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 649 records · Page 36Linked to original sources

PubMed2002

Nonlinear fisher discriminant analysis using a minimum squared error cost function and the orthogonal least squares algorithm.

The nonlinear discriminant function obtained using a minimum squared error cost function can be shown to be directly related to the nonlinear Fisher discriminant (NFD). With the squared error cost function, the orthogonal least squares (OLS) algorithm can be used to find a parsimonious description of the nonlinear discriminant function. Two simple classification techniques will be introduced and tested on a number of real and artificial data sets. The results show that the new classification technique can often perform favourably compared with other state of the art classification techniques.

Algorithms↗

PubMed1999

Protein subcellular location prediction.

The function of a protein is closely correlated with its subcellular location. With the rapid increase in new protein sequences entering into data banks, we are confronted with a challenge: is it possible to utilize a bioinformatic approach to help expedite the determination of protein subcellular locations? To explore this problem, proteins were classified, according to their subcellular locations, into the following 12 groups: (1) chloroplast, (2) cytoplasm, (3) cytoskeleton, (4) endoplasmic reticulum, (5) extracell, (6) Golgi apparatus, (7) lysosome, (8) mitochondria, (9) nucleus, (10) peroxisome, (11) plasma membrane and (12) vacuole. Based on the classification scheme that has covered almost all the organelles and subcellular compartments in an animal or plant cell, a covariant discriminant algorithm was proposed to predict the subcellular location of a query protein according to its amino acid composition. Results obtained through self-consistency, jackknife and independent dataset tests indicated that the rates of correct prediction by the current algorithm are significantly higher than those by the existing methods. It is anticipated that the classification scheme and concept and also the prediction algorithm can expedite the functionality determination of new proteins, which can also be of use in the prioritization of genes and proteins identified by genomic efforts as potential molecular targets for drug design.

Algorithms↗

PubMedDate not supplied

Structure analysis and classification of cervical cells using a processing system based on TV.

This paper presents preliminary results of a cell classification experiment using a new approach for feature extraction. The algorithm takes into account the special requirements of a fast parallel processing system (processor-oriented algorithms). A cell image is described by several hundred features derived from the nucleus only. The most significant features with respect to classification are determined by statistical analysis. Applying principal axis transform, a new feature set is computed, reduced considerably in dimensions. The data base (1,925 cell images of Papanicolaou-stained cervical specimens) was divided into a training set (963 images) and a test set (962 images). The classification results of the test set show that the recognition rate for the two-class problem (normal, suspicious) is better than 91%, using only ten morphologic features.

Cervix Mucus↗

PubMed2002

New methods for the analysis of binarized BIOLOG GN data of Vibrio species: minimization of stochastic complexity and cumulative classification.

We apply minimization of stochastic complexity and the closely related method of cumulative classification to analyse the extensively studied BIOLOG GN data of Vibrio spp. Minimization of stochastic complexity provides an objective tool of bacterial taxonomy as it produces classifications that are optimal from the point of view of information theory. We compare the outcome of our results with previously published classifications of the same data set. Our results both confirm earlier detected relationships between species and discover new ones.

Algorithms↗

PubMed2002

Survival analysis with time-varying regression effects using a tree-based approach.

Nonproportional hazards often arise in survival analysis, as is evident in the data from the International Non-Hodgkin's Lymphoma Prognostic Factors Project. A tree-based method to handle such survival data is developed for the assessment and estimation of time-dependent regression effects under a Cox-type model. The tree method approximates the time-varying regression effects as piecewise constants and is designed to estimate change points in the regression parameters. A fast algorithm that relies on maximized score statistics is used in recursive segmentation of the time axis. Following the segmentation, a pruning algorithm with optimal properties similar to those of classification and regression trees (CART) is used to determine a sparse segmentation. Bootstrap resampling is used in correcting for overoptimism due to split point optimization. The piecewise constant model is often more suitable for clinical interpretation of the regression parameters than the more flexible spline models. The utility of the algorithm is shown on the lymphoma data, where we further develop the published International Risk Index into a time-varying risk index for non-Hodgkin's lymphoma.

Algorithms↗

PubMed1999

Streptomyces malaysiensis sp. nov., a new streptomycete species with rugose, ornamented spores.

The taxonomic position of a streptomycete strain isolated from Malaysian soil was established using a polyphasic approach. The organism, designated strain ATB-11T, was found to have chemical and morphological properties consistent with its classification in the genus Streptomyces. An almost complete 16S rRNA gene (rDNA) sequence determined for the test strain was compared with those of previously studied streptomycetes by using two treeing algorithms. The 16S rDNA sequence data not only supported classification of the strain in the genus Streptomyces but also showed that it formed a distinct phyletic line. At maturity, the aerial hyphae of strain ATB-11T differentiated into tight, spiral chains of rugose, cylindrical spores. The organism was readily distinguished from representatives of validly described Streptomyces species with rugose spores by using a combination of phenotypic features. It is proposed, therefore, that strain ATB-11T be classified in the genus Streptomyces as Streptomyces malaysiensis sp. nov.

Bacterial Typing Techniques↗

PubMed1994

A new hierarchical classification of causes of infant deaths in England and Wales.

In 1986 The Office of Population Censuses and Surveys (OPCS) introduced new certificates for stillbirths and neonatal deaths. This allowed certifiers more flexibility in the completion of the certificate, and the number and ordering of the causes given. Tabulations have been published of the fetal and maternal causes of death mentioned on the certificates for every year from 1986 to 1991 in annual reference volumes. It has not been possible either to derive a single cause group for each death, however, or to compare the information available on neonatal deaths with that on postneonatal deaths, which are still derived from the standard death certificate. The aim of the work described here was to adapt previous classifications to derive a single cause grouping for stillbirths and infant deaths which would provide the maximum information about preventability and yet meet the national and international responsibilities of OPCS. The methods used and the tests carried out on the validity and consistency of the chosen classification are described.

Algorithms↗

PubMedDate not supplied

Analysis of tear protein patterns by a neural network as a diagnostical tool for the detection of dry eyes.

The electrophoretic patterns of tears from patients with dry-eye disease (n = 43) and from healthy subjects (n = 17) were analyzed by means of multivariate statistical methods and an artificial neural network (ANN), following sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE). From each electrophoretic pattern a data set was created, randomly divided into test (unknown samples) and training patterns (known samples), with ANN training by one of these sets. After training, the performance of the ANN was checked by presenting the test data set to the ANN. Furthermore, the data was classified using multivariate analysis of discriminance. The groups were significantly different from each other (P<0.05). The statistical procedure yielded 97% (known samples) and 71% (unknown samples) correct classifications. The ANN revealed 89% of correct classifications using the test set (unknown samples). The use of pruning algorithms (optimization procedure which automatically eliminates small weighted neurons) or genetic algorithms (optimization procedure which performs genetically induced changes of the neural net) resulted in a slight decrease of correct classifications compared to those of the nonoptimized neural network. The results reveal significant differences between the two groups. Using the ANN we were able to classify the electrophoretic tear protein pattern for diagnostic purposes.

Dry Eye Syndromes↗

PubMed1997

Is neural network better than statistical methods in diagnosis of acute appendicitis?

Three statistical classification methods: discriminant analysis, logistic regression analysis and cluster analysis were compared with the back-propagation neural network algorithm in the diagnosis of acute appendicitis. The differences in the classification accuracy, which were evaluated with the receiver operating characteristic (ROC) curve were small, though discriminant analysis and back-propagation showed slightly better results than the other methods. The agreement of the methods on the diagnosis increased the accuracy of the classification, so that the number of misclassified cases reduced. The back-propagation neural network offers a good choice for statistical classification methods, but it was not found to be better than them. The use of several methods and their agreement as the basis of the diagnosis seems to give the best results for this diagnostic classification problem.

Appendicitis↗

PubMed2003

Applications of Fourier transform infrared microspectroscopy in studies of benign prostate and prostate cancer. A pilot study.

Fourier transform infrared (FTIR) microspectroscopy has been applied to a study of prostate cancer cell lines derived from different metastatic sites and to tissue from benign prostate and Gleason-graded malignant prostate tissue. Paraffin-embedded tissue samples were analysed by FTIR, after mounting onto a BaF(2) plate and subsequent removal of wax using Citroclear followed by acetone. Cell lines were analysed as aliquots of cell suspension held between two BaF(2) plates. It was found that the ratio of peak areas at 1030 and 1080 cm(-1), corresponding to the glycogen and phosphate vibrations respectively, suggests a potential method for the differentiation of benign from malignant cells. The use of this ratio in association with FTIR spectral imaging provides a basis for estimating areas of malignant tissue within defined regions of a specimen. Initial chemometric treatment of FTIR spectra, using the linear discriminant algorithm, demonstrates a promising method for the classification of benign and malignant tissue and the separation of Gleason-graded CaP spectra. Using the principle component analysis, this study has achieved for the first time the separation of FTIR spectra of prostate cancer cell lines derived from different metastatic sites.

Adenocarcinoma↗

PubMed2003

Tree-based disease classification using protein data.

A reliable and precise classification of diseases is essential for successful diagnosis and treatment. Using mass spectrometry from clinical specimens, scientists may find the protein variations among disease and use this information to improve diagnosis. In this paper, we propose a novel procedure to classify disease status based on the protein data from mass spectrometry. Our new tree-based algorithm consists of three steps: projection, selection and classification tree. The projection step aims to project all observations from specimens into the same bases so that the projected data have fixed coordinates. Thus, for each specimen, we obtain a large vector of 'coefficients' on the same basis. The purpose of the selection step is data reduction by condensing the large vector from the projection step into a much lower order of informative vector. Finally, using these reduced vectors, we apply recursive partitioning to construct an informative classification tree. This method has been successfully applied to protein data, provided by the Department of Radiology and Chemistry at Duke University.

Computational Biology↗

PubMed1983

An empirical evaluation of qualitative Hennigian analyses of protein electrophoretic data.

In an empirical evaluation of a qualitative approach to construction of phylogenetic trees from protein-electrophoretic data, we have employed Hennigian cladistic principles to generate molecular trees for water-fowl, rodents, bats, and other phylads. This procedure of tree construction is described in detail. Branching structures of molecular trees produced by three different algorithms were compared against those of "model" classifications previously proposed by other systematists. In each case, the qualitative cladistic trees provided fits to model phylogenies which were strong and as good or better than those resulting from phenetic-clustering or distance-Wagner trees based on manipulation of quantitative values in matrices of genetic distance. The qualitative Hennigian approach has several pragmatic (as well as theoretical) advantages for analyzing routine sets of electrophoretic data: (1) the analyses are simple and can be performed by hand; (2) they provide the researcher with a strong "feel" for the data; (3) additional data (from new loci or species) can readily be added to the tree without need to recalculate distance matrices; and (4) the qualitative output of the analyses explicitly defines character states along all branches of the tree, and hence affords a high degree of testability. However, these advantages are counterbalanced by a number of serious disadvantages which will likely limit the general applicability of this qualitative approach. These drawbacks are also discussed in detail. For a deeper appreciation of electrophoretic-based protein phylogenies, it is suggested that both quantitative phenetic and qualitative cladistic analyses be employed when possible, and that results of the two approaches be contrasted.

Animals↗

PubMed1999

[Exclusion of receptive speech disorders with the ADOS (Autism Diagnostic Observation Schedule)].

OBJECTIVE: The purpose of our pilot study was to assess the reliability and diagnostic validity of the Autism Diagnostic Observation Schedule (ADOS). The usefulness of the schedule in the differentiation between children with autism and children with a severe specific receptive language disorder is examined. METHOD: Eight boys with early infantile autism and eight age- and IQ-matched boys with a specific receptive language disorder were examined with the ADOS. The reliability of the instrument was assessed using the ratings of eight pairs of raters. The agreement between diagnostic classification based on the ADOS ICD-10 algorithm and the independent clinical psychiatric diagnosis of two experts was used as the measure of validity. RESULTS: The reliability of the different ADOS items proved to be good among experienced raters. Various ADOS items clearly discriminate both groups. Using the ADOS ICD-10 algorithm, the clinical diagnosis of infantile autism could be confirmed for five of the eight children in this group. None of the children with the clinical diagnosis of a receptive language disorder was identified as autistic according to the algorithm. CONCLUSIONS: In the hands of experienced raters the ADOS is a reliable diagnostic instrument. It can support the differentiation between autism and specific receptive language disorder, but additional parent information is needed to confirm the diagnosis.

Auditory Perceptual Disorders↗

PubMed1999

Integrating disease management and wound care critical pathways in home care.

This article discusses the need for an integration of the concepts of disease management and critical pathways as a foundation of a healthcare delivery system. The steps in the process for development, implementation, and evaluation of a wound care critical pathway are reviewed and variance classifications are defined. Co-pathways and algorithms are presented as methodologies for dealing with variances. A template of a wound care critical pathway that has been developed for use in the home care setting is included.

Algorithms↗

PubMed1993

Clinical classification as a predictor of therapeutic outcome after cervical epidural steroid injection.

A retrospective analysis was done on 100 patients who had received cervical epidural steroid injections for neck pain and cervical radiculopathy to identify the predictors of outcome after such treatment. Potential predictors of outcome were assessed individually and then simultaneously with a multiple-regression model. Patients with radicular symptoms and signs had the best pain relief in contradistinction to those with axial (neck) pain. A clinical classification model predicting the outcome and an algorithm for the use of such injections in the treatment of cervical radiculopathy were developed.

Adult↗

PubMed2002

Prediction of response to hormonal treatment in metastatic breast cancer.

Prediction of outcome and individualization of therapeutic strategies are challenging problems in oncology. Predictive parameters for response to hormonal treatment include the expression of hormone receptor, the extent and location of metastatic spread, disease-free interval, patient age, response to prior hormonal therapy, grading, and more recently, some molecular markers like the expression of HER-2/neu. The use of conventional statistics for prediction of response to hormonal treatment is limited by non-linearities and complex interactions between predictive factors. Modern computational mathematical models like artificial neural networks, entropy-based inductive algorithms or chi(2) interaction detection algorithms can describe these interactions and generate classification models and decision structures. They can be used to predict the clinical outcome for individual patients. In contrast to conventional methods, the level of confidence for the predictions can reach 90% and more. This might be an important step towards further individualization of therapeutic strategies.

Antineoplastic Agents, Hormonal↗

PubMed2000

[Study on statistical method of distribution for erythrocyte morphological features by computerized image processing].

This study sought to develop a new statistic method for the semiautomatic analysis and classification of erythrocyte morphology based on the morphological features and shape analysis of erythrocytes by computer image processing. Shape factor as the description of the erythrocyte morphological features was used for the shape classification of erythrocytes. And the models and algorithms of erythrocytes image segmentation, cell body shape recognition and measure can be implemented through the VC++. The present method can efficiently and semi-automatically provide the statistical analysis of erythrocyte morphology, and can give the distribution of erythrocyte morphological features. The result showed that there was a significant difference between the distribution curves of the normal erythrocyte morphology (one apex) and hemolytic anemia's (two apices). By this way, it can be obtained the proportion data of different cell bodies' shapes. This method could provide some information for the study and diagnosis of the diseases (e.g. hemolytic anemia, pre-leukemia) related to erythrocyte morphology.

Algorithms↗

PubMedDate not supplied

[Surgical strategy of treatment of severe and extremely severe eye burns. I].

A total of 112 patients with severe and extremely severe burns of the eyes were treated. The author proves that one of the main causes of unsatisfactory results is the absence of clearly defined criteria for the choice of surgical strategy during the early period. Based on the classification of interventions, the author suggests an algorithm of early surgical treatment of eye burns.

Corneal Transplantation↗