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 415 records · Page 23Linked to original sources
PubMed2005

A soft decision algorithm for obstructive sleep apnea patient classification based on fast estimation of wavelet entropy of RRI data.

A soft decision algorithm for Obstructive Sleep Apnea (OSA) patient classification using R-R interval (RRI) data is investigated. This algorithm is based on fast and approximate estimation of the entropy of the wavelet-decomposed bands of the RRI data. The classification is done on the whole record as OSA patient or non-patient (normal). The ratio of the estimated entropy of the low-frequency (LF) band to that of the very-low frequency (VLF) band is used as a classification factor. RRI data used in this work are drawn from MIT database. The MIT trial records are used to set the threshold value of the classification factor using the Receiver Operating Characteristics (ROC). This threshold value is used then to classify the MIT challenge (test) records to obtain the efficiency of classification. The new algorithm classifies correctly 30/30 of MIT-test data using different wavelet filters. Comparison of the results of different wavelet filters is done in terms of complexity and distance parameters. The method is also compared with other two techniques using wavelets in their analysis. The consistency of the results is examined using the leave-one-out technique.

Adult↗
PubMed2004

Tolerance to missing data using a likelihood ratio based classifier for computer-aided classification of breast cancer.

While mammography is a highly sensitive method for detecting breast tumours, its ability to differentiate between malignant and benign lesions is low, which may result in as many as 70% of unnecessary biopsies. The purpose of this study was to develop a highly specific computer-aided diagnosis algorithm to improve classification of mammographic masses. A classifier based on the likelihood ratio was developed to accommodate cases with missing data. Data for development included 671 biopsy cases (245 malignant), with biopsy-proved outcome. Sixteen features based on the BI-RADS lexicon and patient history had been recorded for the cases, with 1.3 +/- 1.1 missing feature values per case. Classifier evaluation methods included receiver operating characteristic and leave-one-out bootstrap sampling. The classifier achieved 32% specificity at 100% sensitivity on the 671 cases with 16 features that had missing values. Utilizing just the seven features present for all cases resulted in decreased performance at 100% sensitivity with average 19% specificity. No cases and no feature data were omitted during classifier development, showing that it is more beneficial to utilize cases with missing values than to discard incomplete cases that cannot be handled by many algorithms. Classification of mammographic masses was commendable at high sensitivity levels, indicating that benign cases could be potentially spared from biopsy.

Algorithms↗
PubMed1994

Classification of diagnostic tests.

A method is described for classifying diagnostic tests. It is valid for the large subgroup of tests for which the measured diagnostic variable has a normal distribution for the affected and non-affected individuals. It is based on placing each diagnostic test as a point on a two-dimensional graph, called a separation-asymmetry (SA) diagram, whose x-axis is the separation between the two normal distributions and whose y-axis is the logarithm of the ratio of their standard deviations. The SA diagram is partitioned into functional regions by curves of constant performance, as measured by the percent overlap between the two normal distributions. The concept of 'eccentricity' in a diagnostic test is defined, and the relationship between eccentricity and test validity is discussed. This quantity is also incorporated into SA diagrams, thus allowing a clinician to determine, by inspection, if a given diagnostic test positioned on an SA diagram is valid for clinical use. The logic engine used for calculating iso-performance curves is given, as well as the computer programs which utilize it. Possible ways of using this classification scheme are suggested.

Algorithms↗
PubMed1998

An algorithm for automatic segmentation and classification of magnetic resonance brain images.

In this article, we describe the development and validation of an automatic algorithm to segment brain from extracranial tissues, and to classify intracranial tissues as cerebrospinal fluid (CSF), gray matter (GM), white matter (WM) or pathology. T1 weighted spin echo, dual echo fast spin echo (T2 weighted and proton density (PD) weighted images) and fast Fluid Attenuated Inversion Recovery (FLAIR) magnetic resonance (MR) images were acquired in 100 normal patients and 9 multiple sclerosis (MS) patients. One of the normal studies had synthesized MS-like lesions superimposed. This allowed precise measurement of the accuracy of the classification. The 9 MS patients were imaged twice in one week. The algorithm was applied to these data sets to measure reproducibility. The accuracy was measured based on the synthetic lesion images, where the true voxel class was known. Ninety-six percent of normal intradural tissue voxels (GM, WM, and CSF) were labeled correctly, and 94% of pathological tissues were labeled correctly. A low coefficient of variation (COV) was found (mean, 4.1%) for measurement of brain tissues and pathology when comparing MRI scans on the 9 patients. A totally automatic segmentation algorithm has been described which accurately and reproducibly segments and classifies intradural tissues based on both synthetic and actual images.

Algorithms↗
PubMedDate not supplied

Classification of some active HIV-1 protease inhibitors and their inactive analogues using some uncorrelated three-dimensional molecular descriptors and a fuzzy c-means algorithm.

A fuzzy c-means algorithm was used to classify some 3D convex hull descriptors computed for 345 active HIV-1 protease inhibitors collected from literature and 437 inactive analogues searched from the MDL/ISIS database. The number of descriptors used to represent each compound was from 4 to 8, and they were uncorrelated using the principal component analysis. These uncorrelated descriptors were then divided into two groups and classified by the fuzzy c-means algorithm. The classification produced a clear-cut switch in membership functions computed for each uncorrelated descriptor at the group boundary. Compounds with nonswitching membership functions computed were treated as outliers, and they were counted for estimating the accuracy of the classification. The averaged accuracy of classification for the active inhibitor set was about 80% which was better than that directly classified by a linear discriminant function on the original 3D convex hull descriptors. The whole classification scheme was also applied to several sets of some conventional descriptors computed for each compound, but the averaged accuracy was around 58%. Further classification using some 3D convex hull descriptors searched from comparing the distribution of these descriptors was performed on a new data set composed of 289 outliers-deducted active inhibitors and 63 outliers identified from the inactive analogues through previous classification. This final classification identified 19 inactive analogues which were similar in structural and topological features to those of some highly active inhibitors classified together with them.

Algorithms↗
PubMed2001

Feedforward neural network construction using cross validation.

This article presents an algorithm that constructs feedforward neural networks with a single hidden layer for pattern classification. The algorithm starts with a small number of hidden units in the network and adds more hidden units as needed to improve the network's predictive accuracy. To determine when to stop adding new hidden units, the algorithm makes use of a subset of the available training samples for cross validation. New hidden units are added to the network only if they improve the classification accuracy of the network on the training samples and on the cross-validation samples. Extensive experimental results show that the algorithm is effective in obtaining networks with predictive accuracy rates that are better than those obtained by state-of-the-art decision tree methods.

Algorithms↗
PubMed2006

[Study on the application of classification tree model in screening the risk factors of malignant tumor].

OBJECTIVE: To introduce the partitioning algorithm of classification tree model, and to explore the value of this data mining technique applied in data analysis of multifactorial diseases as malignant tumors. METHODS: Data was analyzed from a survey that conducted on 84 breast cancer patients and 273 cancer-free controls selected randomly in Jiashan county. The classification tree model was constructed using Exhaustive CHAID method and evaluated by the Risk statistics and the area under the ROC curve. RESULTS: 9 out of 105 effect risks factors were selected, in which career was the most important factor indicating that workers, teachers and retirees suffered much more risks than others. Nevertheless, the number of pregnancies, breast examination, reasons for menopause, age at menarche, intake of shrimp, crab, kipper, kelp and laver etc were also risk factors on breast cancer. However, physical exercise played different roles on different people. The Risk statistics of model was 0.174, and the area under the ROC curve was 0.872 which was significantly different from 0.5, suggesting that the classification tree model fit the actuality very well. CONCLUSION: The classification tree model could screen out the major affecting factors quickly and effectively and could also identify the cutting-points for continuous and ordinal variables, as well as revealing the complex interaction among the factors at many levels. This model might become a powerful tool to explore the complexities of the risks on diseases.

Algorithms↗
PubMed2000

Adaptive, template moderated, spatially varying statistical classification.

A novel image segmentation algorithm was developed to allow the automatic segmentation of both normal and abnormal anatomy from medical images. The new algorithm is a form of spatially varying statistical classification, in which an explicit anatomical template is used to moderate the segmentation obtained by statistical classification. The algorithm consists of an iterated sequence of spatially varying classification and nonlinear registration, which forms an adaptive, template moderated (ATM), spatially varying statistical classification (SVC). Classification methods and nonlinear registration methods are often complementary, both in the tasks where they succeed and in the tasks where they fail. By integrating these approaches the new algorithm avoids many of the disadvantages of each approach alone while exploiting the combination. The ATM SVC algorithm was applied to several segmentation problems, involving different image contrast mechanisms and different locations in the body. Segmentation and validation experiments were carried out for problems involving the quantification of normal anatomy (MRI of brains of neonates) and pathology of various types (MRI of patients with multiple sclerosis, MRI of patients with brain tumors, MRI of patients with damaged knee cartilage). In each case, the ATM SVC algorithm provided a better segmentation than statistical classification or elastic matching alone.

Algorithms↗
PubMed2000

Prediction of protein structural classes and subcellular locations.

The structural class and subcellular location are the two important features of proteins that are closely related to their biological functions. With the rapid increase in new protein sequences entering into data banks, it is highly desirable to develop a fast and accurate method for predicting the attributes of these features for them. This can expedite the functionality determination of new proteins and the process of prioritizing genes and proteins identified by genomics efforts as potential molecular targets for drug design. Various prediction methods have been developed during the last two decades. This review is devoted to presenting a systematic introduction and comparison of the existing methods in respect to the prediction algorithm and classification scheme. The attention is focused on the state-of-the-art, which is featured by the covarient-discriminant algorithm developed very recently, as well as some new classification schemes for protein structural classes and subcellular locations. Particularly, addressed are also the physical chemistry foundation of the existing prediction methods, and the essence why the covariant-discriminant algorithm is so powerful.

Algorithms↗
PubMed2004

Accurate prediction of solvent accessibility using neural networks-based regression.

Accurate prediction of relative solvent accessibilities (RSAs) of amino acid residues in proteins may be used to facilitate protein structure prediction and functional annotation. Toward that goal we developed a novel method for improved prediction of RSAs. Contrary to other machine learning-based methods from the literature, we do not impose a classification problem with arbitrary boundaries between the classes. Instead, we seek a continuous approximation of the real-value RSA using nonlinear regression, with several feed forward and recurrent neural networks, which are then combined into a consensus predictor. A set of 860 protein structures derived from the PFAM database was used for training, whereas validation of the results was carefully performed on several nonredundant control sets comprising a total of 603 structures derived from new Protein Data Bank structures and had no homology to proteins included in the training. Two classes of alternative predictors were developed for comparison with the regression-based approach: one based on the standard classification approach and the other based on a semicontinuous approximation with the so-called thermometer encoding. Furthermore, a weighted approximation, with errors being scaled by the observed levels of variability in RSA for equivalent residues in families of homologous structures, was applied in order to improve the results. The effects of including evolutionary profiles and the growth of sequence databases were assessed. In accord with the observed levels of variability in RSA for different ranges of RSA values, the regression accuracy is higher for buried than for exposed residues, with overall 15.3-15.8% mean absolute errors and correlation coefficients between the predicted and experimental values of 0.64-0.67 on different control sets. The new method outperforms classification-based algorithms when the real value predictions are projected onto two-class classification problems with several commonly used thresholds to separate exposed and buried residues. For example, classification accuracy of about 77% is consistently achieved on all control sets with a threshold of 25% RSA. A web server that enables RSA prediction using the new method and provides customizable graphical representation of the results is available at http://sable.cchmc.org.

Artificial Intelligence↗
PubMed1993

Comparing wall motion quantification methods by numerical classification.

Quantitative left ventriculography has been studied for many years as a method for assessing left ventricular function. All currently used quantitative left ventriculography methods evaluate functional status based on different assumptions concerning the time course of contraction, shape of the ventricular silhouette, and/or fixed points of reference. Commonly, analyses are performed using only end-diastolic (ED) and end-systolic (ES) frames. However, myocardial infarction manifests itself not only in spatial parameters, e.g., area of affected myocardium, but also in temporal parameters, e.g., deviation from a synchronous contraction during systole. ED/ES comparisons omit information contained in other frames of the cardiac cycle. Therefore, each single method has a limited reliability or usefulness. The present study used several quantitative methods, fitted curvatures, correlation coefficients of the percentage of radial shortening from end diastole to end systole, and Fourier coefficients of the polar coordinates of the endocardial contour points. Features were derived from a sequence of ventriculograms of a whole cardiac cycle from patients with anterior myocardial infarction (AMI group) and without (NV group) to address three major goals: (1) Determine features derived from LV-grams that discriminate between the two patient groups and do so with the highest accuracy, "recognition rate," or lowest error rates; (2) compare the accuracy of features generated by different quantitative methods; and (3) group features generated by the different quantitative methods to achieve higher accuracy. The discriminant capabilities of several feature sets were tested on a patient sample containing 102 patients (63 patients with AMI, 39 patients with no infarction) using numerical classification. The numerical classification had a Supervised Learning design with two cardiologists assigning the patients to the two patient groups. Each quantification method showed a characteristic pattern for detecting pathologic or normal wall motion. Combining features generated by different extraction methods into one feature set improved the correct classification rates.

Algorithms↗
PubMed2006

A survey of methods for classification of gene expression data using evolutionary algorithms.

The rapid increase in the quantity of available biologic data over the last decade, brought about by the introduction of massively parallel methods for gene expression measurements, has highlighted the need for more efficient computational techniques for analysis. This paper reviews the use of evolutionary algorithms (EAs) in connection with classification based on gene expression data matrices. Brief introductions to data classification methods and EAs are given, followed by a survey of studies dealing with the application of evolutionary algorithms to various (cancer related) data sets. The general conclusion, based on the published results surveyed here, is that EAs may constitute an efficient method for optimal gene selection, and can also help in reducing the size (number of features used) of classifiers. In many cases, the classification accuracy obtained using EAs, often in conjunction with other methods, represents a significant improvement over results obtained without the use of EAs. However, long-term, independent clinical follow-up studies will be essential to validate prognostic markers identified by the use of EA-based methods.

Algorithms↗
PubMedDate not supplied

Spline-fitting with a genetic algorithm: a method for developing classification structure-activity relationships.

Classification methods allow for the development of structure-activity relationship models when the target property is categorical rather than continuous. We describe a classification method which fits descriptor splines to activities, with descriptors selected using a genetic algorithm. This method, which we identify as SFGA, is compared to the well-established techniques of recursive partitioning (RP) and soft independent modeling by class analogy (SIMCA) using five series of compounds: cyclooxygenase-2 (COX-2) inhibitors, benzodiazepine receptor (BZR) ligands, estrogen receptor (ER) ligands, dihydrofolate reductase (DHFR) inhibitors, and monoamine oxidase (MAO) inhibitors. Only 1-D and 2-D descriptors were used. Approximately 40% of compounds in each series were assigned to a test set, "cherry-picked" from the complete set such that they lie outside the training set as much as possible. SFGA produced models that were more predictive for all but the DHFR set, for which SIMCA was most predictive. RP gave the least predictive models for all but the MAO set. A similar trend was observed when using training and test sets to which compounds were randomly assigned and when gradually eliminating compounds from the (designed) training set. The stability of models was examined for the random and reduced sets, where stability means that classification statistics and the selected descriptors are similar for models derived from different sets. Here, SIMCA produced the most stable models, followed by SFGA and RP. We show that a consensus approach that combines all three methods outperforms the single best model for all data sets.

Algorithms↗
PubMedDate not supplied

Feature selection for descriptor based classification models. 1. Theory and GA-SEC algorithm.

The paper describes different aspects of classification models based on molecular data sets with the focus on feature selection methods. Especially model quality and avoiding a high variance on unseen data (overfitting) will be discussed with respect to the feature selection problem. We present several standard approaches and modifications of our Genetic Algorithm based on the Shannon Entropy Cliques (GA-SEC) algorithm and the extension for classification problems using boosting.

Journal Article↗
PubMed1990

Segmentation of coronary arteriograms by iterative ternary classification.

A segmentation algorithm for extracting arterial structures in coronary angiograms is presented. The algorithm mimics the process of interactive interpretation in human vision by iteratively implementing a ternary classification and learning process. Two gray-scale thresholds are computed to define three pixel classes: artery, background, and undecided. Then, two new thresholds for undecided pixels are computed using statistics conditioned upon the current classification. The threshold adaptation is governed by a learning algorithm based on the line and consistency measurements around each pixel. The process converges and results in a binary image. The performance of this algorithm on human coronary arteriograms was compared qualitatively to that of a relaxation algorithm and of a scattering based algorithm. Quantitative comparison was also made possible with computer generated images, which were obtained with the help of a model of the imaging chain and a process of interactive visualization of the modeled data. The iterative ternary classifier showed the best performance over a broad range of image quality. The study also demonstrated the use of visualization and user interaction in model building and algorithm development.

Algorithms↗
PubMed1997

Automatic SNOMED classification--a corpus-based method.

This paper presents a method of automatic classification of clinical narrative through text comparison. A diagnosis report can be classified by searching archive texts that show a high textual similarity, and the 'nearest neighbor classifies the case. This paper describes the method's theoretical background and gives implementation details. Large scale simulation experiments were run with a wide range of histology reports. Results showed that for 80-84% of the trials, relevant classification lines were included among the first five alternatives. In 5% of the cases, retrieval was unsuccessful due to the absence of relevant archive reports. From the results it is concluded that the method is a versatile approach for finding potentially good classifications.

Algorithms↗
PubMed2006

Gene selection in cancer classification using sparse logistic regression with Bayesian regularization.

MOTIVATION: Gene selection algorithms for cancer classification, based on the expression of a small number of biomarker genes, have been the subject of considerable research in recent years. Shevade and Keerthi propose a gene selection algorithm based on sparse logistic regression (SLogReg) incorporating a Laplace prior to promote sparsity in the model parameters, and provide a simple but efficient training procedure. The degree of sparsity obtained is determined by the value of a regularization parameter, which must be carefully tuned in order to optimize performance. This normally involves a model selection stage, based on a computationally intensive search for the minimizer of the cross-validation error. In this paper, we demonstrate that a simple Bayesian approach can be taken to eliminate this regularization parameter entirely, by integrating it out analytically using an uninformative Jeffrey's prior. The improved algorithm (BLogReg) is then typically two or three orders of magnitude faster than the original algorithm, as there is no longer a need for a model selection step. The BLogReg algorithm is also free from selection bias in performance estimation, a common pitfall in the application of machine learning algorithms in cancer classification. RESULTS: The SLogReg, BLogReg and Relevance Vector Machine (RVM) gene selection algorithms are evaluated over the well-studied colon cancer and leukaemia benchmark datasets. The leave-one-out estimates of the probability of test error and cross-entropy of the BLogReg and SLogReg algorithms are very similar, however the BlogReg algorithm is found to be considerably faster than the original SLogReg algorithm. Using nested cross-validation to avoid selection bias, performance estimation for SLogReg on the leukaemia dataset takes almost 48 h, whereas the corresponding result for BLogReg is obtained in only 1 min 24 s, making BLogReg by far the more practical algorithm. BLogReg also demonstrates better estimates of conditional probability than the RVM, which are of great importance in medical applications, with similar computational expense. AVAILABILITY: A MATLAB implementation of the sparse logistic regression algorithm with Bayesian regularization (BLogReg) is available from http://theoval.cmp.uea.ac.uk/~gcc/cbl/blogreg/

Algorithms↗
PubMed2002

Identifying sources of variability in scoliosis classification using a rule-based automated algorithm.

STUDY DESIGN: Use of a rule-based automated algorithm to determine sources of variability in radiographic classification. OBJECTIVES: To determine whether unambiguous rules encoded in a computer program would ensure reliable classification. SUMMARY OF BACKGROUND DATA: Reliability problems have been identified in classifications used in surgical planning for patients with thoracic idiopathic scoliosis, but the sources of unreliability are not understood. METHODS: Objective classification methodology was tested on the King et al (1983) scheme. There were two novel components: 1) positions of the corners of vertebrae in radiographs were digitized relative to a defined axis system and used in automated evaluation of spinal shape parameters required for classification; and 2) the assignment of a classification was done with a rule-based algorithm. The algorithm was implemented after some ambiguities and absence of precise definitions in the King et al classification scheme had been resolved. The algorithm was tested with radiographs of patients having adolescent idiopathic scoliosis. RESULTS: The automated procedure could encounter reliability problems in cases in which a lumbar curve was very close to crossing the midline, thoracic and lumbar curves were of approximately equal value, when the apex level in the thoracolumbar region was ambiguous, when a Cobb angle was close to 10 degrees, or when the flexibility index was close to unity. CONCLUSION: Objective measurements and rule-based algorithms can eliminate some sources of interobserver and intraobserver errors in classification of spinal deformity. When classification parameters fall close to the boundaries for classification, reliability problems will persist.

Algorithms↗