SEARCH · PubMed Health

Results for “Algorithms”

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 937 records · Page 52Linked to original sources

PubMed2005

[Which is the most appropriate diagnostic algorithm for prostate cancer screening?].

Since the use of PSA to detect prostate cancer was generalised in the late 1980's, prostate cancer diagnosis has increased considerably. Although there is now indirect evidence pointing to the beneficial effect of screening, there are no data justifying PSA screening in the general population. There is also a controversy concerning the most appropriate algorithm, should screening be performed. Therefore, our aim was to review the literature and, based on our experience, attempt to define the best algorithm for prostate cancer screening. We have made a search on Medline using the following terms: prostate biopsy, screening, algorithms, radical prostatectomy, PSA and prostate cancer. After analysing the literature, we can confirm that there is no "definitive" algorithm, due to the rapid appearance and use of new technical and biological breakthroughs, although it appears that at this time, without ceasing to include a rectal examination, more value should be given to personal risk factors, including PSA, at ages under 50, with individual monitoring based on these factors. The algorithms applied to a population have first to be validated for the population concerned.

Algorithms↗

PubMed1997

[Coronary perfusion: a classification based on the type and relative extension of coronary irrigation (II). An angiographic algorithm].

INTRODUCTION AND OBJECTIVES: An angiographic algorithm of clinical utility, applicable to conventional coronariography, is proposed to establish different patterns of coronary distribution depending on the characteristics of the myocardial perfusion, considering the starting point as the segmentary classification of the arterial irrigation of the left ventricle. METHODS: To validate this system of classification, 30 hearts coming from necropsy were studied, through anatomical and angiographical analysis. The average age of the population studied was of 69.8 +/- 14.6 years. The range was between 26 and 91 years. To study them, the hearts were unrolled and after a coronariography and a dissection of the coronary arterial tree, the identification of the perfusion mode--exclusive or shared--of every left ventricle segment was done. Then an algorithm based on the type of division of the left main branch, and on the type of perfusion of the left ventricle inferobasal segment was applied to the angiographic frames. There was statistical analysis of the data obtained in the anatomic and angiographic studies. To verify the applicability of the algorithm, it was employed to successive series of 100 coronariographies in vivo, and these were then compared to the results obtained with the necropsy series. RESULTS: The statistical comparison between the percentages of the classification obtained from both analyses of the necropsy series showed no significant differences. The statistical comparison of the percentages of the classification obtained between the in vivo and post-mortem analyses did not show any significant difference either. CONCLUSIONS: The angiographical algorithm developed allows to classify the myocardial perfusion of the left ventricle, by the conventional coronary arteriography, in three groups of clinical interest. The classification is based on the predominance of the left ventricular segments exclusively irrigated by: the anterior interventricular artery (type I), the circumflex artery (type II), or a balance between both arteries (type III). The angiographic projections in left anterior oblique with caudal angulation and right anterior oblique are important for its application. The classification of the ventricular perfusion established with the developed algorithm can be validated as being equivalent to the one obtained through the anatomical series.

Adult↗

PubMed2003

Generalized Kohonen's competitive learning algorithms for ophthalmological MR image segmentation.

Kohonen's self-organizing map is a two-layer feedforward competitive learning network. It has been used as a competitive learning clustering algorithm. In this paper, we generalize Kohonen's competitive learning (KCL) algorithm with fuzzy and fuzzy-soft types called fuzzy KCL (FKCL) and fuzzy-soft KCL (FSKCL). These generalized KCL algorithms fuse the competitive learning with soft competition and fuzzy c-means (FCM) membership functions. We then apply these generalized KCLs to MRI and MRA ophthalmological segmentations. These KCL-based MRI segmentation techniques are useful in reducing medical image noise effects using a learning mechanism. They may be particularly helpful in clinical diagnosis. Two real cases with MR image data recommended by an ophthalmologist are examined. First case is a patient with Retinoblastoma in her left eye, an inborn malignant neoplasm of the retina frequently metastasis beyond the lacrimal cribrosa. The second case is a patient with complete left side oculomotor palsy immediately after a motor vehicle accident. Her brain MRI with MRA, skull routine, orbital CT, and cerebral angiography did not reveal brainstem lesions, skull fractures, or vascular anomalies. These generalized KCL algorithms were used in segmenting the ophthalmological MRIs. KCL, FKCL and FSKCL comparisons are made. Overall, the FSKCL algorithm is recommended for use in MR image segmentation as an aid to small lesion diagnosis.

Algorithms↗

PubMed2003

A new pacemaker algorithm for the treatment of atrial fibrillation: results of the Atrial Dynamic Overdrive Pacing Trial (ADOPT).

OBJECTIVES: The Atrial Dynamic Overdrive Pacing Trial (ADOPT) was a single blind, randomized, controlled study to evaluate the efficacy and safety of the atrial fibrillation (AF) Suppression Algorithm (St. Jude Medical Cardiac Rhythm Management Division, Sylmar, California) in patients with sick sinus syndrome and AF. BACKGROUND: This algorithm increases the pacing rate when the native rhythm emerges and periodically reduces the rate to search for intrinsic atrial activity. METHODS: Symptomatic AF burden (percentage of days during which symptomatic AF occurred) was the primary end point. Patients underwent pacemaker implantation, were randomized to DDDR with the algorithm on (treatment) or off (control), and were followed for six months. RESULTS: Baseline characteristics and antiarrhythmic drugs used were similar in both groups. The percentage of atrial pacing was higher in the treatment group (92.9% vs. 67.9%, p < 0.0001). The AF Suppression Algorithm reduced symptomatic AF burden by 25% (2.50% control vs. 1.87% treatment). Atrial fibrillation burden decreased progressively in both groups but was lower in the treatment group at each follow-up visit (one, three, and six months) (p = 0.005). Quality of life scores improved in both groups. The mean number of AF episodes (4.3 +/- 11.5 control vs. 3.2 +/- 8.6 treatment); total hospitalizations (17 control vs. 15 treatment); and incidence of complications, adverse events, and deaths were not statistically different between groups. CONCLUSIONS: The ADOPT demonstrated that overdrive atrial pacing with the AF Suppression Algorithm decreased symptomatic AF burden significantly in patients with sick sinus syndrome and AF. The decrease in relative AF burden was substantial (25%), although the absolute difference was small (2.50% control vs. 1.87% treatment).

Aged↗

PubMed1997

A new electrocardiographic algorithm using retrograde P waves for differentiating atrioventricular node reentrant tachycardia from atrioventricular reciprocating tachycardia mediated by concealed accessory pathway.

OBJECTIVES: The purpose of this study was to use an electrocardiographic (ECG) algorithm, derived from the results of radiofrequency ablation, to discriminate atrioventricular node reentrant tachycardia (AVNRT) from atrioventricular reciprocating tachycardia (AVRT) and to localize a concealed accessory pathway, prospectively. BACKGROUND: Information about ECG criteria for differentiating AVNRT from AVRT is limited and has not been confirmed by surgical or catheter ablation. METHODS: Four hundred six ECGs (obtained from 406 different patients) that demonstrated narrow QRS complex (< 0.12 s) supraventricular tachycardia with an RP' interval less than the P'R interval or pseudo r' wave in lead V1 or pseudo S wave in inferior leads, or both, were examined, and the results were confirmed by radiofrequency catheter ablation. The initial 226 ECGs were analyzed to develop a stepwise algorithm, and the subsequent 180 ECGs were prospectively evaluated by the new algorithm. RESULTS: The presence of a pseudo r' wave in lead V1 or a pseudo S wave in leads II, III, aVF indicated anterior-type AVNRT with an accuracy of 100%. With the difference of RP' intervals in leads V1 and III > 20 ms, posterior-type AVNRT could be differentiated from AVRT utilizing a posteroseptal pathway with a sensitivity of 71% (95% confidence interval [CI] 55% to 89%), a specificity of 87% (95% CI 67% to 97%) and a positive predictive value of 75% (95% CI 56% to 91%). According to the polarity of retrograde P waves in leads V1, II, III, aVF and I during AVRT, the concealed accessory pathway could be localized to one of the nine regions on the atrioventricular annuli with an accuracy of 75% (for a right midseptal pathway) to 93.8% (for a left posterior pathway). Overall, the new algorithm had an accuracy of 97.8% in discriminating AVNRT from AVRT and 88.1% in localizing a concealed accessory pathway, prospectively. Prediction was incorrect in only 15 patients (9.1%). CONCLUSIONS: The new ECG algorithm derived from the analysis of retrograde P waves during tachycardia could provide a criterion for differential diagnosis between AVNRT and AVRT and for predicting the location of concealed accessory pathways.

Adolescent↗

PubMedDate not supplied

An efficient learning algorithm for improving generalization performance of radial basis function neural networks.

This paper presents an efficient recursive learning algorithm for improving generalization performance of radial basis function (RBF) neural networks. The approach combines the rival penalized competitive learning (PRCL) [Xu, L., Kizyzak, A. & Oja, E. (1993). Rival penalized competitive learning for clustering analysis, RBF net and curve detection, IEEE Transactions on Neural Networks, 4, 636-649] and the regularized least squares (RLS) to provide an efficient and powerful procedure for constructing a minimal RBF network that generalizes very well. The RPCL selects the number of hidden units of network and adjusts centers, while the RLS constructs the parsimonious network and estimates the connection weights. In the RLS we derived a simple recursive algorithm, which needs no matrix calculation, and so largely reduces the computational cost. This combined algorithm significantly enhances the generalization performance and the real-time capability of the RBF networks. Simulation results of three different problems demonstrate much better generalization performance of the present algorithm over other existing similar algorithms.

Algorithms↗

PubMed2000

Approximating a solution of the s-t max-cut problem with a deterministic annealing algorithm.

The s-t max-cut problem is an NP-hard combinatorial optimization problem. In this paper an equivalent linearly constrained continuous optimization problem is formulated and an algorithm is proposed for approximating its solution. The algorithm is derived from an application of a logarithmic barrier function, where the barrier parameter behaves as temperature in an annealing procedure and decreases to zero from a sufficiently large positive number satisfying that the barrier function is convex. The algorithm searches for a better solution in a feasible descent direction, which has a desired property that lower and upper bounds are always satisfied automatically if the step length is a number between zero and one. We prove that the algorithm converges to at least a local minimum point if a local minimum point of the barrier problem is generated for a sequence of descending values of the barrier parameter with zero limit. Numerical results show that the algorithm seems effective and efficient.

Algorithms↗

PubMed2001

A real-coded genetic algorithm for training recurrent neural networks.

The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. Training algorithms for Recurrent Neural Networks, based on the error gradient, are very unstable in their search for a minimum and require much computational time when the number of neurons is high. The problems surrounding the application of these methods have driven us to develop new training tools. In this paper, we present a Real-Coded Genetic Algorithm that uses the appropriate operators for this encoding type to train Recurrent Neural Networks. We describe the algorithm and we also experimentally compare our Genetic Algorithm with the Real-Time Recurrent Learning algorithm to perform the fuzzy grammatical inference.

Algorithms↗

PubMed2001

A new algorithm to design compact two-hidden-layer artificial neural networks.

This paper describes the cascade neural network design algorithm (CNNDA), a new algorithm for designing compact, two-hidden-layer artificial neural networks (ANNs). This algorithm determines an ANN's architecture with connection weights automatically. The design strategy used in the CNNDA was intended to optimize both the generalization ability and the training time of ANNs. In order to improve the generalization ability, the CNDDA uses a combination of constructive and pruning algorithms and bounded fan-ins of the hidden nodes. A new training approach, by which the input weights of a hidden node are temporarily frozen when its output does not change much after a few successive training cycles, was used in the CNNDA for reducing the computational cost and the training time. The CNNDA was tested on several benchmarks including the cancer, diabetes and character-recognition problems in ANNs. The experimental results show that the CNNDA can produce compact ANNs with good generalization ability and short training time in comparison with other algorithms.

Algorithms↗

PubMedDate not supplied

Stochastic error whitening algorithm for linear filter estimation with noisy data.

Mean squared error (MSE) has been the most widely used tool to solve the linear filter estimation or system identification problem. However, MSE gives biased results when the input signals are noisy. This paper presents a novel stochastic gradient algorithm based on the recently proposed error whitening criterion (EWC) to tackle the problem of linear filter estimation in the presence of additive white disturbances. We will briefly motivate the theory behind the new criterion and derive an online stochastic gradient algorithm. Convergence proof of the stochastic gradient algorithm is derived making mild assumptions. Further, we will propose some extensions to the stochastic gradient algorithm to ensure faster, step-size independent convergence. We will perform extensive simulations and compare the results with MSE as well as total-least squares in a parameter estimation problem. The stochastic EWC algorithm has many potential applications. We will use this in designing robust inverse controllers with noisy data.

Algorithms↗

PubMedDate not supplied

A second-generation computer-based edge detection algorithm for short-axis, two-dimensional echocardiographic images: accuracy and improvement in interobserver variability.

The present study tested the hypothesis that a second-generation endocardial edge detection algorithm that used a priori endocardial and epicardial information would improve accuracy and reduce the variability of border definition. Five nonexpert observers utilized the version 2 algorithm on 20 cycles of two-dimensional short-axis images (five excellent, seven good, and eight poor quality studies stored digitally from a previously reported project). Manually defined areas by five recognized experts on these 20 cardiac cycles were considered to be "true areas." Areas defined by the experts with version 1 of the algorithm were also used for comparison. Regression of the version 2 areas with mean, manually defined excellent quality areas yielded a similar correlation (r = 0.985) to that reported between the manual and the version 1 areas (r = 0.986). For all 20 cycles in the series, however, the correlation between version 2 and the manually defined areas was lower (r = 0.952) than that of the same correlation with version 1 areas (r = 0.980). For all studies the interobserver variability (percent area difference) was +/- 14.4% for manually defined borders, +/- 11.1% for version 1-defined borders, and +/- 7.7% for version 2-defined borders. No difference in variability was observed for excellent quality studies (+/- 5.3% versus 5.2%) between version 1 and version 2 areas. However, the version 2 algorithm significantly reduced interobserver variability for good and poor quality studies (+/- 8.4% to 7.6%, p less than 0.025, and 16.3% to 9.1%, p less than 0.05, respectively). We concluded that: the version 2 algorithm provided accuracy and significantly reduced the variability of area measurement in good and poor quality studies and that epicardial information was important to the improvement by providing wall thickness information to assist in filling areas of dropout and avoidance of intracavitary structures.

Algorithms↗

PubMedDate not supplied

Marching cube algorithm: review and trilinear interpolation adaptation for image-based dosimetric models.

Current internal organ dose assessment methodologies utilize three-dimensional (3D) medical images of the body to model organ shapes and tissue interfaces. These models are coupled to computer programs that measure radionuclide energy deposition or chord-length distributions directly within these images. Previous studies have shown that the rectangular shape of image voxels generates voxel effects that alter the outcome of these calculations. To minimize voxel effects, the present study proposes to use the Marching Cube (MC) algorithm to generate isosurfaces delineating tissue interfaces from the gray-level images. First, a review of the different techniques surrounding the MC algorithm is presented. Next, an adaptation of the algorithm is proposed in which a trilinear interpolation of the gray levels is used to generate a hyperboloid surface within the MCs. This new technique is shown to solve the classic ambiguity problem of the MC algorithm and also to reduce the data size inherent to the triangulated surface. It also provides a simple algorithm to accurately measure distances within the image. The technique is then tested with a mathematical model of trabecular bone. The trilinear interpolation method is shown to remove voxel effects and to produce reliable chord-length distributions across image regions. The technique is thus recommended for use with digital medical images needed for internal radiation transport simulations. The current study is performed for a single isosurface that separates two media within the same image, but it is proposed that the technique can be extended to multiple isosurfaces that delineate several organs or organ regions within 3D tomographic voxels of human anatomy.

Algorithms↗

PubMed2000

The international classification of the epilepsies and epileptic syndromes. An algorithm for its use in clinical practice.

An algorithm has been structured as a guided reading of the international league against epilepsy (ILAE) syndromic classification to be used in clinical practice by less experienced physicians in newly diagnosed patients. The algorithm followed the original structure of the classification, which identifies major syndromic groups, subgroups, and specific syndromes. Validation required two raters, a resident and a board-certified neurologist, to apply the algorithm with different techniques (direct or recorded interview, medical record consultation) to 19 children and 18 adults with epilepsy with information available at the time of diagnosis. The two raters' diagnoses were compared with those of the caring physicians, and cases where disagreement arose were discussed in conference to achieve consensus. The kappa statistic was used as a measure of inter-rater agreement. Caring physicians and both raters agreed in 51% of cases. Substantial agreement (kappa = 0.75) was obtained between the resident and the neurologist on major diagnostic groups and subgroups, mostly in adults. Agreement with the caring physician was slightly more satisfactory for the resident (kappa=0.67) than for the neurologist (kappa = 0.60). Agreement was better with direct or indirect interview than with record consultation, and improved further after discussion. Agreement was obtained after discussion in 32% of cases, in some of which the caring physician agreed on the resident's diagnosis. Agreement was less satisfactory for specific syndromes. On this basis, an algorithm of the ILAE classification is a fairly reliable instrument only for making a broad syndromic classification of epilepsy at the time of diagnosis. The limits of the algorithm tend mostly to reflect the intrinsic limitations of the classification itself.

Adolescent↗

PubMed1998

A data dependent computer algorithm for the detection of muscle activity onset and offset from EMG recordings.

This paper describes modifications to an algorithm presented by Marple-Horvat and Gilbey (1992) for identifying bursts of muscle activity in electromyographical (EMG) recordings. Our efforts to apply their algorithm to spontaneously moving infants and toddlers resulted in limited success. The modified algorithm makes several parameters dependent on the data being analyzed; these changes enabled it to analyze a variety of EMG recordings more effectively. The original algorithm had a success rate (correctly identified bursts) of 62.9% and combined error rate (number of insertions and deletions) of 73.0% when applied to an independent test data set. The modified algorithm displayed a success rate of 85.4% and combined error rate of 23.6%.

Adult↗

PubMed2002

Comparison of pulmonary arterial thermodilution and arterial pulse contour analysis: evaluation of a new algorithm.

STUDY OBJECTIVE: To compare cardiac index (CI) measurement by arterial pulse contour analysis using two different algorithms (CI(PC), CI(PCnew)) with pulmonary arterial thermodilution values (CI(PA)) so as to evaluate the difference between the conventional algorithm, CI(PC), and a new algorithm, CI(PCnew), that accounts for patients' individual aortic compliance. DESIGN: Prospective, clinical study. SETTING: Intensive care unit of a university hospital. PATIENTS: 20 ASA physical status II and III patients following elective cardiac surgery. MEASUREMENTS AND MAIN RESULTS: 360 parallel triplicate determinations of CI (CI(PA), CI(PC), CI(PCnew)) were performed within a 90-minute period during the immediate postoperative period. Prior to the start of the study period, CI(PC) as well as CI(PCnew) were calibrated by triplicate femoral arterial thermodilution measurements. Regression analysis of CI(PA) and CI(PC), as well as CI(PA) and CI(PCnew), revealed r = 0.89, p < 0.001, and r = 0.93, p < 0.001, respectively. Bland-Altman analysis was used for determining the accuracy and precision of CI(PC) and CI(PCnew) compared with CI(PA). The mean differences (m) and standard deviation (SD) between CI(PA) and CI(PC,) as well as CI(PA) and CI(PCnew), resulted in m = -0.312 L/min/m(2), SD = 0.456 L/min/m(2), and m = - 0.140 L/min/m(2), SD = 0.328 L/min/m(2), respectively. CONCLUSION: Arterial pulse contour analysis measurement of CI using either algorithm correlates well with CI values derived by pulmonary arterial thermodilution. However, the algorithm introduced in this study proved to be a more accurate predictor of values as derived by pulmonary artery catheter.

Algorithms↗

PubMed2001

On the extended depth of focus algorithms for bright field microscopy.

Microscopes offer a limited depth of focus which precludes the observation of a complete image of a three-dimensional (3D) object in a single view. Investigations, by a variety of researchers, have led to the development of extended depth of focus algorithms for serial optical slices of microscopic 3D objects in recent years. However, to date, no quantitative comparison of the different algorithms has been performed, generally leaving the evaluation to the subjective qualitative appreciation of the observer. In this paper we use three different tests for extended depth of focus algorithm evaluation and test 10 different algorithms, some of them have been adapted (by us) for a series of optical slices. However, the main contribution of the paper is a new improved algorithm for computing the extended depth of focus.

Algorithms↗

PubMed2001

Evaluation of intra-muscular EMG signal decomposition algorithms.

We propose and test a tool to evaluate and compare EMG signal decomposition algorithms. A model for the generation of synthetic intra-muscular EMG signals, previously described, has been used to obtain reference decomposition results. In order to evaluate the performance of decomposition algorithms it is necessary to define indexes which give a compact but complete indication about the quality of the decomposition. The indexes given by traditional detection theory are in this paper adapted to the multi-class EMG problem. Moreover, indexes related to model parameters are also introduced. It is possible in this way to compare the sensitivity of an algorithm to different signal features. An example application of the technique is presented by comparing the results obtained from a set of synthetic signals decomposed by expert operators having no information about the signal features using two different algorithms. The technique seems to be appropriate for evaluating decomposition performance and constitutes a useful tool for EMG signal researchers to identify the algorithm most appropriate for their needs.

Action Potentials↗

PubMed2000

Fast algorithm for soft straightening of the colon.

RATIONALE AND OBJECTIVES: In this study, the authors developed a fast algorithm for soft straightening of the colon with computed tomographic data that greatly accelerates the unraveling process based on the interpolation of representative electric force lines. MATERIALS AND METHODS: Each curved cross section of the colon is defined by electric force lines of a common origin on an electrically charged central path and is constructed by interpolating most of these force lines from a limited number of representative force lines that are traced directly. Both a synthetic colon phantom and a colon in a living patient were used to demonstrate the feasibility of the fast interpolation algorithm compared with direct implementation for soft straightening of the colon. RESULTS: The interpolation-based soft-straightening algorithm ran approximately 40 times faster than the direct implementation of the electric field-based soft-straightening algorithm. CONCLUSION: The fast algorithm for soft straightening of the colon has potential for use in computed tomographic colonography.

Algorithms↗