Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Classification Algorithms”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 685 records · Page 38Linked to original sources
PubMed2003

Method for optimizing pulsed-field gel electrophoresis banding pattern data.

The genomic DNA of 47 strains of TSST-1 toxin-producing Staphylococcus aureus were cleaved with SmaI restriction endonuclease and resolved in an agarose gel by pulsed-field gel electrophoresis (PFGE). An algorithm was designed to standardize the band weights or brightness (trace quantity) produced to a bounded region between 0 and 1 regardless of DNA fragment size while simultaneously reducing gel-to-gel variability. The algorithm allows for classification of isolates by band intensity as well as DNA mobility without a numerical hierarchy of band intensity that is caused by ranging DNA fragment lengths. On analysis many isolates were classified as separate entities on the basis of DNA co-migration only. Isolates differing by only DNA co-migration were subjected to a second digestion with restriction enzyme SacII. These isolates were characterized similarly to the standardized trace quantity analysis of SmaI PFGE patterns. The standardization method proposed in this article permits characterization of isolates on the basis of band differences, regardless of DNA co-migration, thus increasing the discriminatory power (0.79 to 0.89) of PFGE by increasing band-associated information. An established unbiased approach to the partitioning of data were also explored.

Algorithms↗
PubMed2004

Gene expression profiling of pediatric acute myelogenous leukemia.

Contemporary treatment of pediatric acute myeloid leukemia (AML) requires the assignment of patients to specific risk groups. To explore whether expression profiling of leukemic blasts could accurately distinguish between the known risk groups of AML, we analyzed 130 pediatric and 20 adult AML diagnostic bone marrow or peripheral blood samples using the Affymetrix U133A microarray. Class discriminating genes were identified for each of the major prognostic subtypes of pediatric AML, including t(15;17)[PML-RARalpha], t(8;21)[AML1-ETO], inv(16) [CBFbeta-MYH11], MLL chimeric fusion genes, and cases classified as FAB-M7. When subsets of these genes were used in supervised learning algorithms, an overall classification accuracy of more than 93% was achieved. Moreover, we were able to use the expression signatures generated from the pediatric samples to accurately classify adult de novo AMLs with the same genetic lesions. The class discriminating genes also provided novel insights into the molecular pathobiology of these leukemias. Finally, using a combined pediatric data set of 130 AMLs and 137 acute lymphoblastic leukemias, we identified an expression signature for cases with MLL chimeric fusion genes irrespective of lineage. Surprisingly, AMLs containing partial tandem duplications of MLL failed to cluster with MLL chimeric fusion gene cases, suggesting a significant difference in their underlying mechanism of transformation.

Adult↗
PubMed1997

Quantitative MRI of the gray-white matter distribution in traumatic brain injury.

Quantitative analyses were performed on magnetic resonance images (MRIs) obtained from the brains of 31 traumatic brain-injured (TBI) patients and 25 normal control subjects. The quantitative analyses involved comparisons of the shapes of proton density gray scale pixel histograms obtained from both 3-mm and 5-mm slice thickness. Image segmentation was accomplished by a multispectral fuzzy C-means and/or k-nearest-neighbor (kNN) algorithms and manual classification was used to label segmented classes into CSF, white matter, and other. Shape descriptors were derived from the pixel intensity histograms of the combined gray matter and white matter classes for each MRI slice. Statistical analyses revealed significant differences in pixel intensity distributions between TBI and control subjects. Normal control subjects tended to exhibit bimodal gray matter-white matter histograms, whereas, TBI patients tended to exhibit unimodal gray matter-white matter histograms. In the control subjects the pixels intermediate in intensity between gray and white matter were located primarily at the border between the gray and white matter, whereas TBI patients exhibited a thickening of the number of intermediate pixels at the border as well as an increase in intermediate pixels in the middle of the gray and white matter. The greater the severity of TBI, then the larger the number of intermediate intensity pixels within and between gray and white matter. Further analyses demonstrated shifts in magnetic resonance relaxation times in gray and white matter in TBI patients, which suggested that the tendency toward unimodality in TBI patients represents a pathological reduction in brain differentiation due to measurable biophysical change.

Adult↗
PubMed2004

Contrast-enhanced high-resolution MRI of invasive breast cancer: correlation with histopathologic subtypes.

OBJECTIVE: We sought to determine whether contrast-enhanced MRI could aid in the identification of the histopathologic subtypes of invasive ductal carcinoma. MATERIALS AND METHODS: We evaluated the contrast-enhanced MR images obtained in 62 women with invasive ductal carcinoma of no special type. The presence or absence of three distinct MRI findings-linear enhancement, a serrated border, and delayed rim enhancement-was evaluated. Classification and regression tree analyses were performed to construct the most efficient algorithm for predicting histopathologic subtype on the basis of dynamic MRI features. RESULTS: Histopathologic subtypes of the invasive ductal carcinomas were scirrhous carcinoma in 22 patients, solid tubular carcinoma in 14, and papillotubular carcinoma in 26. A lesion with a serrated border was observed in 28 (45.2%) of the 62 patients. Delayed rim enhancement was seen in 23 (37.1%) and linear enhancement in 20 (32.3%). Scirrhous carcinomas were closely associated with a serrated border (20/22 or 90.9%, p < 0.0001). Delayed rim enhancement was frequently observed in solid tubular carcinomas (12/14 or 85.7%, p < 0.0001) but was not typically seen in scirrhous carcinomas (1/22 or 4.5%, p < 0.0001). Linear enhancement showed relatively high prevalence in papillotubular carcinomas (13/26 or 50%) and low prevalence in solid tubular carcinomas (1/22 or 7%, p < 0.02). Histopathologic subtypes of invasive breast carcinoma of no special type could be correctly identified in 47 (75.8%) of 62 lesions using the diagnostic algorithm generated by the classification and regression tree analyses. CONCLUSION: MRI features showed a close relationship with histopathologic subtypes of invasive ductal carcinoma of no special type. Contrast-enhanced MRI can be a noninvasive diagnostic tool for histopathologic subtypes of invasive breast cancer.

Adult↗
PubMed1997

Impact of a worker's compensation practice guideline on lumbar spine fusion in Washington State.

OBJECTIVES: In the face of escalating medical costs for injured workers, the Washington State Department of Labor and Industries (L&I), which pays for most workers' compensation costs in the state, established guidelines for elective lumbar fusion as part of its inpatient utilization review program. The guidelines were tied to reimbursement strictures. The authors attempt to assess the effects of these guidelines, which were introduced in November 1988, upon subsequent L&I fusion procedures. METHODS: Discharge data from the Comprehensive Hospital Abstract Reporting System and algorithms using International Classification of Diseases, Version 9, Clinical Modification diagnosis and procedure codes were used to identify lumbar surgical cases. Population estimates were from the 1990 US Census Bureau. RESULTS: During the period of years 1987 through 1992, the lumbar fusion rate for the state showed a 26% decline compared with a 3% decrease for all lumbar operations. After November 1988, when the guidelines went into effect, the state fusion rate declined 33%, whereas rates for nonfusion operations essentially were unchanged. The sharpest decline corresponded in time to implementation of the guidelines. Prior to the initiation of L&I guidelines, the proportion of fusions among L&I patients was higher than among non-L&I patients. The opposite was true by the end of 1992, and the L&I proportion decreased more rapidly than the non-L&I proportion. Time series analysis revealed that both the decline in Washington state lumbar fusion rates and the decline in the proportion of lumbar fusion among L&I patients were statistically significant. CONCLUSIONS: The data suggest that the L&I lumbar fusion surgery criteria and reimbursement standards implemented in 1988 contributed to a decline in rates of performing that procedure. The utilization review aspect of the guidelines as well as the process of involving surgeons in the preparation and dissemination of guidelines also may have been contributory.

Adult↗
PubMed1997

A pattern classification procedure integrating the multivariate statistical analysis with neural networks.

A new procedure integrating multivariate statistical analysis with artificial neural networks (ANN) for complex pattern classification is proposed. Firstly, a specially designed statistical analysis algorithm called correlative component analysis (CCA) was used to identify the classification characteristics (CC) from original high-dimensional pattern information. These CC were then used as input data to the ANN for pattern classification. The proposed new procedure not only effectively decreased the dimensionality of original patterns, but also took advantage of the self-learning power of the ANN. Further, a typical example of classifying natural spearmint essence was employed to verify the effectiveness of the new pattern classification method. The study showed that this novel integrated procedure provides better results than those obtained using individual methods separately.

Algorithms↗
PubMed1986

Development of criteria for the classification and reporting of osteoarthritis. Classification of osteoarthritis of the knee. Diagnostic and Therapeutic Criteria Committee of the American Rheumatism Association.

For the purposes of classification, it should be specified whether osteoarthritis (OA) of the knee is of unknown origin (idiopathic, primary) or is related to a known medical condition or event (secondary). Clinical criteria for the classification of idiopathic OA of the knee were developed through a multicenter study group. Comparison diagnoses included rheumatoid arthritis and other painful conditions of the knee, exclusive of referred or para-articular pain. Variables from the medical history, physical examination, laboratory tests, and radiographs were used to develop sets of criteria that serve different investigative purposes. In contrast to prior criteria, these proposed criteria utilize classification trees, or algorithms.

Adult↗
PubMed2005

Proteomic signatures for histological types of lung cancer.

We performed proteomic studies on lung cancer cells to elucidate the mechanisms that determine histological phenotype. Thirty lung cancer cell lines with three different histological backgrounds (squamous cell carcinoma, small cell lung carcinoma and adenocarcinoma) were subjected to two-dimensional difference gel electrophoresis (2-D DIGE) and grouped by multivariate analyses on the basis of their protein expression profiles. 2-D DIGE achieves more accurate quantification of protein expression by using highly sensitive fluorescence dyes to label the cysteine residues of proteins prior to two-dimensional polyacrylamide gel electrophoresis. We found that hierarchical clustering analysis and principal component analysis divided the cell lines according to their original histology. Spot ranking analysis using a support vector machine algorithm and unsupervised classification methods identified 32 protein spots essential for the classification. The proteins corresponding to the spots were identified by mass spectrometry. Next, lung cancer cells isolated from tumor tissue by laser microdissection were classified on the basis of the expression pattern of these 32 protein spots. Based on the expression profile of the 32 spots, the isolated cancer cells were categorized into three histological groups: the squamous cell carcinoma group, the adenocarcinoma group, and a group of carcinomas with other histological types. In conclusion, our results demonstrate the utility of quantitative proteomic analysis for molecular diagnosis and classification of lung cancer cells.

Adenocarcinoma↗
PubMed1985

Diabetic neuropathy.

The incidence and prevalence of diabetic neuropathies in Insulin Dependent (IDDM) and Non-Insulin Dependent (NIDDM) Diabetes Mellitus is not known because in previous studies the heterogeneity of diabetes and of the neuropathies was not taken into account, criteria for diagnosis and surveillance for neuropathy were variable, and studies were not prospective or population based. We have begun such prospective epidemiologic studies using a uniform algorithm for the classification of the diabetic disorders and uniform and validated approaches for the assessment of symptoms, neurologic deficits and various quantitative end-points of neural dysfunction. As regards cause, a key question which we are trying to answer is whether hyperglycemia and associated metabolic alterations affect neural tissue directly or whether there is an intervening tissue alteration between metabolic derangement and tissue change. Improved control of hyperglycemia does not appear to be associated with rapid neurologic improvement, possibly arguing for an intervening tissue alteration. The recently observed decrease in nerve oxygen tension and blood flow in streptozotocin diabetes suggests that an alteration of the nerve microenvironment may relate importantly to the cause of diabetic neuropathy.

Diabetes Mellitus, Type 1↗
PubMed2004

Oligosaccharide identification and mixture quantification using Raman spectroscopy and chemometric analysis.

This work demonstrates the feasibility of using Raman spectroscopy for the analysis of small quantities of chemically similar oligosaccharides and their mixtures. Raman spectra were obtained from 10-microL aliquots of 1 mM solutions of maltotetraose and/or stachyose after deposition onto an electrochemically roughened silver substrate (and the resulting spectral features are attributed to a combination of normal and surface-enhanced Raman scattering). These compounds were selected because they are representative of glycans derived from post-translationally modified proteins which, like these compounds, often consist of isomers of equal mass and similar shape. Replicate spectral measurements were recorded and processed using a partial-least-squares (PLS) classification and quantification algorithms with a leave-one-batch-out (LOBO) training and testing procedure. Spectra derived from solutions of individual sugars were identified with 100% accuracy, and mixtures of the two sugars were quantified with an average error of 2.7% in the relative maltotetraose/stachyose composition for mixtures with a total oligosaccharide concentration of 1 mM.

Algorithms↗
PubMed2004

Imatinib therapy for hypereosinophilic syndrome and eosinophilia-associated myeloproliferative disorders.

A pathogenetic mutation, FIP1L1-PDGFRA, that results from an interstitial chromosome 4q12 deletion, leads to a constitutive activation of the platelet-derived growth factor receptor-alpha (PDGFRA) tyrosine kinase as well as a disease phenotype that mimics both the hypereosinophilic syndrome (HES) and systemic mast cell disease associated with eosinophilia (SMCD-eos). Complete remissions, in response to treatment with low-dose imatinib mesylate (100 mg/day or less) have now been documented in all cases of FIP1L1-PDGFRA(+) eosinophilic disorder as well as other eosinophilic disorders that carry activation mutations of the PDGFRB gene that is located on chromosome 5q33. Furthermore, response to therapy has been rapid (within days) and durable. Interestingly, imatinib mesylate treatment, at a higher dose level (400 mg/day), might induce either partial or short-lived complete remissions in HES that is not associated with the aforementioned PDGFR mutations. These observations make it necessary to re-examine current disease classification and treatment algorithms in eosinophilic disorders.

Benzamides↗
PubMed2004

An improved automated ultrasonic NDE system by wavelet and neuron networks.

Despite of the widespread and increasing use of digitized signals, the ultrasonic testing community has not realized yet the full potential of the electronic processing. The performance of an ultrasonic flaw detection method is evaluated by the success of distinguishing the flaw echoes from those scattered by microstructures. So, de-noising of ultrasonic signals is extremely important as to correctly identify smaller defects, because the probability of detection usually decreases as the defect size decreases, while the probability of false call does increase. In this paper, the wavelet transform has been successfully experimented to suppress noise and to enhance flaw location from ultrasonic signal, with a good defect localization. The obtained result is then directed to an automatic Artificial Neuronal Networks classification and learning algorithm of defects from A-scan data. Since there is some uncertainty connected with the testing technique, the system needs a numerical modelling. So, knowing the technical characteristics of the transducer, we can preview which are the defects that experimental inspection should find. Indeed, the system performs simulation of the ultrasonic wave propagation in the material, and gives a very helpful tool to get information and physical phenomena understanding, which can help to a suitable prediction of the service life of the component.

Materials Testing↗
PubMed2000

Predictive model for survival at the conclusion of a damage control laparotomy.

BACKGROUND: We employed modern statistical and data mining methods to model survival based on preoperative and intraoperative parameters for patients undergoing damage control surgery. METHODS: One hundred seventy-four parameters were collected from 68 damage control patients in prehospital, emergency center, operating room, and intensive care unit (ICU) settings. Data were analyzed with logistic regression and data mining. Outcomes were survival and death after the initial operation. RESULTS: Overall mortality was 66.2%. Logistic regression identified pH at initial ICU admission (odds ratio: 4.4) and worst partial thromboplastin time from hospital admission to ICU admission (odds ratio: 9.4) as significant. Data mining selected the same factors, and generated a simple algorithm for patient classification. Model accuracy was 83%. CONCLUSION: Inability to correct pH at the conclusion of initial damage-control laparotomy and the worst PTT can be predictive of death. These factors may be useful to identify patients with a high risk of mortality.

Critical Illness↗
PubMed2000

Grading of cerebral autoregulation in preterm and term neonates.

The response of cerebral blood flow velocity to a single spontaneous transient rise in blood pressure was studied to grade the cerebral autoregulatory response of newborns. Blood pressure was measured continuously through an umbilical or peripheral arterial catheter; continuous flow velocity recordings were taken from the middle cerebral artery using continuous wave Doppler ultrasound. From a cohort of 62 healthy term and preterm neonates, 325 transients in mean arterial blood pressure and mean cerebral blood flow velocity were identified for analysis using a foot-seeking algorithm. An initial classification of active or impaired autoregulation was given to each transient using a self-clustering technique. The grading of the transients was studied by examining the slope of the return of the cerebral blood flow velocity to baseline. Negative slopes indicate a normal autoregulation; slopes of 0 or greater indicate an absence of autoregulation. This classification was in agreement with the self-clustering method (Cohen's kappa = 0.94, P<0.0001). The relationship between the autoregulatory response assessed by the grading method and gestational age, postnatal age, and PCO(2) was examined using linear regression analysis. A significant relationship with gestational age (P = 0.002) but not PCO(2) (P = 0.06) or postnatal age (P = 0.14) was evident.

Blood Flow Velocity↗
PubMed1998

Deriving a preference-based single index from the UK SF-36 Health Survey.

This article presents the results of a study to derive a preference-based single index from the SF-36. The study was an attempt to reconcile a profile health status measure, the SF-36, with the "quality adjusted life years" approach. The study undertook a parsimonious restructuring of the SF-36 using explicit criteria to form the SF-6D health state classification. A sample of multidimensional health states defined by this classification were valued by a convenience sample of health professionals, managers, and patients, who responded to a set of visual analogue scale ratings and standard gamble questions, with highly complete and consistent answers. Statistical models were estimated to predict single index scores for all 9000 health states defined by the new classification. The resultant algorithms can be applied to existing SF-36 data sets and used in the assessment of the cost-effectiveness of health technologies. This preliminary work forms the basis of a larger study currently being undertaken in the UK.

Algorithms↗
PubMed2002

Trimodal spectroscopy for the detection and characterization of cervical precancers in vivo.

OBJECTIVE: The objective of this study was to assess the potential of 3 spectroscopic techniques (intrinsic fluorescence, diffuse reflectance, and light scattering) individually and in combination (trimodal spectroscopy) for the detection of cervical squamous intraepithelial lesions. STUDY DESIGN: The study was conducted with 44 patients who underwent colposcopy for the evaluation of an abnormal Papanicolaou smear. Fluorescence and reflectance spectra were collected from colposcopically normal and abnormal sites and analyzed to extract quantitative information about tissue biochemistry and morphologic condition. This information was compared with histopathologic classification, and diagnostic algorithms were developed and validated with the use of logistic regression and cross-validation. RESULTS: Diagnostically significant differences exist in the composition of fluorescing biochemicals, the scattering properties, and the epithelial cell nuclear morphology of cervical squamous intraepithelial lesions and non-squamous intraepithelial lesions. Trimodal spectroscopy is a superior tool for the detection of cervical squamous intraepithelial lesions than any 1 of the techniques alone. CONCLUSION: Trimodal spectroscopy has the potential to improve the in vivo detection of precancerous cervical changes.

Diagnosis, Differential↗
PubMed2005

Framework for kernel regularization with application to protein clustering.

We develop and apply a previously undescribed framework that is designed to extract information in the form of a positive definite kernel matrix from possibly crude, noisy, incomplete, inconsistent dissimilarity information between pairs of objects, obtainable in a variety of contexts. Any positive definite kernel defines a consistent set of distances, and the fitted kernel provides a set of coordinates in Euclidean space that attempts to respect the information available while controlling for complexity of the kernel. The resulting set of coordinates is highly appropriate for visualization and as input to classification and clustering algorithms. The framework is formulated in terms of a class of optimization problems that can be solved efficiently by using modern convex cone programming software. The power of the method is illustrated in the context of protein clustering based on primary sequence data. An application to the globin family of proteins resulted in a readily visualizable 3D sequence space of globins, where several subfamilies and subgroupings consistent with the literature were easily identifiable.

Algorithms↗