SEARCH · PubMed Health

Results for “generative 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 721 records · Page 40Linked to original sources

PubMed2002

Maximum entropy modeling for mining patient medication status from free text.

Using a classification scheme of patient medication status we sought to recognize and categorize medications mentioned in the unrestricted text of clinical documents generated in clinical practice. The categories refer to the patient's status with respect to the medication such as discontinuation, start or initiation, and continuation of a given medication. This categorization is performed with a machine learning technique, Maximum Entropy (ME), that is well suited to incorporating heterogeneous sources of information necessary for classifying patient's medication status. We use hand labeled training data to generate ME models and test 5 different training feature sets. Our results show that the most optimal feature set includes a combination of the following: two words preceding and following the mention of the drug, the subject of the sentence in which the drug mention occurs, the 2 words following the subject, and a binary feature vector of lexicalized semantic cues indicative of medication status or its change. The average predictive power of a model trained on these features is approximately 89%.

Artificial Intelligence↗

PubMed2002

Prediction of aqueous solubility of organic compounds using a quantitative structure-property relationship.

A quantitative structure-property relationship (QSPR) was developed for predicting the aqueous solubility of drug-like compounds from their chemical structures. A set of 321 structurally diverse drugs or related compounds, with their intrinsic aqueous solubility collected from literature, was used in this analysis. The data were divided into a training set (n = 267) for building the model and a randomly chosen testing set (n = 54) for assessing the predictive ability of the model. A series of molecular descriptors was calculated directly from chemical structures and a set of eight descriptors, including dipole moment, surface area, volume, molecular weight, number of rotatable bonds/total bonds, number of hydrogen-bond acceptors, number of hydrogen-bond donors and density, was chosen for the final model. The eight-descriptor model generated by multiple linear regression was further optimized by a genetic algorithm guided selection method. The model has a correlation coefficient (r) of 0.95 and a root-mean-square (rms) error of 0.56 log unit. It predicts the solubility of testing set compounds with a reasonable degree of accuracy (r = 0.84 and rms = 0.86 log unit). The present model can serve as a tool for medicinal chemists to guide their early synthetic efforts in arriving at appropriate analogs.

Algorithms↗

PubMed2006

Improving automatic analysis of the electrocardiogram acquired during magnetic resonance imaging using magnetic field gradient artefact suppression.

The electrocardiogram (ECG) used for patient monitoring during magnetic resonance imaging (MRI) unfortunately suffers from severe artefacts. These artefacts are due to the special environment of the MRI. Modeling helped in finding solutions for the suppression of these artefacts superimposed on the ECG signal. After we validated the linear and time invariant model for the magnetic field gradient artefact generation, we applied offline and online filters for their suppression. Wiener filtering (offline) helped in generating reference annotations of the ECG beats. In online filtering, the least-mean-square filter suppressed the magnetic field gradient artefacts before the acquired ECG signal was input to the arrhythmia algorithm. Comparing the results of two runs (one run using online filtering and one run without) to our reference annotations, we found an eminent improvement in the arrhythmia module's performance, enabling reliable patient monitoring and MRI synchronization based on the ECG signal.

Algorithms↗

PubMed2003

Designing a knowledge management system for distributed activities: a human centered approach.

In this study we use the principles of distributed cognition and the methodology of human-centered distributed information design to analyze a complex distributed human-computer system, identify its problems, and generate design requirements and implementation specifications of a replacement prototype for effective organizational memory and knowledge management. We argue that a distributed human-computer information system has unique properties, structures and processes that are best described in the language of distributed cognition. Distributed cognition provides researchers a richer theoretical understanding of human-computer interactions and enables re-searchers to capture the phenomenon that emerges in social interactions as well as the interactions between people and structures in their environment.

Artificial Intelligence↗

PubMed1993

Generating MEDLINE search strategies using a librarian knowledge-based system.

We describe a librarian knowledge-based system that generates a search strategy from a query representation based on a user's information need. Together with the natural language parser AQUA, the system functions as a human/computer interface, which translates a user query from free text into a BRS Onsite search formulation, for searching the MEDLINE bibliographic database. In the system, conceptual graphs are used to represent the user's information need. The UMLS Metathesaurus and Semantic Net are used as the key knowledge sources in building the knowledge base.

Artificial Intelligence↗

PubMed2001

Generation of an intelligent medical system, using a real database, to diagnose bacterial infection in hospitalized patients.

The initial diagnosis of bacterial infections in the absence of laboratory microbiological data requires physicians to use clinical algorithms based on symptoms, patient history and infection site. Optimization of such algorithms would be achieved by including as many variables associated with bacterial infection as possible. Demographic data are easily available and frequently used to sub-group human populations. A prospective investigation was, therefore, undertaken to examine the influence of demographic variables on bacterial infection rates, using data obtained from 173 patients presenting to Albert Einstein Medical Center. Data was randomly selected from 149 of these patients and used to generate fuzzy rules to model an intelligent medical system. To test the accuracy of this system at determining bacterial infection, based solely on demographic data, the program was given the remaining 24 patients' information. All 18 patients with either streptococcal, staphylococcal or Escherichia coli infections were correctly diagnosed. Non-E.coli GNR were misdiagnosed as E. coli infections in two patients resulting in an overall prediction rate for the 24 patients of 91.66%. This study suggests that the direct correlation of demographic variables with a predisposition to bacterial infection allow the design of an intelligent medical system, which shows great future potential as a diagnostic tool for all physicians.

Adult↗

PubMed2000

Predictions of protein segments with the same aminoacid sequence and different secondary structure: a benchmark for predictive methods.

The most stringent test for predictive methods of protein secondary structure is whether identical short sequences that are known to be present with different conformations in different proteins known at atomic resolution can be correctly discriminated. In this study, we show that the prediction efficiency of this type of segments in unrelated proteins reaches an average accuracy per residue ranging from about 72 to 75% (depending on the alignment method used to generate the input sequence profile) only when methods of the third generation are used. A comparison of different methods based on segment statistics (2nd generation methods) and/or including also evolutionary information (3rd generation methods) indicate that the discrimination of the different conformations of identical segments is dependent on the method used for the prediction. Accuracy is similar when methods similarly performing on the secondary structure prediction are tested. When evolutionary information is taken into account as compared to single sequence input, the number of correctly discriminated pairs is increased twofold. The results also highlight the predictive capability of neural networks for identical segments whose conformation differs in different proteins.

Algorithms↗

PubMed2005

Shape-based averaging for combination of multiple segmentations.

Combination of multiple segmentations has recently been introduced as an effective method to obtain segmentations that are more accurate than any of the individual input segmentations. This paper introduces a new way to combine multiple segmentations using a novel shape-based averaging method. Individual segmentations are combined based on the signed Euclidean distance maps of the labels in each input segmentation. Compared to label voting, the new combination method produces smoother, more regular output segmentations and avoids fragmentation of contiguous structures. Using publicly available segmented human brain MR images (IBSR database), we perform a quantitative comparison between shape-based averaging and label voting by combining random segmentations with controlled error magnitudes and known ground truth. Shape-based averaging generated combined segmentations that were closer to the ground truth than combinations from label voting for all numbers of input segmentations (up to ten). The relative advantage of shape-based averaging over voting was larger for fewer input segmentations, and larger for greater deviations of the input segmentations from the ground truth. We conclude that shape-based averaging improves the accuracy of combined segmentations, in particular when only a few input segmentations are available and when the quality of the input segmentations is low.

Algorithms↗

PubMed2005

Discovering patterns to extract protein-protein interactions from the literature: Part II.

MOTIVATION: An enormous number of protein-protein interaction relationships are buried in millions of research articles published over the years, and the number is growing. Rediscovering them automatically is a challenging bioinformatics task. Solutions to this problem also reach far beyond bioinformatics. RESULTS: We study a new approach that involves automatically discovering English expression patterns, optimizing them and using them to extract protein-protein interactions. In a sister paper, we described how to generate English expression patterns related to protein-protein interactions, and this approach alone has already achieved precision and recall rates significantly higher than those of other automatic systems. This paper continues to present our theory, focusing on how to improve the patterns. A minimum description length (MDL)-based pattern-optimization algorithm is designed to reduce and merge patterns. This has significantly increased generalization power, and hence the recall and precision rates, as confirmed by our experiments. AVAILABILITY: http://spies.cs.tsinghua.edu.cn.

Abstracting and Indexing↗

PubMed2005

Spatio-temporal nonrigid registration for ultrasound cardiac motion estimation.

We propose a new spatio-temporal elastic registration algorithm for motion reconstruction from a series of images. The specific application is to estimate displacement fields from two-dimensional ultrasound sequences of the heart. The basic idea is to find a spatio-temporal deformation field that effectively compensates for the motion by minimizing a difference with respect to a reference frame. The key feature of our method is the use of a semi-local spatio-temporal parametric model for the deformation using splines, and the reformulation of the registration task as a global optimization problem. The scale of the spline model controls the smoothness of the displacement field. Our algorithm uses a multiresolution optimization strategy to obtain a higher speed and robustness. We evaluated the accuracy of our algorithm using a synthetic sequence generated with an ultrasound simulation package, together with a realistic cardiac motion model. We compared our new global multiframe approach with a previous method based on pairwise registration of consecutive frames to demonstrate the benefits of introducing temporal consistency. Finally, we applied the algorithm to the regional analysis of the left ventricle. Displacement and strain parameters were evaluated showing significant differences between the normal and pathological segments, thereby illustrating the clinical applicability of our method.

Artificial Intelligence↗

PubMedDate not supplied

Hardware-assisted visibility sorting for unstructured volume rendering.

Harvesting the power of modern graphics hardware to solve the complex problem of real-time rendering of large unstructured meshes is a major research goal in the volume visualization community. While, for regular grids, texture-based techniques are well-suited for current GPUs, the steps necessary for rendering unstructured meshes are not so easily mapped to current hardware. We propose a novel volume rendering technique that simplifies the CPU-based processing and shifts much of the sorting burden to the GPU, where it can be performed more efficiently. Our hardware-assisted visibility sorting algorithm is a hybrid technique that operates in both object-space and image-space. In object-space, the algorithm performs a partial sort of the 3D primitives in preparation for rasterization. The goal of the partial sort is to create a list of primitives that generate fragments in nearly sorted order. In image-space, the fragment stream is incrementally sorted using a fixed-depth sorting network. In our algorithm, the object-space work is performed by the CPU and the fragment-level sorting is done completely on the GPU. A prototype implementation of the algorithm demonstrates that the fragment-level sorting achieves rendering rates of between one and six million tetrahedral cells per second on an ATI Radeon 9800.

Algorithms↗

PubMed2003

Cost component analysis.

In optimizations the dimension of the problem may severely, sometimes exponentially increase optimization time. Parametric function approximatiors (FAPPs) have been suggested to overcome this problem. Here, a novel FAPP, cost component analysis (CCA) is described. In CCA, the search space is resampled according to the Boltzmann distribution generated by the energy landscape. That is, CCA converts the optimization problem to density estimation. Structure of the induced density is searched by independent component analysis (ICA). The advantage of CCA is that each independent ICA component can be optimized separately. In turn, (i) CCA intends to partition the original problem into subproblems and (ii) separating (partitioning) the original optimization problem into subproblems may serve interpretation. Most importantly, (iii) CCA may give rise to high gains in optimization time. Numerical simulations illustrate the working of the algorithm.

Algorithms↗

PubMed2004

The affirmation of self: a new perspective on the immune system.

The fundamental concepts of autopoiesis, which emphasize the circular organization underlying both living organisms and cognition, have been criticized on the grounds that since they are conceived as a tight logical chain of definitions and implications, it is often not clear whether they are indeed a scientific theory or rather just a potential scientific vocabulary of doubtful utility to working scientists. This article presents the deployment of the concepts of autopoiesis in the field of immunology, a discipline where working biologists themselves spontaneously have long had recourse to "cognitive" metaphors: "recognition"; a "repertoire" of recognized molecular shapes; "learning" and "memory"; and, most striking of all, a "self versus non-self" distinction. It is shown that in immunology, the concepts of autopoiesis can be employed to generate clear novel hypotheses, models demonstrating these ideas, testable predictions, and novel therapeutic procedures. Epistemologically, it is shown that the self-non-self distinction, while quite real, is misleadingly named. When a real mechanism for generating this distinction is identified, it appears that the actual operational distinction is between (a) a sufficiently numerous set of initial antigens, present from the start of ontogeny, in conditions that allow for their participation in the construction of the system's organization and operation, and (b) single antigens that are first presented to the system after two successive phases of maturation. To call this a self-non-self distinction obscures the issue by presupposing what it ought to be the job of scientific investigation to explain.

Artificial Intelligence↗

PubMed1994

Generating explanations and tutorial problems from Bayesian networks.

We present a system that generates explanations and tutorial problems from the probabilistic information contained in Bayesian belief networks. BANTER is a tool for high-level interaction with any Bayesian network whose nodes can be classified as hypotheses, observations, and diagnostic procedures. Users need no knowledge of Bayesian networks, only familiarity with the particular domain and an elementary understanding of probability. Users can query the knowledge base, identify optimal diagnostic procedures, and request explanations. We describe BANTER's algorithms and illustrate its application to an existing medical model.

Algorithms↗

PubMed2004

Human-centric intelligent systems for exploration and knowledge discovery.

This speculative article discusses research and development relating to computational intelligence (CI) technologies comprising powerful machine-based search and exploration techniques that can generate, extract, process and present high-quality information from complex, poorly understood biotechnology domains. The integration and capture of user experiential knowledge within such CI systems in order to support and stimulate knowledge discovery and increase scientific and technological understanding is of particular interest. The manner in which appropriate user interaction can overcome problems relating to poor problem representation within systems utilising evolutionary computation (EC), machine-learning and software agent technologies is investigated. The objective is the development of user-centric intelligent systems that support an improving knowledge-base founded upon gradual problem re-definition and reformulation. Such an approach can overcome initial lack of understanding and associated uncertainty.

Artificial Intelligence↗

PubMed1991

A model for diagnosing and explaining multiple disorders.

The ability to diagnose multiple interacting disorders and explain them in a coherent causal framework has only partially been achieved in medical expert systems. This paper proposes a causal model for diagnosing and explaining multiple disorders whose key elements are: physician-directed hypotheses generation, object-oriented knowledge representation, and novel explanation heuristics. The heuristics modify and link the explanations to make the physician aware of diagnostic complexities. A computer program incorporating the model currently is in use for diagnosing peripheral nerve and muscle disorders. The program successfully diagnoses and explains interactions between diseases in terms of underlying pathophysiologic concepts. The model offers a new architecture for medical domains where reasoning from first principles is difficult but explanation of disease interactions is crucial for the system's operation.

Acid-Base Imbalance↗

PubMed2004

Design of vector quantizer for image compression using self-organizing feature map and surface fitting.

We propose a new scheme of designing a vector quantizer for image compression. First, a set of codevectors is generated using the self-organizing feature map algorithm. Then, the set of blocks associated with each code vector is modeled by a cubic surface for better perceptual fidelity of the reconstructed images. Mean-removed vectors from a set of training images is used for the construction of a generic codebook. Further, Huffman coding of the indices generated by the encoder and the difference-coded mean values of the blocks are used to achieve better compression ratio. We proposed two indices for quantitative assessment of the psychovisual quality (blocking effect) of the reconstructed image. Our experiments on several training and test images demonstrate that the proposed scheme can produce reconstructed images of good quality while achieving compression at low bit rates. Index Terms-Cubic surface fitting, generic codebook, image compression, self-organizing feature map, vector quantization.

Algorithms↗

PubMed2006

Deriving pathway maps from automated text analysis using a grammar-based approach.

We demonstrate how automated text analysis can be used to support the large-scale analysis of metabolic and regulatory pathways by deriving pathway maps from textual descriptions found in the scientific literature. The main assumption is that correct syntactic analysis combined with domain-specific heuristics provides a good basis for relation extraction. Our method uses an algorithm that searches through the syntactic trees produced by a parser based on a Referent Grammar formalism, identifies relations mentioned in the sentence, and classifies them with respect to their semantic class and epistemic status (facts, counterfactuals, hypotheses). The semantic categories used in the classification are based on the relation set used in KEGG (Kyoto Encyclopedia of Genes and Genomes), so that pathway maps using KEGG notation can be automatically generated. We present the current version of the relation extraction algorithm and an evaluation based on a corpus of abstracts obtained from PubMed. The results indicate that the method is able to combine a reasonable coverage with high accuracy. We found that 61% of all sentences were parsed, and 97% of the parse trees were judged to be correct. The extraction algorithm was tested on a sample of 300 parse trees and was found to produce correct extractions in 90.5% of the cases.

Abstracting and Indexing↗