PubMed Health⌕ Search

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 685 records · Page 38Linked to original sources

[The physician and the computer. 29. Learning systems and neuron networks].

The authors discuss basic properties of the process of learning as a form of artificial intelligence. They deal with the application of adaptive and learning systems in the area of identification, regulation, manipulation and recognition. A very important perspective trend is learning in a medium of neuron networks which are actually software or hardware simulation of the functional architecture of the CNS. The authors discuss peculiar features of representation of knowledge, structure and mode of function of this neuron network. Finally the authors give examples of the solution of optimalization and classification tasks within the framework of neurocomputers.

Artificial Intelligence↗

European research efforts in medical knowledge-based systems.

This article describes the major projects going on in Europe in the field of Artificial Intelligence in Medicine. The important role of the Commission of the European Communities in providing the needed resources is stressed throughout the paper. Particular attention is given to the methodological and technological issues addressed by the European research teams, since the results which these teams accomplish are fundamental for a more extensive diffusion of knowledge-based systems in real medical settings. The variety of medical problems tackled shows that there is no field of medicine where the potential of advanced informatics technologies has not yet been assessed.

Artificial Intelligence↗

Knowledge-based prediction of protein structures.

We propose a knowledge-based approach to the prediction of protein structures in cases where there is no sequence-homology to proteins with known spatial structure. Using methods from Artificial Intelligence we attempt to take into account long-range interactions within the prediction process. This allows not only the assignment of secondary but also of supersecondary structure elements. In particular, the patterns used as conditions of prediction rules are generated by learning methods from information contained in the Protein Data Base. Patterns on higher levels of the protein structure hierarchy are used as constraints to reduce the combinatorial search space. These patterns may also be used to search for specified structure motifs by interactive retrieval.

Artificial Intelligence↗

Meta- and reanalysis of gene expression profiles of hot and cold thyroid nodules and papillary thyroid carcinoma for gene groups.

CONTEXT: There are an increasing number of studies analyzing gene expression profiles in various benign and malignant thyroid tumors. This creates the opportunity to validate results obtained from one microarray study with those from other data sets. This process requires rigorous methods for accurate comparison. OBJECTIVE: The ability to compare data sets derived from different Affymetrix GeneChip generations and the influence of intra- and interindividual comparisons of gene expression data were evaluated to build multigene classifiers of benign thyroid nodules to verify a previously proposed papillary thyroid carcinoma (PTC) classifier and to look for molecular pathways essential for PTC oncogenesis. METHODS: Gene expression profile data sets from autonomously functioning and cold thyroid nodules and from PTC were analyzed by support vector machines. GenMAPP analysis was used for PTC data analysis to examine the expression patterns of biologically relevant gene sets. RESULTS: Only intraindividual reference samples allowed the identification of subtle changes in the expression patterns of relevant signaling cascades, such as the MAPK pathway in PTC. Using an artificial intelligence approach, the autonomously functioning and cold thyroid nodule multigene classifiers were derived and evaluated by cross-comparisons. CONCLUSION: We recommend defining classifiers within one generation of gene chips and subsequently checking them across different array generations. Using this approach, we have demonstrated the specificity of a previously reported PTC classifier on an independent collection of benign tumors. Moreover, we propose multigene classifiers for different types of benign thyroid nodules.

Algorithms↗

Future programs at the National Library of Medicine.

The future of the National Library of Medicine will be shaped by a number of scientific, technical, and social influences. Among these are the continuing rapid development of computer technology and storage systems. Artificial intelligence techniques, factual databases, the emergence of medical informatics as a formal discipline, and the development of Integrated Academic Information Management Systems (IAIMS) are also important influences on the direction of the library. Public policy issues will influence the future of NLM--among them, sharing of scientific information between nations and the role of federal agencies in dissemination of information domestically. The formal, long-range plan now being prepared for the library by panels of expert advisers will be a guide for future programs and goals.

Artificial Intelligence↗

An expert system based preventive medicine examination adviser.

Periodic preventive medicine examinations generally rely on a standardized approach. In addition, they are often performed by physicians with only limited training in preventive medicine. Evaluation of a corporate-based program led to the prototype development of an artificial intelligence (AI)-based expert system to collect information from employees and make very specific recommendations for primary practitioners. Unique features include the customizing of questions for each subject and the selection of information to be acquired, both based on answers to previous questions. Recommendations are highly person specific and fall into four categories: laboratory testing, primary physician testing, counseling, and referral. The AI approach allows for easy updating of recommendations in order to meet changes in local preventive resources and national recommendations.

Artificial Intelligence↗

Classification of the frequency of carotid artery stenosis with MLP and RBF neural networks in patients with coroner artery disease.

For the classification of left and right Internal Carotid Arteries (ICA) stenosis, Doppler signals have been received from the patients with coroner arteries stenosis by using 6.2-8.4 MHz linear transducer. To be able to classify the data obtained from LICA and RICA in artificial intelligence, MLP and RBF neural networks were used. The number of obstructed veins from the coroner angiography, intimal thickness, and plaque formation from the power Doppler US and resistive index values were used as the input data for the neural networks. Our findings demonstrated that 87.5% correct classification rate was obtained from MLP neural network and 80% correct classification rate was obtained from RBF neural network. MLP neural network has classified more successfully when compared with RBF neural network.

Artificial Intelligence↗

Knowing that you know: an essay on mechanistic metaknowledge.

Humans are adept at providing accurate statements of confidence in their perceptual identification and recall memory responses. In spite of this, mechanical pattern-recognition systems and other artificial intelligence devices seldom express response certainty. The purpose of this paper is to show how useful confidence ratings can be in integrating the results of a variety of pattern-recognition systems to produce a single, optimal decision concerning the target to be recognized. We outline several ways neural network pattern-recognition systems could be modified to issue confidence ratings with each classification response. In sketching a mechanical system of confidence ratings we find we have also provided a preliminary framework for understanding human confidence judgments and human metacognition.

Artificial Intelligence↗

A general framework for learning rules from data.

With the aim of getting understandable symbolic rules to explain a given phenomenon, we split the task of learning these rules from sensory data in two phases: a multilayer perceptron maps features into propositional variables and a set of subsequent layers operated by a PAC-like algorithm learns Boolean expressions on these variables. The special features of this procedure are that: i) the neural network is trained to produce a Boolean output having the principal task of discriminating between classes of inputs; ii) the symbolic part is directed to compute rules within a family that is not known a priori; iii) the welding point between the two learning systems is represented by a feedback based on a suitability evaluation of the computed rules. The procedure we propose is based on a computational learning paradigm set up recently in some papers in the fields of theoretical computer science, artificial intelligence and cognitive systems. The present article focuses on information management aspects of the procedure. We deal with the lack of prior information about the rules through learning strategies that affect both the meaning of the variables and the description length of the rules into which they combine. The paper uses the task of learning to formally discriminate among several emotional states as both a working example and a test bench for a comparison with previous symbolic and subsymbolic methods in the field.

Algorithms↗

Mechanistic Perspectives From Genomics and Pangenomics of Medicinal and Aromatic Plants: Linking Genome Architecture to Phytochemical Diversity.

Medicinal and aromatic plants (MAPs) produce a remarkable diversity of specialized metabolites with significant pharmaceutical, nutraceutical, and industrial value. Although advances in long-read sequencing, chromosome-scale genome assembly, and pangenomics have greatly expanded genomic resources, the mechanistic links between genome architecture and phytochemical diversity remain incompletely understood. The present review synthesizes current evidence describing how structural genomic variation may contribute to phytochemical diversity, while acknowledging that many proposed genome-to-metabolite relationships require further experimental validation. Examples illustrate how genome architecture is associated with specialized-metabolite biosynthesis through multiple regulatory processes. However, the strength of supporting evidence varies considerably among MAP species. Moreover, relatively few genome-to-metabolite relationships have been confirmed through direct functional validation. We further discuss how pangenomics, multiomics integration, genome editing, synthetic biology, and artificial intelligence support the discovery, validation, and engineering of specialized metabolic pathways. Casual conclusions are evaluated according to the strength of available evidence, highlighting where causal relationships have been experimentally established and where conclusions remain primarily association-based. Overall, this review provides an integrated conceptual and evidence-based perspective summarizing proposed relationships between genome architecture and phytochemical diversity and outlines future priorities for functional genomics, precision breeding, metabolic engineering, and sustainable utilization of MAPs.

artificial intelligence↗

Cardiovascular Complications Are Increased in Inflammatory Bowel Disease: A Path Toward Achievement of a Personalized Risk Estimation.

Background/Objectives: The global burden of inflammatory bowel diseases (IBDs) continues to rise, with up to 50% of patients experiencing extraintestinal manifestations. Cardiovascular diseases (CVDs) are of particular concern, ranking as the second leading cause of mortality in this population. Despite a comparatively lower prevalence of traditional cardiovascular (CV) risk factors, the persistent inflammatory milieu and immune dysregulation inherent to IBD may contribute to heightened CVD risk. In this study, following a review of the current literature, an ongoing prospective trial designed to clarify CV risk profiles in IBD patients is detailed. Methods: A cohort of patients with IBD is being enrolled for comprehensive baseline evaluation of CV risk factors, lifestyle metrics, and disease characteristics. The incidence of major adverse cardiovascular events (MACEs) will be tracked and contrasted with a gender- and age-matched non-IBD cohort over a 2-year follow-up period. In cases of MACE occurrence, a multi-omics analysis-including genomic, proteomic, transcriptomic, and microbiome profiling-will be performed, along with a parallel evaluation in matched IBD controls without MACE. An artificial intelligence (AI) framework will support the analysis of this complex dataset. Results: To date, over 150 patients with IBD have been enrolled, and detailed phenotypic data and biological samples have been collected. Conclusions: We aim to introduce an IBD-specific correction factor for existing CV risk scores upon study completion. This is particularly relevant for individuals under 40 years of age, who are often inadequately assessed by current risk stratification models.

Crohn’s disease↗

ROENTGEN: case-based reasoning and radiation therapy planning.

ROENTGEN is a design assistant for radiation therapy planning which uses case-based reasoning, an artificial intelligence technique. It learns both from specific problem-solving experiences and from direct instruction from the user. The first sort of learning is the normal case-based method of storing problem solutions so that they can be reused. The second sort is necessary because ROENTGEN does not, initially, have an internal model of the physics of its problem domain. This dependence on explicit user instruction brings to the forefront representational questions regarding indexing, failure definition, failure explanation and repair. This paper presents the techniques used by ROENTGEN in its knowledge acquisition and design activities.

Artificial Intelligence↗

Significant differences in the structural basis of the induction of sister chromatid exchanges and chromosomal aberrations in Chinese hamster ovary cells.

The structural basis of the induction of sister chromatid exchanges (SCE) and chromosomal aberrations (Cvt) in Chinese hamster ovary cells was investigated by the CASE (Computer Automated Structure Evaluation) method, an artificial-intelligence-based system. Using the relevant National Toxicology Program data bases CASE identified a set of structural determinants responsible for the induction of SCE and another one for Cvt. A comparison between the structural determinants associated with SCE and Cvt revealed an overlap of only 22.6%, while the overlap between SCE and the determinants of mutagenicity in Salmonella is 54.5%. This indicates a) that the structural bases of the two phenomena differ and b) that it is likely that SCE, but not Cvt, involves a significant electrophilic/DNA-damaging component.

Animals↗

RGSS-ID: an approach to new radiologic reporting system.

RGSS-ID is a developmental computer system that applies artificial intelligence (AI) methods to a reporting system. The representation scheme called Generalized Finding Representation (GFR) is proposed to bridge the gap between natural language expressions in the radiology report and AI methods. The entry process of RGSS-ID is made mainly by selecting items; our system allows a radiologist to compose a sentence which can be completely parsed by the computer. Further RGSS-ID encodes findings into the expression corresponding to GFR, and stores this expression into the knowledge data base. The final printed report is made in the natural language.

Artificial Intelligence↗

Object-centered representation for species systematics and identification in living systems in nature.

An artificial intelligence application to identification in biological taxonomy is presented. An object-centered representation is described using SHIRKA, a knowledge-based system developed in France. The capacities of this system, relating to a classification algorithm, are described. An application to the identification of the trees and lianas of the evergreen forests of the Western Ghats (India) is presented to illustrate the problems encountered in the development of the knowledge base. A model of a systematist's reasoning, using evolutionary principles, is the basis of this work. Finally the efficiency of the system is discussed.

Artificial Intelligence↗

Escherichia coli molecular genetic map (1000 kbp): update I.

The sequenced genes from Escherichia coli that are available in the EMBL library (release 21) have been localized on an updated and corrected version of the restriction map of the chromosome generated by Kohara et al. (1987). One thousand kbp of sequenced DNA are incorporated in this update; this is equivalent to 23% of the total genome. The accuracy of the map is assessed, and it is corrected and updated where appropriate. A significant number of sites were missing from the original map, mainly involving two of the eight enzymes used by Kohara et al. (1987), ie. PvuII and EcoRV. The nucleotide environment of such missing sites was examined and, using an Artificial Intelligence approach, it appears that the site for these enzymes is sensitive to context effects. Several genes of known position on the E. coli chromosome could not be placed on the restriction map; this suggests that additional gaps are likely to exist on the restriction map, in addition to the original seven identified by Kohara et al. We have also obtained information about the probable direction of transcription of chromosomal genes with respect to the map. Most genes are transcribed in the same direction as the replication forks, particularly around oriC at 84 min.

Artificial Intelligence↗

Categorization of major depression in an outpatient sample.

Intake Beck Depression Inventory (BDI) item scores of 400 outpatient major depressives were submitted to a categorization algorithm developed for artificial intelligence applications. The algorithm maximizes a function of "category utility" that is preferable in several respects to available clustering methods, and has demonstrated its capacity to locate the most informative, or "basic," level of categorization. The analysis yielded four syndromal subtypes: a common, general depressive type; a common and relatively severe melancholic type; an infrequent type characterized by self-critical features, generalized anxiety, and an absence of melancholic features; and an infrequent, mild type distinguished by enervation and anhedonic features. Implications for the classification of depression are discussed.

Affective Symptoms↗

Toxicity estimation by chemical substructure analysis: the TOX II program.

The objectives of our work are to develop methodologies capable of identifying the potential environmental health hazards of chemicals. These techniques are particularly useful when it is necessary to evaluate molecules that have not been synthesized as yet, or for which there is little or no toxicological information known. With the help of MULTICASE, an artificial intelligence program capable of uncovering the relationship between the presence of specific substructures in a molecule and its toxicity, and TOX II, a program capable of identifying the existence of such substructures in a new molecule, it is now possible to predict with a reasonable degree of certainty whether a new molecule will be toxic. TOX II will uncover any functionality previously found to be related to toxicity in any organic molecule. The evaluation is extensive and may include its automatically generated metabolites. The scope of TOX II is vast as more than 70 toxicological endpoints can be evaluated.

Artificial Intelligence↗