planning system which is capable of displaying real-time 3D dose distributions within volume reconstructed data sets (VISTAnet--an extension of the virtual simulator). The tetrad plan is based on the methane molecule and the hexad plan has a minimum separation of 58 degrees on beam entrance. All fields are conformal. The irradiated volume equals the clinical target volume plus a 1 cm margin. Competing plans are compared using cumulative dose-volume histograms and normal tissue complication probabilities. RESULTS: The crossover point, the isodose surface that conforms more to the beams than the target, is introduced and described. The hexad and tetrad plans result in tighter dose distributions when compared to the planar plans with the same number of beams. The tetrad plan treats a volume less than or equal to the planar six-field plan at isodose surfaces above 18% except between 37% and 44% where the tetrad volume is slightly larger. As expected from integral dose considerations, the amount of normal tissue receiving some radiation increases, but the amount receiving clinically significant amounts of radiation decreases as the number of beams increase. The plan involving the largest number of noncoplanar beams results in the tightest isodose distribution. Analysis of rectal and bladder cumulative dose volume histograms does not reveal a clearly superior plan based on normal tissue complication probabilities. CONCLUSIONS: Using basic principles of solid geometry, maximally separated beams without significant overlap on exit or entrance can be designed which minimize clinically significant dose to surrounding tissues and tighten the isodose distribution around the target volume. The emphasis of this treatment plan optimization is geometric in contrast to methods using computer optimization or artificial intelligence.

Humans↗
PubMedDate not supplied

Approaching the millennium: perinatal problems and software solutions.

Strategic planning for rational development of perinatal computing capabilities for the year 2000 should be driven by anticipated trends in (1) the health care business, (2) computer technology and (3) medicine, as well as (4) the needs of perinatal practitioners. In the USA, health care is the fastest growing segment of the economy. This will produce increasing attention from hardware and software developers, and vendors, and will lead to a proliferation of computing platforms, operating systems and specific medical application software. Desktop computers, already capable of 20 million instructions per second (MIPS) with massive storage capacities, will continue to evolve and fall in price. Increasingly, perinatologists will develop software packages to facilitate patient care in their own environments. All of these trends will lead to severe fragmentation in medical computing. Simultaneously, however, the need for integrated institutional computer-based data access for quality assurance and fiscal and operations management will increase. Perinatal care will be more regionalized, complex and rigorous with new clinical trial- and effectiveness research-based interventions, as well as molecular diagnosis and therapy. To practice appropriately, clinicians will need to be familiar with computer capabilities. Having been exposed to computer-aided instruction (CAI) at the undergraduate and postgraduate levels, they will except on-line access to detailed and accurate patient information with linkage to laboratory, radiology and other medical databases, as well as to reference databases, such as Medlines and the Oxford Database of Perinatal Trials. Artificial intelligence (AI) software may support perinatal decision making; computerized professional and facility billing will be available.

Forecasting↗