SEARCH · PubMed Health

Results for “Clustering 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 739 records · Page 41Linked to original sources

PubMed1995

Variability analysis of visual evoked potentials in humans by pattern recognition in phase domain.

A novel approach to single trial visually evoked potentials (VEP) variability analysis based on a new model of post-stimulus brain electrical activity is presented. The convolution model introduced by the author is experimentally verified by the analysis of flash stimulus effects on EEG amplitude and phase spectra. Pattern recognition in the signal phase domain is proposed for detection of any time locked transient signals. This is illustrated by an application of a clustering algorithm in two-dimensional unwrapped phase of EEG Fourier transform space for occipitally recorded VEPs in human subjects.

Adult↗

PubMed2000

Bidirectional classification procedures: double tree and double cluster.

Partition based prediction rules as derived in CART, RECPAM or CBR, relating multivariate predictor variables X to a response variable Y, may be extended to bidirectional classification procedures. Tree or clustering algorithms are simultaneously applied to X and Y resulting in a double partition classification table that should be able to detect existing characteristic patterns of predictor and response values and relate them to each other.

Algorithms↗

PubMed1975

A flow-system multiangle light-scattering instrument for cell characterization.

A flow-system cell-analysis instrument is described in which cells from a heterogeneous population are characterized by their light-scatter patterns alone. As the cells pass at high speed through a focused helium/neon laser beam, the scatter pattern from each cell is sampled simultaneously at up to 32 angles between 0 degrees and 30 degrees with respect to the laser beam axis, and the scatter pattern for each cell is transferred to a computer. A mathematical clustering algorithm is used to determine the number of classes into which the cells can be divided, and a linear separation algorithm is used to find the boundaries between the classes. Preliminary results on exfoliated cells from gynecological specimens are presented. This technique may be useful for automated prescreening of gynecological specimens.

Autoanalysis↗

PubMed2001

[Correlation of endotracheal tube biofilm and recurrent ventilator-associated pneumonia with Pseudomonas aeruginosa].

OBJECTIVE: To determine the correlation of endotracheal tube biofilm (ETT-BF) and recurrent ventilator-associated pneumonia with Pseudomonas aeruginosa (PA-VAP) in long-term ventilation patients. METHODS: Pulsed-field gel electrophoresis (PFGE) of Spe I enzyme-restricted chromosomal DNA was performed to identify the DNA patterns of Pseudomonas aeruginosa from ETT-BF, pharynx and lower respiratory tract secretion in 15 VAP patients. The chromosomal DNA fingerprint profile of each strain was compared with those from all other strains to calculate the similarity by using the correlation coefficient. The strains were then grouped and groups were depicted as a dendrite using the average clustering algorithm. RESULTS: When bacteria has been isolated from ETT-BF, the same DNA pattern species are isolated from the lower respiratory tract secretion in 7 of 15 patients. Recurrent PA-VAP is caused by closely related and indistinguishable isolates in 6 of 15 patients. All PEGE patterns from 9 patients are different from one another (correlation coefficient < 31.2%). CONCLUSIONS: The close pathogenic relationship between ETT-BF and lower airway secretion suggests that adhesive colonization of ETTs may be an important factor in the pathogenesis of VAP.

Aged↗

PubMed2002

Microarray-based copy number and expression profiling in dedifferentiated and pleomorphic liposarcoma.

Sixteen dedifferentiated and pleomorphic liposarcomas were analyzed by comparative genomic hybridization (CGH) to genomic microarrays (matrix-CGH), cDNA-derived microarrays for expression profiling, and by quantitative PCR. Matrix-CGH revealed copy number gains of numerous oncogenes, i.e., CCND1, MDM2, GLI, CDK4, MYB, ESR1, and AIB1, several of which correlate with a high level of transcripts from the respective gene. In addition, a number of genes were found differentially expressed in dedifferentiated and pleomorphic liposarcomas. Application of dedicated clustering algorithms revealed that both tumor subtypes are clearly separated by the genomic profiles but only with a lesser power by the expression profiles. Using a support vector machine, a subset of five clones was identified as "class discriminators." Thus, for the distinction of these types of liposarcomas, genomic profiling appears to be more advantageous than RNA expression analysis.

Algorithms↗

PubMed2002

The effect of contrast and luminance on mfERG responses in a monkey model of glaucoma.

PURPOSE: To evaluate the effect of contrast and luminance attenuation on the multifocal electroretinogram (mfERG) responses of normal and glaucomatous eyes of cynomolgus monkeys. METHODS: Nine adult male cynomolgus monkeys with unilateral experimentally induced glaucoma were used. Hypertension-induced damage was confirmed by tomography of the optic disc. mfERGs were recorded with five different stimulus contrasts and/or luminance settings. The first-order and the first slice of second-order responses were analyzed. RESULTS: Waveforms of normal and glaucomatous eyes differed in shape and amplitude. Second-order responses contributed to first-order responses of the signals in the normal eyes, but made a negligible contribution to the signals in the glaucomatous eyes. Contrast and luminance attenuation affected both first- and second-order responses. The differences between signals in normal and glaucomatous eyes were sufficiently large for an unsupervised clustering algorithm to achieve accurate segregation. CONCLUSIONS: The observations in this study indicate that outer and inner retinal generators participate in first-order mfERG responses and that both inner and outer retinal contributors respond to contrast and luminance changes in stimulus. The hypertension-induced changes in the mfERG furthermore suggest damage to both inner and outer retina.

Animals↗

PubMed2002

Real-time PCR technology for cancer diagnostics.

BACKGROUND: Advances in the biological sciences and technology are providing molecular targets for diagnosing and treating cancer. Current classifications in surgical pathology for staging malignancies are based primarily on anatomic features (e.g., tumor-node-metastasis) and histopathology (e.g., grade). Microarrays together with clustering algorithms are revealing a molecular diversity among cancers that promises to form a new taxonomy with prognostic and, more importantly, therapeutic significance. The challenge for pathology will be the development and implementation of these molecular classifications for routine clinical practice. APPROACH: This article discusses the benefits, challenges, and possibilities for solid-tumor profiling in the clinical laboratory with an emphasis on DNA-based PCR techniques. CONTENT: Molecular markers can be used to provide accurate prognosis and to predict response, resistance, or toxicity to therapy. The diversity of genomic alterations involved in malignancy necessitates a variety of assays for complete tumor profiling. Some new molecular classifications of tumors are based on gene expression, requiring a paradigm shift in specimen processing to preserve the integrity of RNA for analysis. More stable markers (i.e., DNA and protein) are readily handled in the clinical laboratory. Quantitative real-time PCR can determine gene duplications or deletions. Furthermore, melting curve analysis immediately after PCR can identify small mutations, down to single base changes. These techniques are becoming easier and faster and can be multiplexed. Real-time PCR methods are a favorable option for the analysis of cancer markers. SUMMARY: There is a need to translate recent discoveries in oncology research into clinical practice. This requires objective, robust, and cost-effective molecular techniques for clinical trials and, eventually, routine use. Real-time PCR has attractive features for tumor profiling in the clinical laboratory.

Biomarkers, Tumor↗

PubMed2002

Molecular profiling of the role of the NF-kappaB family of transcription factors during alloimmunity.

Allograft rejection involves a complex network of multiple immune regulators and effector mechanisms. In the current study, we focused on the role of nuclear factor (NF)-kappaB/Rel. Previous studies had established that deficiency of the p50 NF-kappaB family member prolonged allograft survival only modestly. However, because of its crucial role in signal transduction in inflammatory and immune responses, we hypothesized that other NF-kappaB/Rel family members may produce more profound effects on alloimmunity. Therefore, in addition to p50, we analyzed the role of c-Rel, which is expressed predominantly in lymphocytes. Also, to investigate NF-kappaB activation in T cells, we examined transgenic mice that express a transdominant inhibitor of NF-kappaB [IkappaB(DeltaN)] regulated by a T cell-restricted promoter. Allograft survival was prolonged indefinitely in the c-Rel-deficient and IkappaB(DeltaN)-transgenic recipients. To determine the molecular basis of NF-kappaB modulation of rejection, we analyzed a panel of 58 parameters including effector molecules, chemokines, cytokines, receptors, and cellular markers using hierarchical clustering algorithms and self-organizing maps in p50(-/-), c-Rel(-/-), and IkappaB(DeltaN)-transgenic, experimental groups plus allogeneic-, syngeneic-, and lymphocyte-deficient (alymphoid) control groups. Surprisingly, profiles of gene expression in the c-Rel recipients (which have indefinite graft survival) were similar to the p50(-/-) and allogeneic recipients (which rapidly reject grafts). As expected, gene expression in the IkappaB(DeltaN) recipients (which also have indefinite graft survival) was similar to profiles of nonrejecting syngeneic and alymphoid recipients. Importantly, self-organizing maps identified a small subset of genes including several chemokine receptors and cytokines with expression profiles that correlate with graft survival. Thus, our results demonstrate a crucial role for NF-kappaB in acute allograft rejection, identify different molecular mechanisms of rejection by distinct NF-kappaB family members, and identify a small subset of inducible genes whose inhibition is linked to graft acceptance.

Algorithms↗

PubMed2003

Classification of follicular thyroid tumors by molecular signature: results of gene profiling.

PURPOSE: Thyroid nodules are common, with a lifetime risk of developing a clinically significant thyroid nodule of 10% or higher. Preoperative diagnosis was greatly enhanced by the introduction of fine needle aspiration in the 1970s, but there has been little advancement since that time. Discrimination between benign and malignant follicular neoplasms is currently not possible by fine needle aspiration and can even be difficult after full pathologic review. The purpose of these studies is to identify genes expressed in follicular adenomas and carcinomas of the thyroid that will permit molecular differentiation of these neoplasms. EXPERIMENTAL DESIGN: Gene expression patterns of 17 thyroid follicular tumors were analyzed by oligonucleotide array analysis. Gene profiles for follicular adenomas and carcinomas were identified, and the two groups were compared for differences in expression levels. The differentially expressed genes were used to perform a hierarchical clustering analysis training set. Five follicular tumors with diagnosis undisclosed to the investigators and 2 minimally invasive carcinomas were entered into the cluster analysis as a test set to determine whether diagnosis by gene profile correlated with that obtained by pathologic evaluation. RESULTS: Thyroid follicular adenomas and carcinomas showed strikingly distinct gene expression patterns. The expression patterns of 105 genes were found to be significantly different between follicular adenoma and carcinoma. Many uncharacterized genes contributed to the distinction between tumor types. For five follicular tumors for which the final diagnosis was undisclosed, the clustering algorithm gave the correct diagnosis in all 5 cases. CONCLUSIONS: Gene profiling is a useful tool to predict the molecular diagnosis of follicular thyroid tumors. Genes were identified that reliably differentiate follicular thyroid carcinoma from adenoma. This study provides insight into genes that may be important in the molecular pathogenesis of follicular thyroid tumors, as well candidates for preoperative diagnosis of follicular thyroid carcinoma.

Adenocarcinoma, Follicular↗

PubMed1992

Emotion differentiation. A correlate of symptom severity in major depression.

The relationship of emotion differentiation to symptom severity in depression was investigated. The subjects were 25 patients diagnosed with unipolar major depression. Subjects were clinically assessed using the Schedule for Affective Disorders and Schizophrenia and the Hamilton rating scales for anxiety and depression. In addition, subjects completed a number of self-report measures of symptoms and attitudes. Twelve basic emotion terms were incorporated into free-response attribute lists which subjects used to rate aspects of themselves and of other significant people in their lives. A clustering algorithm (HICLAS) was used to derive a social perception structure from this data for each subject. The differentiation of negative emotion within an individual's structure (NES) was measured by dividing the number of attribute categories containing negative emotions by the total number of categories in that person's structure. The results indicated that NES is a significant correlate of depressive symptomatology independent of self-esteem and other variables. Relatively undifferentiated emotion structure (low NES) was associated with significantly higher levels of depressive symptomatology.

Adult↗

PubMed2006

A method for clustering white matter fiber tracts.

BACKGROUND/PURPOSE: Despite its potential for visualizing white matter fiber tracts in vivo, diffusion tensor tractography has found only limited applications in clinical research in which specific anatomic connections between distant regions need to be evaluated. We introduce a robust method for fiber clustering that guides the separation of anatomically distinct fiber tracts and enables further estimation of anatomic connectivity between distant brain regions. METHODS: Line scanning diffusion tensor images (LSDTI) were acquired on a 1.5T magnet. Regions of interest for several anatomically distinct fiber tracts were manually drawn; then, white matter tractography was performed by using the Runge-Kutta method to interpolate paths (fiber traces) following the major directions of diffusion, in which traces were seeded only within the defined regions of interest. Next, a fully automatic procedure was applied to fiber traces, grouping them according to a pairwise similarity function that takes into account the shapes of the fibers and their spatial locations. RESULTS: We demonstrated the ability of the clustering algorithm to separate several fiber tracts which are otherwise difficult to define (left and right fornix, uncinate fasciculus and inferior occipitofrontal fasciculus, and corpus callosum fibers). CONCLUSION: This method successfully delineates fiber tracts that can be further analyzed for clinical research purposes. Hypotheses regarding specific fiber connections and their abnormalities in various neuropsychiatric disorders can now be tested.

Adolescent↗

PubMed2006

Gene expression profiles of small-cell lung cancers: molecular signatures of lung cancer.

To characterize the molecular mechanisms involved in the carcinogenesis and progression of small-cell lung cancer (SCLC) and identify molecules to be applied as novel diagnostic markers and/or for development of molecular-targeted drugs, we applied cDNA microarray profile analysis coupled with purification of cancer cells by laser-microbeam microdissection (LMM). Expression profiles of 32,256 genes in 15 SCLCs identified 252 genes that were commonly up-regulated and 851 transcripts that were down-regulated in SCLC cells compared with non-cancerous lung tissue cells. An unsupervised clustering algorithm applied to the expression data easily distinguished SCLC from the other major histological type of non-small cell lung cancer (NSCLC) and identified 475 genes that may represent distinct molecular features of each of the two histological types. In particular, SCLC was characterized by altered expression of genes related to neuroendocrine cell differentiation and/or growth such as ASCL1, NRCAM, and INSM1. We also identified 68 genes that were abundantly expressed both in advanced SCLCs and advanced adenocarcinomas (ADCs), both of which had been obtained from patients with extensive chemotherapy treatment. Some of them are known to be transcription factors and/or gene expression regulators such as TAF5L, TFCP2L4, PHF20, LMO4, TCF20, RFX2, and DKFZp547I048 as well as those encoding nucleotide-binding proteins such as C9orf76, EHD3, and GIMAP4. Our data provide valuable information for better understanding of lung carcinogenesis and chemoresistance.

Antineoplastic Agents↗

PubMed1991

Multivariate procedures to describe clinical staging of melanoma.

Analyzing multivariate clinical data to identify subclasses of patients being treated for a specific disease may improve patient management and increase understanding of the behavior of disease under clinical conditions. In some cases, patients have been classified on prognostic characteristics using standard risk assessment procedures (e.g., Cox' regression). This requires long term follow-up, differentiates patients only on attributes relevant to survival, and assumes that patients are sampled from a common population. Other approaches involve the use of clustering algorithms to classify patients into categories based on multiple clinical attributes. We illustrate the use of a multivariate statistical procedure to directly characterize patients on multiple clinical characteristics. The procedure is designed to analyze discrete response data with parameters representing individual differences within groups. Its use is illustrated for patients with Stage I melanoma in determining how age is related to treatment response in different patient groups.

Adult↗

PubMed1990

From biopsy to automatic diagnosis.

High resolution two-dimensional gel electrophoresis is a very powerful biochemical tool for analysis of complex protein mixtures. In well defined situations, protein maps, obtained from tissue biopsies or biological fluids by this technique, can be automatically analyzed by computer. Some polypeptide patterns are the fingerprints of diseases. Applying clustering algorithm and learning techniques, the prototype expert system MELANIE recognized patterns and associated the correct diagnosis to the specific pattern.

Diagnosis, Computer-Assisted↗

PubMedDate not supplied

[Phylogenetic analysis of partial nucleotide sequences of 18S rRNA for 14 plant species].

The variable 260 base long region from the interior of 18S rRNA of 14 plant species was determined by chain termination method with the use of reverse transcriptase. The hairpin revealed in this region appeared to be conservative in all species compared. Thermodynamic stability of such hairpin is lower than of an alternative structure with different base pairing mode. From sequence data dendrograms were produced by clustering algorithms and by the compatibility method. In addition to the plant sequences these dendrograms included also the homologous regions from yeast and Xenopus 18S rRNAs. The compatibility method seems to be more reliable. Inferences were drawn on relations between gymnosperms and angiosperms, monocots and dicots on the bases of the analysis of this tree.

Base Sequence↗

PubMed1989

Quantification of progressive diabetic macular nonperfusion.

We used the IS-2000 Image Analyzer to estimate the extent of progressive diabetic macular nonperfusion in a patient by means of an automatic clustering algorithm applied to digitized fluorescein angiograms of the patient's macula taken over time. This method may provide an objective and reproducible quantification of progressive macular nonperfusion.

Adult↗

PubMedDate not supplied

Quantification of gray/white matter in neonates and adults.

Quantitation of gray/white matter is important in evaluation of cerebral blood flow, atrophy, and development of the brain. First-order statistical analysis of neonatal computed tomographic (CT) images revealed that there was only a 6 Hounsfield unit (H) difference between gray and white matter compared with the observed 3 H for the standard deviation over the field of a skull water phantom. Scene segmentation methods based on first-order statistics proved unsuccessful in separating gray and white matter. A new regional clustering algorithm based on local textural properties was developed for separation of these structures.

Adult↗

PubMed1984

Automatic classification of EEG segments and extraction of representative ones by dynamic clusters method.

Use of the dynamic clusters method for automatic extraction of compressed information about recorded EEG signal is presented. The computer first divides the record into quasi-stationary segments by means of adaptive segmentation. Second, the extracted segments are classified by a method of dynamic clusters into homogeneous classes. One part of the used clustering algorithm permits to specify and draw the most typical class members, which may represent the whole studied EEG signal and may be used as input for the further phase of the automatic EEG analysis, i.e. for the classification of the whole EEG records. The above procedure was applied to a 75 sec long EEG record of anaesthetized cat intoxicated by CO.

Computers↗