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 865 records · Page 48Linked to original sources

PubMed2006

OrthologID: automation of genome-scale ortholog identification within a parsimony framework.

MOTIVATION: The determination of gene orthology is a prerequisite for mining and utilizing the rapidly increasing amount of sequence data for genome-scale phylogenetics and comparative genomic studies. Until now, most researchers use pairwise distance comparisons algorithms, such as BLAST, COG, RBH, RSD and INPARANOID, to determine gene orthology. In contrast, orthology determination within a character-based phylogenetic framework has not been utilized on a genomic scale owing to the lack of efficiency and automation. RESULTS: We have developed OrthologID, a Web application that automates the labor-intensive procedures of gene orthology determination within a character-based phylogenetic framework, thus making character-based orthology determination on a genomic scale possible. In addition to generating gene family trees and determining orthologous gene sets for complete genomes, OrthologID can also identify diagnostic characters that define each orthologous gene set, as well as diagnostic characters that are responsible for classifying query sequences from other genomes into specific orthology groups. The OrthologID database currently includes several complete plant genomes, including Arabidopsis thaliana, Oryza sativa, Populus trichocarpa, as well as a unicellular outgroup, Chlamydomonas reinhardtii. To improve the general utility of OrthologID beyond plant species, we plan to expand our sequence database to include the fully sequenced genomes of prokaryotes and other non-plant eukaryotes. AVAILABILITY: http://nypg.bio.nyu.edu/orthologid/

Algorithms↗

PubMed2005

Alaryngeal speech aid using an intra-oral electrolarynx and a miniature fingertip switch.

We developed and evaluated an intra-oral electrolaryngeal speech aid system for those who could not acquire common alaryngeal speech or for early post-surgery speech rehabilitation. Our system consisted of a denture-base intra-oral vibrator, a wireless miniature fingertip switch and a controller. To produce natural speech, the fingertip switch produced binary commands of voicing and accent and the controller implemented the pitch generation model using the commands. We first estimated the intelligibility of consonant-vowel syllables produced by our system. We then obtained the feedback about the system from the Japanese users on the basis of their daily life use, and evaluated the possibility and acceptability as an alaryngeal speech aid. Although the users were less satisfied at the intra-oral electrolarynx, the intelligibility of the intra-oral electrolarygeal speech was comparable to that of transcervical electrolaryngeal speech, and most of them were willing to employ it if they lost their current electrolaryngeal speech. According to the feedbacks from the users, a completely wire-free system and less eye-catching designs would make the prosthesis more acceptable. These results placed the intra-oral electrolarynx as a useful option of alaryngeal speech aids and encouraged the further development of the intra-oral electrolarynx.

Aged↗

PubMed2006

Continuous template collection and updating for electrogram morphology discrimination in implantable cardioverter defibrillators.

INTRODUCTION: Electrogram morphology analysis improves discrimination of supraventricular tachycardias (SVTs) from ventricular tachycardias (VTs) in implantable cardioverter defibrillators (ICDs), but electrogram morphology may change with lead maturation, drugs, or disease progression. We report the clinical performance of an automatic algorithm that creates and updates templates from non-paced, slow rhythm and continuously checks the quality of the template used for arrhythmia discrimination. METHODS AND RESULTS: We studied this algorithm in 193 patients with single-chamber ICDs (Marquis VR, Medtronic Inc., Minneapolis, MN, USA). Of the 112 patients who completed 6-month follow-up, 99.1% of the patients had > or =1 automatic template created. Match scores between template and ongoing rhythm are computed using Haar Wavelets. Of the 435 automatic templates evaluated at follow-up, 423 (97.2%) had a median match score > or =70%. Intrinsic rhythm at 1 month had significantly higher match scores (P < 0.001) with automatic templates (90.3 +/- 7.0%) than with manual templates (85.7 +/- 10.9%) generated at pre-hospital discharge (PHD). The percentage of appropriately rejected SVTs was slightly higher with the automatic template (280/339 episodes) than with the manual template at PHD (272/339 episodes) while the Wavelet detection of VT was the same (218/220 episodes). CONCLUSIONS: In patients receiving ICDs, the automatic templates were successfully created during a 6-month follow-up period, and consistently matched the patients' intrinsic rhythm at the nominal match threshold. Both early (<1 month postimplant) and late (1- to 3-month follow-up period) changes in electrogram morphology were identified, confirming the need for automatic template updating.

Algorithms↗

PubMed2005

Toward personal eHealth in cardiology. Results from the EPI-MEDICS telemedicine project.

Despite many attempts to improve the management of acute myocardial infarction, only small trends to shorter time intervals before treatment have been reported. The self-care solution developed by the European EPI-MEDICS project (2001-2004) is a novel, very affordable, easy-to-use, portable, and intelligent Personal ECG Monitor (PEM) for the early detection of cardiac ischemia and arrhythmia that is able to record a professional-quality, 3-lead electrocardiogram (ECG) based on leads I, II, and V2; derive the missing leads of the standard 12-lead ECG (thanks to either a generic or a patient-specific transform), compare each ECG with a reference ECG by means of advanced neural network-based decision-making methods taking into account the serial ECG measurements and the patient risk factors and clinical data; and generate different levels of alarms and forward the alarm messages with the recorded ECGs and the patient's Personal electronic Health Record (PHR) to the relevant health care providers by means of a standard Bluetooth-enabled, GSM/GPRS-compatible mobile phone. The ECG records are SCP-ECG encoded and stored with the PHR on a secure personal SD Card embedded in the PEM device. The alarm messages and the PHR are XML encoded. Major alarm messages are automatically transmitted to the nearest emergency call center. Medium or minor alarms are sent on demand to a central PEM Alarm Web Server. Health professionals are informed by a Short Message Service. The PEM embeds itself a Web server to facilitate the reviewing and/or update of the PHR during a routine visit at the office of the general physician or cardiologist. Eighty PEM prototypes have been finalized and tested for several weeks on 697 citizens/patients in different clinical and self-care situations involving end users (188 patients), general physicians (10), and cardiologists (9). The clinical evaluation indicates that the EPI-MEDICS concept may save lives and is very valuable for prehospitalization triage.

Allied Health Personnel↗

PubMed1998

Evolving artificial neural networks for screening features from mammograms.

Disagreement or inconsistencies in mammographic interpretation motivates utilizing computerized pattern recognition algorithms to aid the assessment of radiographic features. We have studied the potential for using artificial neural networks (ANNs) to analyze interpreted radiographic features from film screen mammograms. Attention was given to 216 cases (mammogram series) that presented suspicious characteristics. The domain expert (Wasson) quantified up to 12 radiographic features for each case based on guidelines from previous literature. Patient age was also included. The existence or absence of malignancy was confirmed in each case via open surgical biopsy (111 malignant, 105 benign). ANNs of various complexity were trained via evolutionary programming to indicate whether or not a malignancy was present given a vector of scored input features in a statistical cross validation procedure. For suspicious masses, the best evolved ANNs generated a mean area under the receiver operating characteristic curve (AZ) of 0.9196 +/- 0.0040 (1 S.E.), with a mean specificity of 0.6269 +/- 0.0272 at 0.95 sensitivity. Results when microcalcifications were included were not quite as good (AZ = 0.8464), however, ANNs with only two hidden nodes performed as well as more complex ANNs and better than ANNs with only one hidden node. The performance of the evolved ANNs was comparable to prior literature, but with an order of magnitude less complexity. The success of small ANNs in diagnosing breast cancer offers the promise that suitable explanations for the ANN's behavior can be induced, leading to a greater acceptance by physicians.

Artificial Intelligence↗

PubMed2006

Selection of generative models in classification.

This paper is concerned with the selection of a generative model for supervised classification. Classical criteria for model selection assess the fit of a model rather than its ability to produce a low classification error rate. A new criterion, the Bayesian Entropy Criterion (BEC), is proposed. This criterion takes into account the decisional purpose of a model by minimizing the integrated classification entropy. It provides an interesting alternative to the cross-validated error rate which is computationally expensive. The asymptotic behavior of the BEC criterion is presented. Numerical experiments on both simulated and real data sets show that BEC performs better than the BIC criterion to select a model minimizing the classification error rate and provides analogous performance to the cross-validated error rate.

Algorithms↗

PubMed2005

Noise-robust soft clustering of gene expression time-course data.

Clustering is an important tool in microarray data analysis. This unsupervised learning technique is commonly used to reveal structures hidden in large gene expression data sets. The vast majority of clustering algorithms applied so far produce hard partitions of the data, i.e. each gene is assigned exactly to one cluster. Hard clustering is favourable if clusters are well separated. However, this is generally not the case for microarray time-course data, where gene clusters frequently overlap. Additionally, hard clustering algorithms are often highly sensitive to noise. To overcome the limitations of hard clustering, we applied soft clustering which offers several advantages for researchers. First, it generates accessible internal cluster structures, i.e. it indicates how well corresponding clusters represent genes. This can be used for the more targeted search for regulatory elements. Second, the overall relation between clusters, and thus a global clustering structure, can be defined. Additionally, soft clustering is more noise robust and a priori pre-filtering of genes can be avoided. This prevents the exclusion of biologically relevant genes from the data analysis. Soft clustering was implemented here using the fuzzy c-means algorithm. Procedures to find optimal clustering parameters were developed. A software package for soft clustering has been developed based on the open-source statistical language R. The package called Mfuzz is freely available.

Algorithms↗

PubMed1995

Subassembly generation via mechanical conformational switches.

A question is posed on how a particular subassembly sequence is generated in randomized assembly. An extended design of mechanical conformational switches [16] is proposed that can encode several subassembly sequences. A particular subassembly sequence is generated due to conformational changes of parts during one-dimensional randomized assembly. The optimal subassembly sequence that maximizes the yield of a desired assembly can be found via genetic search over a space of parameterized conformational switch designs, rather than a space of subassembly sequences. The resulting switch design encodes the optimal subassembly sequence so that the desired assemblies are put together only in the optimal sequence. The results of genetic search and rate equation analyses reveal that the optimal subassembly sequence depends on the initial concentration of parts and the defect probabilities during randomized assembly. The results indicate that abundant parts and parts with high defect probabilities should be assembled earlier rather than later.

Algorithms↗

PubMed2002

Automated annotation of keywords for proteins related to mycoplasmataceae using machine learning techniques.

MOTIVATION: With the increase in submission of sequences to public databases, the curators of these are not able to cope with the amount of information. The motivation of this work is to generate a system for automated annotation of data we are particularly interested in, namely proteins related to the Mycoplasmataceae family. Following previous works on automatic annotation using symbolic machine learning techniques, the present work proposes a method of automatic annotation of keywords (a part of the SWISS-PROT annotation procedure), and the validation, by an expert, of the annotation rules generated. The aim of this procedure is twofold: to complete the annotation of keywords of those proteins which is far from adequate, and to produce a prototype of the validation environment, which is aimed at an expert who does not have a deep knowledge of the structure of the current databases containing the necessary information s/he needs. RESULTS: As for the first objective, a rate of correct keywords annotation of 60% is reported in the literature. Our preliminary results show that with a slightly different method, applied this method to data related to Mycoplasmataceae only, we are able to increase that rate of correct annotation.

Abstracting and Indexing↗

PubMed2006

Visualizing coevolution with CIAO plots.

In a previous article, we introduced a number of visualization techniques that we had developed for monitoring the dynamics of artificial competitive coevolutionary systems. One of these techniques involves evaluating the performance of an individual from the current population in a series of trials against opponents from all previous generations, and visualizing the results as a 2D grid of shaded cells or pixels: qualitative patterns in the shading can indicate different classes of coevolutionary dynamics. As this technique involves pitting a current individual against ancestral opponents, we referred to the visualizations as CIAO plots. Since then, a number of other authors studying the dynamics of competitive coevolutionary systems have used CIAO plots or close derivatives to help illuminate the dynamics of their systems, and it has become something of a de facto standard visualization technique. In this very brief article we summarize the rationale for CIAO plots, explain the method of constructing a CIAO plot, and review important recent results that identify significant limitations of this technique.

Artificial Intelligence↗

PubMed2001

Induction of hypotheses concerning hip arthroplasty: a modified methodology for medical research.

OBJECTIVES: The objective of this study is to advocate a methodology for medical research that, in contrast to traditional medical methodology, exploits the flexibility of machine learning and retains the kind of statistical tests that are generally accepted in the medical field for the confirmation of hypotheses. METHODS: First, the medical problem is defined and data for an observed population are collected; then a machine learning tool is used to generate hypotheses regarding the problem; finally, statistical methods are used to determine the validity of the generated hypotheses. RESULTS: To illustrate this approach, the problem of defining indications for hip arthroplasty after an acute medial femoral neck fracture is investigated as a case study. CONCLUSIONS: The methodology is similar to the usual style of applying machine learning, but insists on a link to the techniques of statistical tests that are normally used in medicine. It aims at a more flexible and economical use of experimental data than in the usual medical research, which is enabled by techniques of machine learning. At the same time, by reference to traditional statistical tests, it is hoped that this approach will lead to improved acceptance of machine learning in the medical field.

Aged↗

PubMed1995

An algorithm for complete enumeration of the mechanisms of supraventricular tachycardias that use multiple atrioventricular, AV nodal, and/or Mahaim pathways.

The EINTHOVEN system is a model-based expert system that interprets the cardiac rhythm from the electrocardiogram. It simulates the expected behavior of realistic semi-quantitative cardiac models constructed by heuristic rules to generate interpretations that include both text descriptions and event-by-event causal explanations in the form of ladder diagrams. The simulation has been limited by an inability to predict all possible behaviors of hearts with more than one reentrant circuit. We now describe an algorithm that overcomes this limitation. Its output has been validated by an independent possibility-tree analysis. Timing and storage measurements are presented for models with up to three slow atrioventricular nodal pathways, four atrioventricular pathways, and a single atriofascicular (Mahaim) pathway. This is the first report in the literature of an algorithm that enumerates all possible mechanisms for reentrant supraventricular tachycardias that use atrioventricular, atrioventricular nodal, and/or atriofascicular pathways in humans.

Algorithms↗

PubMed2005

Knowledge-based computational search for genes associated with the metabolic syndrome.

MOTIVATION: A methodology to search for genes associated with multifactorial diseases by integrating the large amount of accumulated knowledge is seriously needed. A comprehensive understanding derived from a holistic view of gene relationship structures can be gained from our proposed analysis called the cross-subspace analysis (CSA). In this analysis, gene objects are generated by machine learning using their term occurrence patterns in MEDLINE abstracts and the degree of relationship between gene objects is quantified by matching these patterns. RESULTS: Structuralization of relationships of a set of genes was performed using CSA, which were retrieved using the terms, 'obesity', 'diabetes', 'hypertriglyceridemia' and 'hypertension' that refer to diseases comprising metabolic syndrome, on a 2D plane inferring important biomedical concepts from the gene distribution. Then, we prioritized the significance of 6131 well-annotated human genes in terms of the distance on the plane from the centroid of 'metabolic syndrome'-related genes distribution. The validity was confirmed by comparing the knowledge extracted by the ordering with existing medical knowledge.

Abstracting and Indexing↗

PubMed2005

Automated generation of heuristics for biological sequence comparison.

BACKGROUND: Exhaustive methods of sequence alignment are accurate but slow, whereas heuristic approaches run quickly, but their complexity makes them more difficult to implement. We introduce bounded sparse dynamic programming (BSDP) to allow rapid approximation to exhaustive alignment. This is used within a framework whereby the alignment algorithms are described in terms of their underlying model, to allow automated development of efficient heuristic implementations which may be applied to a general set of sequence comparison problems. RESULTS: The speed and accuracy of this approach compares favourably with existing methods. Examples of its use in the context of genome annotation are given. CONCLUSIONS: This system allows rapid implementation of heuristics approximating to many complex alignment models, and has been incorporated into the freely available sequence alignment program, exonerate.

Algorithms↗

PubMed2004

Automatic segmentation and plaque characterization in atherosclerotic carotid artery MR images.

In vivo MRI provides a means to non-invasively image and assess the morphological features of atherosclerotic carotid arteries. To assess quantitatively the degree of vulnerability and the type of plaque, the contours of the lumen, outer boundary of the vessel wall and plaque components, need to be traced. Currently this is done manually, which is time-consuming and sensitive to inter- and intra-observer variability. The goal of this work was to develop an automated contour detection technique for tracing the lumen, outer boundary and plaque contours in carotid MR short-axis black-blood images. Seventeen patients with carotid atherosclerosis were imaged using high-resolution in vivo MRI, generating a total of 50 PD- and T1-weighted MR images. These images were automatically segmented using the algorithm presented in this work, which combines model-based segmentation and fuzzy clustering to detect the vessel wall, lumen and lipid core boundaries. The results demonstrate excellent correspondence between automatic and manual area measurements for lumen (r = 0.92) and outer (r = 0.91), and acceptable correspondence for fibrous cap thickness (r = 0.71). Though further optimization is required, our algorithm is a powerful tool for automatic detection of lumen and outer boundaries, and characterization of plaque in atherosclerotic vessels.

Aged↗

PubMedDate not supplied

Representation in natural and artificial agents: an embodied cognitive science perspective.

The goal of the present paper is to provide an embodied cognitive science view on representation. Using the fundamental task of category learning, we will demonstrate that this perspective enables us to shed new light on many pertinent issues and opens up new prospects for investigation. The main focus of this paper is on the prerequisites to acquire representations of objects in the real world. We suggest that the main prerequisite is embodiment which allows an agent--human, animal or robot--to manipulate its sensory input such that invariances are generated. These invariances, in turn, are the basis of representation formation. In other words, the paper does not focus on representations per se, but rather discusses the various processes involved in order to make learning and representation acquisition possible. The argument structure is as follows. First we introduce two new perspectives on representation, namely frame-of-reference, and complete agent. Then we elaborate the complete agent perspective and focus in particular on embodiment and situatedness. We argue that embodiment has two main aspects, a dynamic and an information theoretic one. Focusing on the latter, there are a number of implications: Representation can only be understood if the embedding of the neural substrate in the physical agent is known, which includes morphology (shape), positioning and nature of sensors. Because an autonomous mobile agent in the real world is exposed to a continuously changing high-dimensional stream of sensory stimulation, if it is to learn category distinctions, it first needs a focus of attention mechanism, and then it must have a way to reduce the dimensionality of this high-dimensional sensory stream. Learning is very hard because the invariances are typically not found in the sensory data directly--the classical problem of object constancy: it is a so-called type 2 problem. Rather than trying to improve the learning algorithms--which is the standard approach--the embodied cognitive science view suggests a different approach which focuses on the nature of the data: the agent is not passively exposed to a given data distribution, but, by exploiting its body and through the interaction with the environment, it can actually generate the data. More specifically, it can generate correlated data that has the property that it can be easily learned. This learnability is due to redundancies resulting from the appropriate interactions with the environment. Through such interactions, the former type 2 problem is transformed into a type 1 problem, thus reducing the complexity of the learning task by orders of magnitude. By observing the frame-of-reference problem we will discuss to what extent these invariances are reflected--represented--in the "neural substrate", i.e. the internal mechanisms of the agent. It is concluded, that representation is not a concept that can be studied in the abstract, but should be elaborated in the context of concrete agent-environment interactions. These ideas are all illustrated with examples of natural agents and artificial agents. In particular, we will present a suite of experiments on simulated and real-world artificial agents instantiating the main arguments.

Algorithms↗

PubMed2007

Mechanical design of walking machines.

The performance of existing actuators, such as electric motors, is very limited, be it power-weight ratio or energy efficiency. In this paper, we discuss the method to design a practical walking machine under this severe constraint with focus on two concepts, the gravitationally decoupled actuation (GDA) and the coupled drive. The GDA decouples the driving system against the gravitational field to suppress generation of negative power and improve energy efficiency. On the other hand, the coupled drive couples the driving system to distribute the output power equally among actuators and maximize the utilization of installed actuator power. First, we depict the GDA and coupled drive in detail. Then, we present actual machines, TITAN-III and VIII, quadruped walking machines designed on the basis of the GDA, and NINJA-I and II, quadruped wall walking machines designed on the basis of the coupled drive. Finally, we discuss walking machines that travel on three-dimensional terrain (3D terrain), which includes the ground, walls and ceiling. Then, we demonstrate with computer simulation that we can selectively leverage GDA and coupled drive by walking posture control.

Artificial Intelligence↗

PubMed2006

Dynamics of epileptic phenomena determined from statistics of ictal transitions.

In this paper, we investigate the dynamical scenarios of transitions between normal and paroxysmal state in epilepsy. We assume that some epileptic neural network are bistable i.e., they feature two operational states, ictal and interictal that co-exist. The transitions between these two states may occur according to a Poisson process, a random walk process or as a result of deterministic time-dependent mechanisms. We analyze data from animal models of absence epilepsy, human epilepsies and in vitro models. The distributions of durations of ictal and interictal epochs are fitted with a gamma distribution. On the basis of qualitative features of the fits, we identify the dynamical processes that may have generated the underlying data. The analysis showed that the following hold. 1) The dynamics of ictal epochs differ from those of interictal states. 2) Seizure initiation can be accounted for by a random walk process while seizure termination is often mediated by deterministic mechanisms. 3) In certain cases, the transitions between ictal and interictal states can be modeled by a Poisson process operating in a bistable network. These results imply that exact prediction of seizure occurrence is not possible but termination of an ictal state by appropriate counter stimulation might be feasible.

Adolescent↗