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 1,261 records · Page 70Linked to original sources
PubMed1991

[A new database system for radiological reports].

We have designed and developed a new database system to facilitate automatic feedback of the content of radiology reports to radiologists. The prototype of this database system has been implemented in the RGSS-IDJ, a developmental computer system that applies artificial intelligence methods to a reporting system. This prototype system was constructed to test the feasibility of overcoming the limitations of conventional database systems. The new database system is based on our semantic model for radiology reports and is able to treat data with unnormalized relations. Operations specific to our database system include the ability to acquire information about a set of reports that contains any semantic expression included in the lexicon and the ability to obtain the expressions that belong to a set of several semantic expressions in the reports. Thus, our new database system will offer a more powerful tool for analyzing the content of reports than conventional database systems.

Databases, Bibliographic↗
PubMed1991

[Medical diagnosis].

The diagnostic process holds a firm position in medical practice, but is often claimed to be part of the "art of medicine", partially beyond reach of rational and logical analysis. Research in clinical cognition, decision analysis and artificial intelligence have, however, elucidated essential parts of medical diagnosis. A characteristic feature of diagnosis is the manner in which uncertainties are handled. Early generation of hypotheses about the nature of the condition present seems to be useful method. Similarly, probabilistic, causal and deterministic reasoning can be illustrated by diagnostic models which have found favor during recent years. A certain type of cognitive process (heuristic) is employed when assessing information of probabilistic nature. The diagnostic models are partial and concern the parts of the process, which may be represented verbally and consciously. This raises the question of how the clinician actually draws upon experience (background knowledge), which preconditions shape the generation of applicable diagnostic hypotheses and how the diagnostic capability of the individual physician can be facilitated.

Clinical Competence↗
PubMed1991

The diagnosis of acute abdominal pain with computer assistance: worldwide perspective.

This presentation describes the use of computer aided decision support in acute abdominal pain. The development of such support and the feasability of providing it are described with reference to worldwide studies involving nearly 100,000 patients in the UK, the European Community and worldwide. This presentation will give an overview of the experienced gained in these and other studies. As a result of this experience, it will be suggested: a) The diagnosis of acute abdominal pain by inexperienced emergency surgeons remains a difficult problem. 2) Doctors who have been assisted by a computer have, in many instances, improved their diagnostic and decision-making performance. 3) This improvement has not been due to superior "artificial intelligence" of the computer--but due to the computer acting as an educational focus and a stimulus to good clinical practice. 4) On an international level, these studies have been immensely valuable. They have helped bring together different national groups and helped to develop common medical terminology--as well as foster collaborative "spin-off" in terms of research around the world.

Abdomen, Acute↗
PubMedDate not supplied

The cytomorphologic and cytometric manifestations of cervical reparative processes.

The process of tissue repair or regeneration is the attempt of the injured tissue to be restructured and to reestablish its function as it existed prior to injury. The cytologic alterations depend on the original tissue site, the elapsed time after the incurred injury as well as on the type of the injury itself. From a practical standpoint, the importance of the recognition of tissue repair alterations as such, is the avoidance of false positive cytologic diagnoses and/or the under evaluation of existing malignant lesions with potentially severe clinical consequences. The computerized on-line file of patients examined cytologically and histologically since the year 1959 which contains over two million patient records was searched for those cases identified as "tissue repair". The major criteria of cytomorphology of tissue repair and differential diagnoses are described. For the purpose of enhancing the differential diagnostic accuracy two procedures useful as diagnostic aids are presented: (1) local administration of estrogens, and (2) computerized cell image analyses evaluated and guided by an artificial intelligence expert system.

Carcinoma, Squamous Cell↗
PubMed1990

Twelve years' experience of computer-aided diagnosis in a district general hospital.

This paper describes experience in a modern district general hospital with a small desktop system for computer-aided diagnosis of acute abdominal pain, over a 12-year period involving 5512 cases. When compared with a baseline year (1973) in which unaided performance was monitored, during an initial study period (1974-76) the diagnostic accuracy of junior staff rose by between 10 and 15%. This higher performance level was then maintained for a decade (1976-86) despite changes in staff. The perforation rate among appendicitis cases fell from 27% to 12.5%, accompanied by a smaller fall in negative laparotomy rates. The saving in surgical bednights devoted to acute abdominal pain was approximately 15%, and the notional cost of resources saved during the first 6 years of operation was 120,000 pounds. Other hospitals have shown--in the short term--benefits similar to those obtained at Airedale District General Hospital. The long-term benefits of the system at Airedale reinforce the conclusions of the earlier short-term trials that a comparable system should probably be offered to all DGHs in the UK, not as an exercise in 'artificial intelligence' but as an effective continuing stimulus to good clinical practice.

Abdominal Pain↗
PubMed1990

The discrimination of similarly colored objects in computer images of the ocular fundus.

The STARE (STructured Analysis of the REtina) project uses object-identification and artificial intelligence techniques to provide automated diagnoses from color pictures and fluorescein angiograms of the ocular fundus, or automated change detection from sequential images. As part of the object-identification process, we apply expert judgment and experimentation to define features--such as size, shape, color, and texture--of objects (disk, blood vessels, lesions) in digitized images. In our initial investigations, we explored color alone, because it yields a great deal of information in the classification process. We verified that even similarly colored lesions (exudates, cotton-wool spots, and drusen) could be classified by color with moderate success by a quadratic discriminant function. When color alone is not sufficient, refinement in the classification of objects may be achieved by using more features in statistical pattern recognition. Ultimately, we build a description of the fundus image which can be used either to identify one or more diagnoses that can cause the pattern of lesions in the ocular fundus or to recognize change in sequential images.

Color↗
PubMed1990

Identification of rodent carcinogens by an expert system.

CASE, an artificial intelligence method for identifying structural determinants responsible for biological activity was applied to the U.S. National Toxicology Program (NTP) cancer bioassay results. CASE identified structures which were significantly associated with rodent carcinogenicity. On the basis of these structural determinants CASE exhibited a sensitivity of 0.98 and a specificity of 1.00. CASE showed a similarly remarkable performance in predicting the carcinogenicity, or lack thereof, of chemicals not in the NTP data base. A comparison between the activating structures (biophores) responsible for mutagenicity in Salmonella and rodent carcinogenicity showed a significant overlap, verifying that there are structural commonalities between the two phenomena. CASE also identified biophores significantly associated with the activity of non-genotoxic carcinogens, thereby suggesting the unexpected possibility that there is a structural commonality among the chemicals included in this group. A comparison between the biophores responsible for carcinogenicity in mice and rats resulted in the identification of common ("universal") biophores. It is suggested that agents which contain "universal" biophores are more likely to present a risk to human than carcinogens that do not possess such biophores. CASE also permitted the recognition of species-specific carcinogenic biophores. While the former are primarily electrophiles or potential electrophiles, the latter represent non-electrophilic structures.

Animals↗
PubMed1989

Expert systems in medicine.

The emergence of the artificial intelligence (AI) in computer technology and its application in the medical field enables the researchers to carry out such intelligent activities like image processing, medical reasoning systems, clinical decision supporting and natural language understanding, etc. A gastroenterological expert system application is briefly demonstrated in this paper. Similar expert systems can be seen to be useful in the research of gastrointestinal cytoprotection, including the plan of different compounds with cytoprotective effect, experimental and clinical medical research.

Decision Making, Computer-Assisted↗
PubMed1989

Knowledge engineering for clinical consultation programs: modeling the application area.

Developers of computer-based decision-support tools frequently adopt either pattern recognition or artificial intelligence techniques as the basis for their programs. Because these developers often choose to accentuate the differences between these alternative approaches, the more fundamental similarities are frequently overlooked. The principal challenge in the creation of any clinical consultation program - regardless of the methodology that is used - lies in creating a computational model of the application domain. The difficulty in generating such a model manifests itself in symptoms that workers in the expert systems community have labeled "the knowledge-acquisition bottleneck" and "the problem of brittleness". This paper explores these two symptoms and shows how the development of consultation programs based on pattern-recognition techniques is subject to analogous difficulties. The expert systems and pattern recognition communities must recognize that they face similar challenges, and must unite to develop methods that assist with the process of building of models of complex application tasks.

Decision Support Techniques↗
PubMed1989

Protein databases and software on BIONET.

BIONET provides databases, software, and networking/communications tools to over 2500 molecular biologists worldwide. Software for the analysis of nucleic acid and protein sequence data is provided by both IntelliGenetics and academic contributors. BIONET is currently implementing dedicated high speed servers for searching protein databases, as well as providing more flexible tools for protein structure recognition and prediction. In this review, protein databases and analysis software available on the BIONET resource are described, and progress in providing new tools for structure prediction, comparative sequence analysis, and pattern recognition using Artificial Intelligence (AI) techniques are summarized.

Amino Acid Sequence↗
PubMed1989

Comparison of conventional morphometry and image analysis for the solution of histomorphometric problems.

The main differences between conventional morphometry and image analysis for their application in histopathology are pointed out. Conventional morphometry allows the use of contextural informations and a priori knowledge in a convenient manner. This is the most complicated thing in image analysis. The solution of this problem lies on the field of artificial intelligence. On the other hand, image analysis is able to measure densitometrical and textural features, to determine arbitrary quantiles and moments of feature distributions, to match scenes. Therefore the descriptive power of image analysis is much higher than the power of conventional morphometry.

Humans↗
PubMed1989

Three-dimensional radiation treatment planning.

A major aim of radiation therapy is to deliver sufficient dose to the tumour volume to kill the cancer cells while sparing the nearby healthy organs to prevent complications. With the introduction of devices such as CT and MR scanners, radiation therapy treatment planners have access to full three-dimensional anatomical information to define, simulate, and evaluate treatments. There are a limited number of prototype software systems that allow 3D treatment planning currently in use. In addition, there are more advanced tools under development or still in the planning stages. They require sophisticated graphics and computation equipment, complex physical and mathematical algorithms, and new radiation treatment machines that deliver dose very precisely under computer control. Components of these systems include programs for the identification and delineation of the anatomy and tumour, the definition of radiation beams, the calculation of dose distribution patterns, the display of dose on 2D images and as three dimensional surfaces, and the generation of computer images to verify proper patient positioning in treatment. Some of these functions can be performed more quickly and accurately if artificial intelligence or expert systems techniques are employed.

Radiotherapy Dosage↗
PubMed1989

Computer-assisted interpretation in forensic toxicology: morphine-involved deaths.

Case data from 200 morphine-involved deaths (Spiehler, V. and Brown, R., Journal of Forensic Sciences, Vol. 32, No. 4, July 1987, pp. 906-916) were analyzed for patterns and relationships using artificial intelligence (AI) computer software. Case parameters were blood unconjugated morphine, blood, brain, and liver total morphine, sex, age, frequency of use, time of death after injection, cause of death, and presence of other drugs. The programs used were Expert 4 (Biosoft-Cambridge), BEAGLE (Warm Boot, Ltd.), and KnowledgeMaker (Knowledge Garden Inc.). Interpretation was defined as estimating the dose, response, and time after drug dosing. The AI programs were used to advise on time and response outcomes for cases, to calculate the probability of the estimate being true, to develop rules for interpretation of morphine-involved cases, and to diagram a decision tree. On known cases the AI programs were successful 70 to 90% of the time in classifying the cases as to response and time. No data on dose were available in this database. The success rate in individual cases was proportional to the program-estimated probability. All three programs found the case parameters of most value in predicting response to be blood unconjugated morphine, blood total morphine, and liver total morphine. The case data most useful in estimating time of death since drug injection were blood unconjugated morphine, percent unconjugated morphine in blood, and brain total morphine. The rule induction programs found that morphine overdoses were characterized by blood unconjugated morphine greater than 0.24 micrograms/mL, liver morphine greater than 0.50 to 0.75 micrograms/g, brain morphine greater than 0.08 micrograms/g or greater than blood unconjugated morphine, and percent blood unconjugated morphine greater than 37%. Rapid deaths were characterized by percent unconjugated morphine greater than 44 to 50%; blood unconjugated morphine, as a function of other drugs present, greater than 0.09 to 0.21 micrograms/mL; and brain total morphine greater than 0.16 to 0.22 micrograms/g. This work demonstrates that inexpensive AI programs commercially available for personal computers can be useful in interpretation in forensic toxicology.

Cause of Death↗
PubMed1988

[Systems assisting decisions in clinical medicine].

There are numerous systems and computerized procedures which have been developed and tested as a guide to clinical decisions. The methods used in the development of these systems can be divided into two large groups: mathematical and logical. None of these can be considered as better than the other in absolute, but the efficiency of each system depends on that problem is to be described and solved. The mathematical methods seem more suitable in the description of biological systems and for the selection of groups which have discriminant and sufficiently defined characteristics. Meanwhile the logical methods are better in the description and the formalization of more complicated clinical problems, characterized by uncertainty and availability of more or less numerous alternatives. It is foreseen that in the next years the systems for aided decision making will be programmed making use of methods belonging to both categories, and particularly, the expert systems will be planned using both artificial intelligence techniques and mathematical and statistical methods. The increasing frequency in the use of such systems in clinical practice will cause a reevaluation and a checking of most aspects of medical proceedings, as seen by the new methodologies or the traditional methods whose use could be driven by computer.

Algorithms↗
PubMed1988

Patterns and contrasts in ophthalmic investigation.

The Snellen test has been the most popular clinical measurement of spatial vision for over a century, but it does not fully express the visual ability of an individual. For more analytical purposes the information capacity of the visual system may be assessed by tests of contrast sensitivity and peripheral vision. The visual system selectively reduces the spatial information content of the visual field to avoid overloading the limited capacity for perception and decision making in the brain. The ways in which this reduction occurs and the processing of spatial information is of interest in many disciplines, and theoretical knowledge has been accelerated by the study of artificial intelligence. These processes may be investigated in human subjects by psychophysical and electrophysiological techniques. This provides additional information for diagnostic purposes and will form the basis of new systems of clinical investigation.

Evoked Potentials, Visual↗
PubMed1988

Equilibration and cognition: a review and elaboration of Piaget's genetic epistemology.

Piaget's concept of equilibration--and its current status--has been briefly reviewed. Two fundamental and essentially related issues were identified: the question of conformity between cognitive structures and their referent external reality and, from a cognitive viewpoint, the description of a "growing self-regulatory adaptive system." These issues were reconsidered in relation to, and elaborated on the basis of, relevant ideas mainly from philosophy, cybernetics, and artificial intelligence. A model of a cognitive homeostatic system was developed from an innate subsystem to a learning-based control hierarchy that additionally involves a naturomorphic cognitive subsystem and an abstract cognitive subsystem. The process of equilibration of cognitive structures was approached in terms of the information processing characteristics of these two cognitive subsystems and their inherent sources of error, and the theoretical requirements for ensuring conformity between cognitive structures and their external referents have been indicated. The model, which takes into account these requirements, constitutes a systematic description of a learning based "growing self-regulating adaptive system."

Cognition↗
PubMed1987

[Current computerized support for vestibular function tests.I. Expert systems and their clinical applications].

Expert Systems are a new method developed by the branch of Computer Science known as Artificial Intelligence in order to make available the knowledge and the expertise of the specialists in a certain domain of the science to other operators in the same field. Most of their applications belong to the medical domain. In this paper the main features of the expert systems are briefly described. As an example the structure and the characteristics of the shell EXPERT (Weiss and Kulikowski, 1979) are presented in detail. This shell has already been used to develop several expert systems. It is the tool by which we constructed a consultation system (VERTIGO) aimed to classify different types of vertigo.

Expert Systems↗
PubMed1986

Computer-assisted dental diagnosis.

Computer-assisted dental diagnosis has been discussed from the perspective of applications, decision-making processes, and a specific example of a diagnostic system. Rapid technologic advancement and anticipated developments in the field of artificial intelligence will undoubtedly change both our expectations of future evolutions and our capacity to transform these expectations into reality. The ability of computers to enhance the diagnostic capabilities of practitioners will make automation integral to future dental practice.

Decision Making↗