SEARCH · PubMed Health

Results for “Classification 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 1,315 records · Page 73Linked to original sources

PubMed2005

Interpreting procedures from descriptive guidelines.

Errors in clinical practice guidelines may translate into errors in real-world clinical practice. The best way to eliminate these errors is to understand how they are generated, thus enabling the future development of methods to catch errors made in creating the guideline before publication. We examined the process by which a medical expert from the American College of Physicians (ACP) created clinical algorithms from narrative guidelines, as a case study. We studied this process by looking at intermediate versions produced during the algorithm creation. We identified and analyzed errors that were generated at each stage, categorized them using Knuth's classification scheme, and studied patterns of errors that were made over the set of algorithm versions that were created. We then assessed possible explanations for the sources of these errors and provided recommendations for reducing the number of errors, based on cognitive theory and on experience drawn from software engineering methodologies.

Artificial Intelligence↗

PubMed2006

Algorithm for automatic genotype calling of single nucleotide polymorphisms using the full course of TaqMan real-time data.

Single nucleotide polymorphisms (SNPs) are often determined using TaqMan real-time PCR assays (Applied Biosystems) and commercial software that assigns genotypes based on reporter probe signals at the end of amplification. Limitations to the large-scale application of this approach include the need for positive controls or operator intervention to set signal thresholds when one allele is rare. In the interest of optimizing real-time PCR genotyping, we developed an algorithm for automatic genotype calling based on the full course of real-time PCR data. Best cycle genotyping algorithm (BCGA), written in the open source language R, is based on the assumptions that classification depends on the time (cycle) of amplification and that it is possible to identify a best discriminating cycle for each SNP assay. The algorithm is unique in that it classifies samples according to the behavior of blanks (no DNA samples), which cluster with heterozygous samples. This method of classification eliminates the need for positive controls and permits accurate genotyping even in the absence of a genotype class, for example when one allele is rare. Here, we describe the algorithm and test its validity, compared to the standard end-point method and to DNA sequencing.

Algorithms↗

PubMed2005

Extensively cystic renal neoplasms in adults (Bosniak classification II or III)--possible "common" histological diagnoses: multilocular cystic renal cell carcinoma, cystic nephroma, and mixed epithelial and stromal tumor of the kidney.

OBJECTIVE(S): To give an algorithm for resolution of extensively cystic renal neoplasms, preoperatively classified in the Bosniak classification as a category II and III. METHODS: From 1991 to 6/2004, 701 patients with 727 renal tumours were surgically treated at our hospital. Extensively cystic tumours were found in 10 cases. Extensively cystic tumours were defined as multicystic tumours without any solid nodules visible neither on CT, nor grossly in the specimen at operation (the Bosniak classification type II or III). RESULTS: Seven multilocular cystic renal cell carcinomas, three mixed epithelial and stromal tumour of the kidney and one cystic nephroma were diagnosed on histology. CONCLUSION(S): Extensively cystic renal tumours classified as the Bosniak type II or III correspond histologically to the entities mentioned above (multilocular cystic renal cell carcinoma, cystic nephroma, mixed epithelial and stromal tumour of the kidney). These entities cannot be distinguished one from another on preoperative imaging studies. A preoperative biopsy and intra-operative frozen-section analysis do not lead to a correct diagnosis in many cases. Fortunately, the operative strategy is the same for all these tumours. In such cases, the nephron sparing surgery is indicated, whenever technically feasible, as almost all extensively cystic renal tumours have a good prognosis.

Adult↗

PubMed1989

Algorithmic sequential decision-making in the frequency domain for life threatening ventricular arrhythmias and imitative artefacts: a diagnostic system.

A preliminary study to approach the problem of reliably detecting life threatening ventricular arrhythmias in real time is described. An algorithm (DIAGNOSIS) has been developed in order to classify ECG signal records on the basis of the computation of four simple parameters calculated from a representation in the frequency domain. This algorithm uses a set of rules constituting an operative classification scheme based on the comparison of the parameters with a set of pre-established thresholds. This allows us to differentiate four general categories: ventricular fibrillation-flutter, ventricular rhythms, imitative artefacts and predominant sinus rhythm.

Algorithms↗

PubMedDate not supplied

[Mathematical modelling and the prognosis of treatment efficacy in papillomavirus infection of the cervix uteri].

In this paper, consideration is given to the problem of mathematical modelling, diagnosis and effects of treatment options on the condition of a patient exposed to papillomavirus infection. The problem is tackled of identifying the most prominent signs of degree of severity of the disease course and of therapy efficiency on the basis of parameters characterizing the immunologic vigor with making use of the covariation matrix eigenvalues algorithm, namely the modelling manifolds algorithm. Such an approach allows the central problem of classification of indices for the immunologic vigor to be settled. A mathematical model as discrimination surface to be used for prediction of results of the treatments administered is constructed.

Algorithms↗

PubMed2004

Adaptive BCI based on variational Bayesian Kalman filtering: an empirical evaluation.

This paper proposes the use of variational Kalman filtering as an inference technique for adaptive classification in a brain computer interface (BCI). The proposed algorithm translates electroencephalogram segments adaptively into probabilities of cognitive states. It, thus, allows for nonstationarities in the joint process over cognitive state and generated EEG which may occur during a consecutive number of trials. Nonstationarities may have technical reasons (e.g., changes in impedance between scalp and electrodes) or be caused by learning effects in subjects. We compare the performance of the proposed method against an equivalent static classifier by estimating the generalization accuracy and the bit rate of the BCI. Using data from two studies with healthy subjects, we conclude that adaptive classification significantly improves BCI performance. Averaging over all subjects that participated in the respective study, we obtain, depending on the cognitive task pairing, an increase both in generalization accuracy and bit rate of up to 8%. We may, thus, conclude that adaptive inference can play a significant contribution in the quest of increasing bit rates and robustness of current BCI technology. This is especially true since the proposed algorithm can be applied in real time.

Algorithms↗

PubMed2001

A proposed taxonomy for nailfold capillaries based on their morphology.

Certain diseases cause permanent changes to the shapes and densities of nailfold capillaries and, therefore, nailfold capillaroscopy is important as a tool for diagnosing and monitoring these diseases. The first aim of the project is to resolve differences in terminology that have developed over the years in previous work. We propose a taxonomy for nailfold capillaries that cover six descriptive classes: cuticulis, open, tortuous, crossed, bushy, and bizarre. The first three are parametric in that they may be distinguished by the ratio of capillary length to width and by the curvature of the capillary limbs. The last three are characterized by their topology; a crossed capillary has a closed area that is not connected to the image background. Bushy and bizarre capillaries have atypical shapes that are characterized by the convex hull of their skeleton. These descriptive classes may be modified according to anomalies in width and length. The second aim is to automate the classification of capillaries by encapsulating the taxonomy in an algorithm; our computer program rivals the most experienced clinicians in classifying capillaries consistently with an overall agreement of 85% with the clinicians' majority view. This was particularly valuable in classifying borderline shapes objectively and consistently.

Capillaries↗

PubMed2005

Correlation between MR imaging-derived nasopharyngeal carcinoma tumor volume and TNM system.

PURPOSE: To measure nasopharyngeal carcinoma tumor volume based on magnetic resonance images using a validated semiautomated measurement methodology and correlate tumor volume with TNM T classification. METHODS AND MATERIALS: The study population consisted of 206 consecutive nasopharyngeal carcinoma patients who had magnetic resonance imaging staging scans. Tumor volume was measured using a semisupervised knowledge-based fuzzy clustering algorithm. Patients were divided into 4 groups according to TNM T classification. The difference in tumor volumes among the various TNM T-classification groups was examined. RESULTS: The mean tumor volume in each T-classification group is as follows: T1, 8.6 mL +/- 5.0 (standard deviation [SD]); T2, 18.1 mL +/- 8.1 (SD); T3, 25.8 mL +/- 14.1 (SD); and T4, 36.2 mL +/- 18.9 (SD). The mean tumor volume increased significantly with advancing T classification (p < 0.0001). Tumor volume in a more advanced T group was significantly larger than that in an adjacent early T group (p < 0.01). CONCLUSION: Validated magnetic resonance imaging-based tumor volume shows positive correlation between tumor volume and advancing T-classification groups. It may be possible to incorporate tumor volume as an additional prognostic factor into the existing TNM system.

Adolescent↗

PubMed2006

Airway disease in highway and tunnel construction workers exposed to silica.

BACKGROUND: Construction workers employed in a unique type of tunnel construction known as tunnel jacking were exposed over an 18-month period to respirable crystalline silica at concentrations that exceeded the OSHA permissible exposure limit. The present study examines workplace exposures and occurrence of airway disease in these workers. METHODS: Medical and occupational histories and chest radiographs were obtained on 343 active construction workers who had worked on the site during the period in question. Chest radiographs were interpreted according to the ILO-1980 system of classification. Standardized questions were used to develop an algorithm to define symptoms consistent with asthma (SCA) and to determine these respiratory outcomes: chronic bronchitis, shortness of breath (SOB), and physician-diagnosed asthma (current vs. not current). Relationships with each of three work activities were examined: slurry wall breakthrough (SWB), chipping caisson overpour, and tunneling/mining. RESULTS: Participants included laborers, carpenters, tunnel workers, ironworkers, operating engineers, and electricians. No cases of silicosis were found on chest X-ray. Overall prevalence of chronic bronchitis, SCA, SOB, and physician-diagnosed asthma was 10.7%, 25%, 29%, and 6.6%, respectively. Odds ratios (OR) for carpenters compared to laborers were significantly elevated for chronic bronchitis, SCA, and SOB. SWB was associated with chronic bronchitis and SCA (OR 4.93, 95% CI = 1.01, 24.17; OR 3.32, 95% CI = 1.25, 8.84, respectively). The interaction between SWB, SCA, and trade was significant for carpenters (OR 6.87, 95% CI = 1.66, 28.39). Inverse trends were observed for months on the site and chronic bronchitis, SCA, and SOB (P = 0.0374, 0.0006, and 0.0307, respectively). CONCLUSIONS: Tunnel construction workers exposed to respirable crystalline silica and cement dust are at increased risk for airway disease. Extent of risk varies by trade and work activity. Our data indicate the importance of bystander exposures and suggest that tunnel jacking may be associated with greater risk compared to more traditional methods of tunnel construction. A healthy worker effect is suggested.

Adult↗

PubMed1994

Automated peak detection and cell cycle analysis of flow cytometric DNA histograms.

We describe an algorithm for fully automated flow cytometric DNA histogram classification and analysis that provides rapid, reproducible determination of DNA index and S-phase fraction (SPF). Automated classification agreed with subjective assessment of DNA ploidy in 96-98% of DNA histograms. Automated and conventional analyses of DNA index (r = 0.95) and SPF (r = 0.89) were also highly correlated with one another. In a series of 86 node-negative breast carcinomas, SPF calculated with the fully automated method was a significant predictor of 10 year survival (p = 0.009). Automation greatly increased the speed of DNA histogram analysis, allowing evaluation of the same set of histograms with different methods. In a preliminary study exploring the optimization of DNA histogram analysis, the best association between SPF and prognosis of breast cancer patients was achieved using sliced nuclei debris modeling, reporting only the aneuploid SPF (in aneuploid histograms), while excluding small aneuploid clones (< 15% of total cell count) from evaluation. In conclusion, automated DNA histogram analysis does not replace the need for close human supervision but provides a useful guideline for less experienced users, facilitates interlaboratory comparisons, and makes possible extensive reanalyses of large data sets.

Breast Neoplasms↗

PubMed2004

Methods for detecting functional classifications in neuroimaging data.

Data-driven statistical methods are useful for examining the spatial organization of human brain function. Cluster analysis is one approach that aims to identify spatial classifications of temporal brain activity profiles. Numerous clustering algorithms are available, and no one method is optimal for all areas of application because an algorithm's performance depends on specific characteristics of the data. K-means and fuzzy clustering are popular for neuroimaging analyses, and select hierarchical procedures also appear in the literature. It is unclear which clustering methods perform best for neuroimaging data. We conduct a simulation study, based on PET neuroimaging data, to evaluate the performances of several clustering algorithms, including a new procedure that builds on the kth nearest neighbor method. We also examine three stopping rules that assist in determining the optimal number of clusters. Five hierarchical clustering algorithms perform best in our study, some of which are new to neuroimaging analyses, with Ward's and the beta-flexible methods exhibiting the strongest performances. Furthermore, Ward's and the beta-flexible methods yield the best performances for noisy data, and the popular K-means and fuzzy clustering procedures also perform reasonably well. The stopping rules also exhibit good performances for the top five clustering algorithms, and the pseudo-T2 and pseudo-F stopping rules are superior for noisy data. Based on our simulations for both noisy and unscaled PET neuroimaging data, we recommend the combined use of the pseudo-F or pseudo-T2 stopping rule along with either Ward's or the beta-flexible clustering algorithm.

Algorithms↗

PubMed2005

Diagnosis of cerebral cryptococcoma using a computerized analysis of 1H NMR spectra in an animal model.

Viable cryptococci load in biopsy material from an animal model of cerebral cryptococcoma were correlated with 1H NMR spectra and metabolite profiles. A statistical classification strategy was applied to distinguish among high-resolution 1H NMR spectra acquired from cryptococcomas, glioblastomas, and normal brain tissue. The overall classification accuracy was 100% when a genetic-algorithm-based optimal region selection preceded the development of linear discriminant analysis-based classifiers. The method remained robust despite differences in the microbial load of the cryptococcoma group when harvested at different time points. These results indicate the feasibility of the method for diagnosis without isolation of the pathogenic microorganism and its potential for in vivo diagnosis based on computerized analysis of magnetic resonance spectra.

Algorithms↗

PubMedDate not supplied

Individualization of pharmacological anemia management using reinforcement learning.

Effective management of anemia due to renal failure poses many challenges to physicians. Individual response to treatment varies across patient populations and, due to the prolonged character of the therapy, changes over time. In this work, a Reinforcement Learning-based approach is proposed as an alternative method for individualization of drug administration in the treatment of renal anemia. Q-learning, an off-policy approximate dynamic programming method, is applied to determine the proper dosing strategy in real time. Simulations compare the proposed methodology with the currently used dosing protocol. Presented results illustrate the ability of the proposed method to achieve the therapeutic goal for individuals with different response characteristics and its potential to become an alternative to currently used techniques.

Algorithms↗

PubMedDate not supplied

Improved system for object detection and star/galaxy classification via local subspace analysis.

The two traditional tasks of object detection and star/galaxy classification in astronomy can be automated by neural networks because the nature of the problems is that of pattern recognition. A typical existing system can be further improved by using one of the local Principal Component Analysis (PCA) models. Our analysis in the context of object detection and star/galaxy classification reveals that local PCA is not only superior to global PCA in feature extraction, but is also superior to gaussian mixture in clustering analysis. Unlike global PCA which performs PCA for the whole data set, local PCA applies PCA individually to each cluster of data. As a result, local PCA often outperforms global PCA for data of multi-modes. Moreover, since local PCA can effectively avoid the trouble of having to specify a large number of free elements of each covariance matrix of gaussian mixture, it can give a better description of local subspace structures of each cluster when applied on high dimensional data with small sample size. In this paper, the local PCA model proposed by Xu [IEEE Trans. Neural Networks 12 (2001) 822] under the general framework of Bayesian Ying Yang (BYY) normalization learning will be adopted. Endowed with the automatic model selection ability of BYY learning, the BYY normalization learning-based local PCA model can cope with those object detection and star/galaxy classification tasks with unknown model complexity. A detailed algorithm for implementation of the local PCA model will be proposed, and experimental results using both synthetic and real astronomical data will be demonstrated.

Astronomy↗

PubMedDate not supplied

Quantitative self-organizing maps for clustering electron tomograms.

Tomography emerges as a powerful methodology for determining the complex architectures of biological specimens that are better regarded from the structural point of view as singular entities. However, once the structure of a sufficiently large number of singular specimens is solved, quite possibly structural patterns start to emerge. This latter situation is addressed here, where the clustering of a set of 3D reconstructions using a novel quantitative approach is presented. In general terms, we propose a new variant of a self-organizing neural network for the unsupervised classification of 3D reconstructions. The novelty of the algorithm lies in its rigorous mathematical formulation that, starting from a large set of noisy input data, finds a set of "representative" items, organized onto an ordered output map, such that the probability density of this set of representative items resembles at its possible best the probability density of the input data. In this study, we evaluate the feasibility of application of the proposed neural approach to the problem of identifying similar 3D motifs within tomograms of insect flight muscle. Our experimental results prove that this technique is suitable for this type of problem, providing the electron microscopy community with a new tool for exploring large sets of tomogram data to find complex patterns.

Algorithms↗

PubMed1997

Fractal texture analysis in computer-aided diagnosis of solitary pulmonary nodules.

RATIONALE AND OBJECTIVES: The authors investigated the use of fractal texture characterization to improve the accuracy of solitary pulmonary nodule computer-aided diagnosis (CAD) systems. METHODS: Thirty chest radiographs were acquired from patients who had no pulmonary nodules. Thirty regions were selected that were considered remotely suspicious-looking for nodules. Artificial nodules of multiple shapes, sizes, and orientations were added at subtle levels of contrast to 30 non-suspicious-looking regions of the radiographs. Fractal dimensions of the 60 "nodule candidates" were calculated to quantify the texture of each region. Four radiologists also interpreted the images. RESULTS: The fractal dimension of each possible nodule provided statistically significant (P < .05) differentiation between regions that contained an artificial nodule and those that did not. The area under the receiver operating characteristic curve for the fractal analysis was significantly better (P < .05) than that for the radiologists. CONCLUSION: Fractal texture characterization provides useful information for the classification of potential solitary pulmonary nodules with CAD algorithms.

Diagnosis, Computer-Assisted↗

PubMed2007

Taxonicity of nonverbal learning disabilities in spina bifida.

As currently defined, it is not clear whether Nonverbal Learning Disabilities (NLD) should be considered a matter of kind or magnitude (Meehl, 1995). The taxonicity of NLD, or the degree to which it is best construed as discrete versus continuous, has not been investigated using methods devised for this purpose. Latent Class Analysis (LCA) is a method for finding subtypes of latent classes from multivariate categorical data. This study represents an application of LCA on a sample of children and adolescents with spina bifida myelomeningocele (SBM) (N = 44), those presenting with features of NLD (N = 28) but no medical condition, and control volunteers (N = 44). The two-class solution provided evidence for the presence of a taxon with an estimated base-rate in the SBM group of .57. Indicator validities (the conditional probabilities of indicator endorsement in each latent class) suggest a somewhat different priority for defining NLD than is typically used by researchers investigating this disorder. A high degree of correspondence between LCA classifications and those based on a more conventional algorithm provided evidence for the validity of this approach.

Adolescent↗

PubMedDate not supplied

2D QSAR consensus prediction for high-throughput virtual screening. An application to COX-2 inhibition modeling and screening of the NCI database.

Using classification (SOM, LVQ, Binary, Decision Tree) and regression algorithms (PLS, BRANN, k-NN, Linear), this paper details the building of eight 2D-QSAR models from a 266 COX-2 inhibitor training set. The predictive performances of these eight models were subsequently compared using an 88 COX-2 inhibitor test set. Each ligand is described by 52 2D descriptors expressed as van der Waals Surface Areas (P_VSA) and its COX-2 binding IC50. One of our best predictive models is the neural network model (BRANN), which is able to select a subset, from the 88 ligand test set, that contains 94% COX-2 active inhibitors (pIC50>7.5) and detects 71% of all the actives. We then introduce a QSAR consensus prediction protocol that is shown to be more predictive than any single QSAR model: our C3 consensus approach is able to select a subset from the 88 ligand test set that contains 94% active inhibitors and 83% of all the actives. The 2D QSAR consensus protocol was finally applied to the high-throughput virtual screening of the NCI database, containing 193,477 organic compounds.

Cyclooxygenase 2↗