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 883 records · Page 49Linked to original sources

PubMed2005

Semiautomated four-dimensional computed tomography segmentation using deformable models.

The purpose of this work is to demonstrate a proof of feasibility of the application of a commercial prototype deformable model algorithm to the problem of delineation of anatomic structures on four-dimensional (4D) computed tomography (CT) image data sets. We acquired a 4D CT image data set of a patient's thorax that consisted of three-dimensional (3D) image data sets from eight phases in the respiratory cycle. The contours of the right and left lungs, cord, heart, and esophagus were manually delineated on the end inspiration data set. An interactive deformable model algorithm, originally intended for deforming an atlas-based model surface to a 3D CT image data set, was applied in an automated fashion. Triangulations based on the contours generated on each phase were deformed to the CT data set on the succeeding phase to generate the contours on that phase. Deformation was propagated through the eight phases, and the contours obtained on the end inspiration data set were compared with the original manually delineated contours. Structures defined by high-density gradients, such as lungs, cord, and heart, were accurately reproduced, except in regions where other gradient boundaries may have confused the algorithm, such as near bronchi. The algorithm failed to accurately contour the esophagus, a soft-tissue structure completely surrounded by tissue of similar density, without manual interaction. This technique has the potential to facilitate contour delineation in 4D CT image data sets; and future evolution of the software is expected to improve the process.

Algorithms↗

PubMed2004

Automated soil resources mapping based on decision tree and Bayesian predictive modeling.

This article presents two approaches for automated building of knowledge bases of soil resources mapping. These methods used decision tree and Bayesian predictive modeling, respectively to generate knowledge from training data. With these methods, building a knowledge base for automated soil mapping is easier than using the conventional knowledge acquisition approach. The knowledge bases built by these two methods were used by the knowledge classifier for soil type classification of the Longyou area, Zhejiang Province, China using TM bi-temporal imageries and GIS data. To evaluate the performance of the resultant knowledge bases, the classification results were compared to existing soil map based on field survey. The accuracy assessment and analysis of the resultant soil maps suggested that the knowledge bases built by these two methods were of good quality for mapping distribution model of soil classes over the study area.

Algorithms↗

PubMed2005

Using argumentation to retrieve articles with similar citations: an inquiry into improving related articles search in the MEDLINE digital library.

The aim of this study is to investigate the relationships between citations and the scientific argumentation found abstracts. We design a related article search task and observe how the argumentation can affect the search results. We extracted citation lists from a set of 3200 full-text papers originating from a narrow domain. In parallel, we recovered the corresponding MEDLINE records for analysis of the argumentative moves. Our argumentative model is founded on four classes: PURPOSE, METHODS, RESULTS and CONCLUSION. A Bayesian classifier trained on explicitly structured MEDLINE abstracts generates these argumentative categories. The categories are used to generate four different argumentative indexes. A fifth index contains the complete abstract, together with the title and the list of Medical Subject Headings (MeSH) terms. To appraise the relationship of the moves to the citations, the citation lists were used as the criteria for determining relatedness of articles, establishing a benchmark; it means that two articles are considered as "related" if they share a significant set of co-citations. Our results show that the average precision of queries with the PURPOSE and CONCLUSION features is the highest, while the precision of the RESULTS and METHODS features was relatively low. A linear weighting combination of the moves is proposed, which significantly improves retrieval of related articles.

Abstracting and Indexing↗

PubMedDate not supplied

Concept design of computer-aided study on traditional Chinese drugs.

Traditional Chinese drugs (TCDs) have played a key role for Chinese people in the treatment of diseases since ancient times. The use of TCDs has generated a great amount of information in the past thousand years about the relationship between natural products and the human body. However, up to now, our understanding on the mode of action of the TCD is still limited. Considering that the basic mechanism of all drug function involves the interaction between the drug and biological receptors at the molecular level, we propose to connect TCDs with modern medicine theory through molecular structures. We propose to explain functions of TCDs by using the knowledge developed in modern molecular biology, pharmacology, computer chemistry, and biochemistry. We are working on a computer-aided Chinese drug study that is discussed in this paper. A short introduction on the progress of our research is also given.

Artificial Intelligence↗

PubMed2005

A knowledge-based energy function for protein-ligand, protein-protein, and protein-DNA complexes.

We developed a knowledge-based statistical energy function for protein-ligand, protein-protein, and protein-DNA complexes by using 19 atom types and a distance-scale finite ideal-gas reference (DFIRE) state. The correlation coefficients between experimentally measured protein-ligand binding affinities and those predicted by the DFIRE energy function are around 0.63 for one training set and two testing sets. The energy function also makes highly accurate predictions of binding affinities of protein-protein and protein-DNA complexes. Correlation coefficients between theoretical and experimental results are 0.73 for 82 protein-protein (peptide) complexes and 0.83 for 45 protein-DNA complexes, despite the fact that the structures of protein-protein (peptide) and protein-DNA complexes were not used in training the energy function. The results of the DFIRE energy function on protein-ligand complexes are compared to the published results of 12 other scoring functions generated from either physical-based, knowledge-based, or empirical methods. They include AutoDock, X-Score, DrugScore, four scoring functions in Cerius 2 (LigScore, PLP, PMF, and LUDI), four scoring functions in SYBYL (F-Score, G-Score, D-Score, and ChemScore), and BLEEP. While the DFIRE energy function is only moderately successful in ranking native or near native conformations, it yields the strongest correlation between theoretical and experimental binding affinities of the testing sets and between rmsd values and energy scores of docking decoys in a benchmark of 100 protein-ligand complexes. The parameters and the program of the all-atom DFIRE energy function are freely available for academic users at http://theory.med.buffalo.edu.

Algorithms↗

PubMed2004

Mismatch string kernels for discriminative protein classification.

MOTIVATION: Classification of proteins sequences into functional and structural families based on sequence homology is a central problem in computational biology. Discriminative supervised machine learning approaches provide good performance, but simplicity and computational efficiency of training and prediction are also important concerns. RESULTS: We introduce a class of string kernels, called mismatch kernels, for use with support vector machines (SVMs) in a discriminative approach to the problem of protein classification and remote homology detection. These kernels measure sequence similarity based on shared occurrences of fixed-length patterns in the data, allowing for mutations between patterns. Thus, the kernels provide a biologically well-motivated way to compare protein sequences without relying on family-based generative models such as hidden Markov models. We compute the kernels efficiently using a mismatch tree data structure, allowing us to calculate the contributions of all patterns occurring in the data in one pass while traversing the tree. When used with an SVM, the kernels enable fast prediction on test sequences. We report experiments on two benchmark SCOP datasets, where we show that the mismatch kernel used with an SVM classifier performs competitively with state-of-the-art methods for homology detection, particularly when very few training examples are available. Examination of the highest-weighted patterns learned by the SVM classifier recovers biologically important motifs in protein families and superfamilies.

Algorithms↗

PubMed2004

Frequency-sensitive competitive learning for scalable balanced clustering on high-dimensional hyperspheres.

Competitive learning mechanisms for clustering, in general, suffer from poor performance for very high-dimensional (>1000) data because of "curse of dimensionality" effects. In applications such as document clustering, it is customary to normalize the high-dimensional input vectors to unit length, and it is sometimes also desirable to obtain balanced clusters, i.e., clusters of comparable sizes. The spherical kmeans (spkmeans) algorithm, which normalizes the cluster centers as well as the inputs, has been successfully used to cluster normalized text documents in 2000+ dimensional space. Unfortunately, like regular kmeans and its soft expectation-maximization-based version, spkmeans tends to generate extremely imbalanced clusters in high-dimensional spaces when the desired number of clusters is large (tens or more). This paper first shows that the spkmeans algorithm can be derived from a certain maximum likelihood formulation using a mixture of von Mises-Fisher distributions as the generative model, and in fact, it can be considered as a batch-mode version of (normalized) competitive learning. The proposed generative model is then adapted in a principled way to yield three frequency-sensitive competitive learning variants that are applicable to static data and produced high-quality and well-balanced clusters for high-dimensional data. Like kmeans, each iteration is linear in the number of data points and in the number of clusters for all the three algorithms. A frequency-sensitive algorithm to cluster streaming data is also proposed. Experimental results on clustering of high-dimensional text data sets are provided to show the effectiveness and applicability of the proposed techniques. Index Terms-Balanced clustering, expectation maximization (EM), frequency-sensitive competitive learning (FSCL), high-dimensional clustering, kmeans, normalized data, scalable clustering, streaming data, text clustering.

Artificial Intelligence↗

PubMed2005

Using unsupervised learning with independent component analysis to identify patterns of glaucomatous visual field defects.

PURPOSE: Clustering by unsupervised learning with machine learning classifiers was shown to segment clusters of patterns in standard automated perimetry (SAP) for glaucoma in previous publications. In this study, unsupervised learning by independent component analysis decomposed SAP field patterns into axes, and the information represented by these axes was evaluated. METHODS: SAP fields were used that were obtained with the Humphrey Visual Field Analyzer (Carl Zeiss Meditec, Dublin, CA) from 189 normal eyes and 156 eyes with glaucomatous optic neuropathy (GON) determined by masked review with stereoscopic optic disc photographs. The variational Bayesian independent component analysis mixture model (vB-ICA-mm) partitioned the SAP fields into the most informative number of clusters. Simultaneously, the model learned an optimal number of maximally independent axes for each cluster. RESULTS: The most informative number of clusters in the SAP set was two. vB-ICA-mm placed 68.6% of the eyes with GON in a cluster labeled G and 98.4% of the eyes with normal optic discs in a cluster labeled N. Cluster G optimally contained six axes. Post hoc analysis of patterns generated at -1 SD and +2 SD from the cluster G mean on the six axes revealed defects similar to those identified by experts as indicative of glaucoma. SAP fields associated with an axis showed increasing severity, as they were located farther in the positive direction from the cluster G mean. CONCLUSIONS: vB-ICA-mm represented the SAP fields with patterns that were meaningful for glaucoma experts. This process also captured severity in the patterns uncovered. These findings should validate vB-ICA-mm as a data-mining technique for new and unfamiliar complex tests.

Artificial Intelligence↗

PubMed2003

Categorization of sentence types in medical abstracts.

This study evaluated the use of machine learning techniques in the classification of sentence type. 7253 structured abstracts and 204 unstructured abstracts of Randomized Controlled Trials from MedLINE were parsed into sentences and each sentence was labeled as one of four types (Introduction, Method, Result, or Conclusion). Support Vector Machine (SVM) and Linear Classifier models were generated and evaluated on cross-validated data. Treating sentences as a simple "bag of words", the SVM model had an average ROC area of 0.92. Adding a feature of relative sentence location improved performance markedly for some models and overall increasing the average ROC to 0.95. Linear classifier performance was significantly worse than the SVM in all datasets. Using the SVM model trained on structured abstracts to predict unstructured abstracts yielded performance similar to that of models trained with unstructured abstracts in 3 of the 4 types. We conclude that classification of sentence type seems feasible within the domain of RCT's. Identification of sentence types may be helpful for providing context to end users or other text summarization techniques.

Abstracting and Indexing↗

PubMed2006

On algorithmic rate-coded AER generation.

This paper addresses the problem of converting a conventional video stream based on sequences of frames into the spike event-based representation known as the address-event-representation (AER). In this paper we concentrate on rate-coded AER. The problem is addressed as an algorithmic problem, in which different methods are proposed, implemented and tested through software algorithms. The proposed algorithms are comparatively evaluated according to different criteria. Emphasis is put on the potential of such algorithms for a) doing the frame-based to event-based representation in real time, and b) that the resulting event streams ressemble as much as possible those generated naturally by rate-coded address-event VLSI chips, such as silicon AER retinae. It is found that simple and straightforward algorithms tend to have high potential for real time but produce event distributions that differ considerably from those obtained in AER VLSI chips. On the other hand, sophisticated algorithms that yield better event distributions are not efficient for real time operations. The methods based on linear-feedback-shift-register (LFSR) pseudorandom number generation is a good compromise, which is feasible for real time and yield reasonably well distributed events in time. Our software experiments, on a 1.6-GHz Pentium IV, show that at 50% AER bus load the proposed algorithms require between 0.011 and 1.14 ms per 8 bit-pixel per frame. One of the proposed LFSR methods is implemented in real time hardware using a prototyping board that includes a VirtexE 300 FPGA. The demonstration hardware is capable of transforming frames of 64 x 64 pixels of 8-bit depth at a frame rate of 25 frames per second, producing spike events at a peak rate of 10(7) events per second.

Algorithms↗

PubMed2004

The writer independent online handwriting recognition system frog on hand and cluster generative statistical dynamic time warping.

In this paper, we give a comprehensive description of our writer-independent online handwriting recognition system frog on hand. The focus of this work concerns the presentation of the classification/training approach, which we call cluster generative statistical dynamic time warping (CSDTW). CSDTW is a general, scalable, HMM-based method for variable-sized, sequential data that holistically combines cluster analysis and statistical sequence modeling. It can handle general classification problems that rely on this sequential type of data, e.g., speech recognition, genome processing, robotics, etc. Contrary to previous attempts, clustering and statistical sequence modeling are embedded in a single feature space and use a closely related distance measure. We show character recognition experiments of frog on hand using CSDTW on the UNIPEN online handwriting database. The recognition accuracy is significantly higher than reported results of other handwriting recognition systems. Finally, we describe the real-time implementation of frog on hand on a Linux Compaq iPAQ embedded device.

Algorithms↗

PubMed1998

Simulating patients with Parallel Health State Networks.

The American Board of Family Practice is developing a computer-based recertification process to generate patient simulations from a knowledge base. Simulated patients require a stochastically generated history and response to treatment, suggesting a Monte Carlo-like patient generation process. Knowledge acquisition experiments revealed that description of a patient's overall health as a node in a Monte Carlo model was difficult for domain experts to use, severely limited knowledge reusability, and created a plethora of awkwardly defined health states. We explored a model in which patients traverse several parallel health state networks simultaneously, so that overall health is a vector describing the current nodes from every Parallel Network. This model has a reasonable biological basis, more easily defined data, and greatly improved reuse potential, at the cost of more complex simulation algorithms. Experiments using osteoarthritis stages, weight classification, and absence or presence of gastric ulcers as three Parallel Networks demonstrate the feasibility of this approach to simulating patients.

Algorithms↗

PubMed2006

User customization of the feature generator of an asynchronous brain interface.

A study that customizes the feature generator parameters of an asynchronous Brain Interface (BI) is discussed. The goal is to detect the presence of a certain pattern, in the ongoing EEG, associated with a specific movement and to improve the system's performance. Results of this study show that customization mostly benefits able-bodied subjects with performance improvements of up to 6.8%. We evaluate the performance of our BI using stratified cross-validation scheme. This scheme repeats the analysis on the different cross-validation sets. It is shown that the performances of the system across the different sets are very similar. Thus, we conclude that a robust performance measure of the system can be obtained by using only one of these performance results.

Artificial Intelligence↗

PubMed2001

ONCODOC: a successful experiment of computer-supported guideline development and implementation in the treatment of breast cancer.

Originally published as textual documents, clinical practice guidelines have poorly penetrated medical practice because their editorial properties do not allow the reader to easily solve, at the point of care, a given medical problem. However, despite the proliferation of implemented clinical practice guidelines as decision support systems providing an easy access to patient-centered information, there is still little evidence of high physician compliance to guidelines recommendations. Apart from physicians' psychological reluctance, the incompleteness of guideline knowledge and the impreciseness of the terms used, another reason may be that, although suited to average patients, clinical practice guideline recommendations are not a substitute for the physician-controlled clinical judgement that should be applied to each actual individual patient. Therefore, computer-based approaches based on the automation of context-free operationalization of guideline knowledge, although providing uniform optimal strategies to problem-focused care delivery, may generate inappropriate inferences for a specific patient that the physician does not follow in practice. Rather than providing automated decision support, ONCODOC allows the clinician to control the operationalization of guideline knowledge through his hypertextual reading of a knowledge base encoded as a decision tree. In this way, he has the opportunity to interpret the information provided in the context of his patient, therefore, controlling his categorization to the closest matching formal patient. Experimented in life-size ONCODOC demonstrated good appropriation of the system by physicians with significantly high scores of compliance. We successfully tested the implemented strategy and the knowledge base in a second medical institution, giving then a noticeable example of reuse and sharing of encoded guideline knowledge across institutions.

Artificial Intelligence↗

PubMed2005

Evolutionary search for faces from line drawings.

Single 2D line drawing is a straightforward method to illustrate 3D objects. The faces of an object depicted by a line drawing give very useful information for the reconstruction of its 3D geometry. Two recently proposed methods for face identification from line drawings are based on two steps: finding a set of circuits that may be faces and searching for real faces from the set according to some criteria. The two steps, however, involve two combinatorial problems. The number of the circuits generated in the first step grows exponentially with the number of edges of a line drawing. These circuits are then used as the input to the second combinatorial search step. When dealing with objects having more faces, the combinatorial explosion prevents these methods from finding solutions within feasible time. This paper proposes a new method to tackle the face identification problem by a variable-length genetic algorithm with a novel heuristic and geometric constraints incorporated for local search. The hybrid GA solves the two combinatorial problems simultaneously. Experimental results show that our algorithm can find the faces of a line drawing having more than 30 faces much more efficiently. In addition, simulated annealing for solving the face identification problem is also implemented for comparison.

Algorithms↗

PubMed2005

Evaluation of methods to detect interhemispheric asymmetry on cerebral perfusion SPECT: application to epilepsy.

UNLABELLED: Detecting perfusion interhemispheric asymmetry in neurologic nuclear medicine imaging is an interesting approach to epilepsy. METHODS: This study compared 4 methods that detect interhemispheric asymmetries of brain perfusion in SPECT. The first (M1) was conventional side-by-side expert-based visual interpretation of SPECT. The second (M2) was visual interpretation assisted by an interhemispheric difference (IHD) volume. The last 2 were automatic methods: unsupervised analysis using volumes of interest (M3) and unsupervised analysis of the IHD volume (M4). Use of these methods to detect possible perfusion asymmetry was compared on 60 simulated SPECT datasets by controlling the presence and location of asymmetries. From the detection results, localization receiver operating characteristic curves were generated and areas under curves were estimated and compared. Finally, the methods were applied to analyze interictal SPECT datasets to localize the epileptogenic focus in temporal lobe epilepsies. RESULTS: This study showed an improvement in asymmetry detection on SPECT images with the methods using IHD volume (M2 and M4), in comparison with the other methods (M1 and M3). However, the most useful method for analyzing clinical SPECT datasets appeared to be visual inspection assisted by the IHD volume, since the automatic method using the IHD volume was less specific. CONCLUSION: The use of quantitative methods can improve performance in detection of perfusion asymmetry over visual inspection alone.

Adolescent↗

PubMed2002

Discovery informatics: its evolving role in drug discovery.

Drug discovery and development is a highly complex process requiring the generation of very large amounts of data and information. Currently this is a largely unmet informatics challenge. The current approaches to building information and knowledge from large amounts of data has been addressed in cases where the types of data are largely homogeneous or at the very least well-defined. However, we are on the verge of an exciting new era of drug discovery informatics in which methods and approaches dealing with creating knowledge from information and information from data are undergoing a paradigm shift. The needs of this industry are clear: Large amounts of data are generated using a variety of innovative technologies and the limiting step is accessing, searching and integrating this data. Moreover, the tendency is to move crucial development decisions earlier in the discovery process. It is crucial to address these issues with all of the data at hand, not only from current projects but also from previous attempts at drug development. What is the future of drug discovery informatics? Inevitably, the integration of heterogeneous, distributed data are required. Mining and integration of domain specific information such as chemical and genomic data will continue to develop. Management and searching of textual, graphical and undefined data that are currently difficult, will become an integral part of data searching and an essential component of building information- and knowledge-bases.

Artificial Intelligence↗

PubMed2004

Classification of kinase inhibitors using a Bayesian model.

The use of Bayesian statistics to model both general (multifamily) and specific (single-target) kinase inhibitors is investigated. The approach demonstrates an alternative to current computational methods applied to heterogeneous structure/activity data sets. This approach operates rapidly and is readily modifiable as required. A generalized model generated using inhibitor data from multiple kinase classes shows meaningful enrichment for several specific kinase targets. Such an approach can be used to prioritize compounds for screening or to optimally select compounds from third-party data collections. The observed benefit of the approach is finding compounds that are not structurally related to known actives, or novel targets for which there is not enough information to build a specific kinase model. The general kinase model described was built from a basis of mostly tyrosine kinase inhibitors, with some serine/threonine inhibitors; all the test cases used in prediction were also on tyrosine kinase targets. Confirming the applicability of this technique to other kinase families will be determined once those biological assays become available.

Artificial Intelligence↗