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 793 records · Page 44Linked to original sources

PubMedDate not supplied

RECPAM: a computer program for recursive partition and amalgamation for censored survival data and other situations frequently occurring in biostatistics. I. Methods and program features.

The methodology of recursive partition and amalgamation in biostatistics is presented and a FORTRAN program for its implementation, RECPAM, is described. RECPAM can be used to obtain classifications of patients according to several criteria commonly occurring in clinical biostatistics: an example is prognostic classification based on survival data. Classes are defined by simple statements, expressed in clinical terms, about predictor variables (e.g. prognostic factors). Special features of RECPAM are: the possibility of implementing a variety of classification criteria, the integration of recursive partition and amalgamation, and the availability of several strategies for constructing classification trees. A simple example to illustrate input and output features is given. The scope and flexibility of RECPAM will be illustrated in greater detail in a subsequent paper.

Algorithms↗

PubMed2005

Biochemical clustering of monomeric GTPases of the Ras superfamily.

To date phylogeny has been used to compare entire families of proteins based on their nucleotide or amino acid sequence. Here we developed a novel analytical platform allowing a systematic comparison of protein families based on their biochemical properties. This approach was validated on the Rho subfamily of GTPases. We used two high throughput methods, referred to as AlphaScreen and FlashPlate, to measure nucleotide binding capacity, exchange, and hydrolysis activities of small monomeric GTPases. These two technologies have the characteristics to be very sensitive and to allow homogenous and high throughput assays. To analyze and integrate the data obtained, we developed an algorithm that allows the classification of GTPases according to their enzymatic activities. Integration and hierarchical clustering of these results revealed unexpected features of the small Rho GTPases when compared with primary sequence-based trees. Hence we propose a novel phylobiochemical classification of the Ras superfamily of GTPases.

Algorithms↗

PubMed2002

Chemically-assigned classification of aerosol mass spectra.

An Algorithm for Discriminant Analysis of Mass Spectra--ADAMS--was created that classified aerosol mass spectra into dominant chemically-assigned classes, and grouped rare cases in an outlier class. ADAMS was trained with ambient particulate matter (PM) mass spectra, and then validated through classification tests on known spectra with random noise added, various standard chemicals, and salt-spiked polystyrene latex microspheres. The classification results showed that ADAMS gave a reasonable chemical description of the particle populations. In contrast to adaptive resonance theory (ART-2a) classification, ADAMS could be trained to be advantageously sensitive or insensitive to selected chemical markers. Application of ADAMS to Toronto ambient PM and diesel PM (NIST 2975) demonstrated that these samples could be well described, with a low proportion of the cases falling into the outlier class. Such an algorithm may find application for source-receptor modeling of aerosol mass spectra.

Journal Article↗

PubMed2001

Do current dual chamber cardioverter defibrillators have advantages over conventional single chamber cardioverter defibrillators in reducing inappropriate therapies? A randomized, prospective study.

INTRODUCTION: Supraventricular tachyarrhythmias are the main cause of inappropriate therapies in patients with conventional single chamber implantable cardioverter defibrillators (VVI-ICD). It was anticipated that dual chamber cardioverter defibrillators (DDD-ICD), with their capacity to analyze atrial and ventricular rhythm, could substantially reduce inappropriate therapies. METHODS AND RESULTS: Our prospective study included 92 patients (87 men; mean age 61 +/- 12.7 years) who were randomly assigned to a VVI-ICD (45 patients) or a DDD-ICD (47 patients). Both groups were followed for 7.5 +/- 3.5 and 7.6 +/- 4.1 months, respectively. During the follow-up period, overall 725 ventricular tachycardia (VT)/ventricular fibrillation (VF) episodes were recorded in 45 (49%) of 92 patients. Of these episodes, 404 (56%) occurred in the VVI-ICD group and 321 (44%) episodes occurred in the DDD-ICD group. Twenty-three (51%) patients in the VVI-ICD group and 22 (47%) patients in the DDD-ICD group (P = 0.8) developed VT/VF. Overall, 73 (10%) of 725 treated episodes were inappropriate in 6 (13%) patients in the VVI group and in 10 (21%) patients in the DDD-ICD group (P = 0.2). There were 22 (31%) inappropriately treated episodes in the VVI-ICD group and 51 (69%) in the DDD-ICD group. Thirty-two of the 51 inappropriate episodes in the DDD-ICD patients resulted from intermittent atrial sensing problems that led to failure of the respective dual chamber algorithms. Nonfatal complications occurred in 6 (13%) patients in the VVI-ICD group and in 3 (6%) patients in the DDD-ICD group (P = 0.7). CONCLUSION: We conclude that the implanted DDD-ICD and conventional VVI-ICD are equally safe and effective for therapy of life-threatening ventricular tachyarrhythmias. Although DDD-ICDs allow better rhythm classification, the applied detection algorithms do not offer benefits in avoiding inappropriate therapies during supraventricular tachyarrhythmias.

Aged↗

PubMed1986

An algorithm for differential diagnosis in jaundice and its applications.

During the recent years a broad spectrum of diagnostic methods have appeared for the differentiation of obstructive and nonobstructive jaundice: ultrasound examination, CT-scan, direct cholangiography, etc. These investigations are costly and not without risks. It is therefore essential to devise an optimal diagnostic strategy for each patient. Extensive clinical and clinical chemical information was collected from 1,002 jaundiced patients. By application of Bayes' theorem and logistic discriminant analysis a diagnostic algorithm was developed based upon 21 variables of the 107 variables collected. This algorithm permitted a probabilistic classification of jaundiced patients into four diagnostic categories: acute non-obstructive, chronic non-obstructive, benign obstructive and malignant obstructive jaundice. Adopting a probability limit of 0.80, 683 patients (69 p. 100) were correctly classified, 34 patients (3.5 p. 100) were wrongly so, and 268 patients (27 p. 100) could not be classified with a probability above 0.80 (doubtful cases). The algorithm was also tested in a further series of 110 jaundiced patients and found to perform equally well: 88 patients classified, 22 patients remaining doubtful. Patients with doubtful diagnoses should be referred to a non-invasive test such as ultrasound examination, whereas patients with definite diagnoses can be referred to invasive tests (liver biopsy, direct cholangiography) as appropriate. The diagnostic algorithm seems to be a reliable tool for the primary differential diagnosis of the jaundiced patient and can be used in the planning of further diagnostic tests for the individual patient.

Algorithms↗

PubMed1997

A hybrid classifier for remote sensing applications.

This paper presents a hybrid-unsupervised and supervised-classifier for land use classification of remote sensing images. The entire satellite image is quantized by an unsupervised Neural Gas process and the resulting codebook is labeled by a supervised majority voting process using the ground truth. The performance of the classifier is similar to that of Maximum Likelihood and is only a little worse than Multilayer Perceptions while training and classifying requires no expert knowledge after collecting the ground truth. The hybrid classifier is much better suited to classifications with complex non-normally distributed classes than Maximum Likelihood. The main advantage of the Neural Gas classifier, however, is that it requires much less user interaction than other classifiers, especially Maximum Likelihood.

Algorithms↗

PubMed1998

Automated feature extraction and identification of colon carcinoma.

OBJECTIVE: To assess an automated algorithm, developed for the classification of normal and cancerous colonic mucosa, using geometric analysis of features and texture analysis. STUDY DESIGN: Twenty-one images were analyzed, 10 from normal and 11 from cancerous mucosa. The classification was based on a regularity index dependent on shape, object orientation for establishing parallelism and five texture features derived using the co-occurrence image analysis method. RESULTS: Geometric analysis yielded an overall classification accuracy of 80%. The corresponding sensitivity and specificity were 94% and 64%, respectively. Using texture analysis, the overall classification accuracy was 90%, with a sensitivity and specificity of 82% and 100%, respectively. CONCLUSION: This initial study demonstrated that geometric and texture analysis techniques show promise for automated analysis of colon cancer.

Algorithms↗

PubMedDate not supplied

Where to be born? A normative approach of life duration inequalities in the world.

The following study attempts to demonstrate that traditional classifications of OECD countries according to the health condition of their citizens, based on classifications of life expectancy and infant mortality, can lead to substantial normative errors if we assume that economic agents are rational. In particular, classifications of life expectancy and infant mortality can cause a great deal of information loss, and do not allow a precise idea of typical inequalities in certain countries. This study begins with Meyer's method of classification--which allows us to organise different distributions on the basis of risk aversion of agents. This means that countries can be classified as offering a distribution superior to others in regards to the life duration they offer their citizens.

Aged↗

PubMed2003

Guidelines for case classification for the National Birth Defects Prevention Study.

BACKGROUND: Previous studies have suggested that etiologic heterogeneity may complicate epidemiologic analyses designed to identify risk factors for birth defects. Case classification uses knowledge of embryologic and pathogenetic mechanisms to make case groups more homogeneous and is important to the success of birth defects studies. METHODS: The goal of the National Birth Defects Prevention Study (NBDPS), an ongoing multi-site case-control study, is to identify environmental and genetic risk factors for birth defects. Information on environmental risk factors is collected through an hour-long maternal interview, and DNA is collected from the infant and both parents for evaluation of genetic risk factors. Clinical data on infants are reviewed by clinical geneticists to ensure they meet the detailed case definitions developed specifically for the study. To standardize the methods of case classification for the study, an algorithm has been developed to guide NBDPS clinical geneticists in this process. RESULTS: Methods for case classification into isolated, multiple, and syndrome categories are described. Defects considered minor for the purposes of case classification are defined. Differences in the approach to case classification for studies of specific defects and of specific exposures are noted. CONCLUSIONS: The case classification schema developed for the NBDPS may be of value to other clinicians working on epidemiologic studies of birth defects etiology. Consideration of these guidelines will lead to more comparable case groups, an important element of careful studies aimed at identifying risk factors for birth defects.

Adult↗

PubMed2004

Visualizations for taxonomic and phylogenetic trees.

MOTIVATION: Despite substantial efforts to develop and populate the back-ends of biological databases, front-ends to these systems often rely on taxonomic expertise. This research applies techniques from human-computer interaction research to the biodiversity domain. RESULTS: We developed an interactive node-link tool, TaxonTree, illustrating the value of a carefully designed interaction model, animation, and integrated searching and browsing towards retrieval of biological names and other information. Users tested the tool using a new, large integrated dataset of animal names with phylogenetic-based and classification-based tree structures. These techniques also translated well for a tool, DoubleTree, to allow comparison of trees using coupled interaction. Our approaches will be useful not only for biological data but as general portal interfaces.

Algorithms↗

PubMed2006

Prognostic groups in colorectal carcinoma patients based on tumor cell proliferation and classification and regression tree (CART) survival analysis.

BACKGROUND: In this study, an alternative analytical method was used to model colorectal cancer (CRC) patients' long-term survival by assessing the prognostic value of the Ki-67 protein as a marker of tumor cell proliferation, and to illustrate the interaction between standard clinicopathologic variables and the proliferation marker in relation to their impact on survival. METHODS: A cohort of 106 surgically treated CRC patients was used for analysis. The expression of the cell-cycle-related Ki-67 protein in tumor samples was evaluated by immunohistochemistry. A score was assigned as the percentage of positive tumor cell staining, denoted as proliferation index (PI), and was used in a multivariate analysis using a recursive partitioning algorithm referred to as classification and regression tree (CART) to characterize the long-term survival after surgery. RESULTS: Of the covariates selected for their prognostic value, PI contributed most to the classification of survival status of patients. However, CART analysis selected the presence of distant metastasis as the best first split-up factor for predicting 5-year survival. CART then selected the following covariates for building up subgroups at risk for death: (1) PI; (2) pathological lymph node metastasis; (3) tumor size. Seven terminal subgroups were formed, with an overall misclassification rate of 16%. CONCLUSIONS: These analyses demonstrated that a Ki-67-protein-based tumor proliferation index appeared as an independent prognostic variable that was consistently applied by the CART algorithm to classify patients into groups with similar clinical features and survival.

Adult↗

PubMed1997

Frontal basilar trauma: classification and treatment.

We report our experience with 14 consecutive cases of frontal basilar trauma occurring in children and adolescents aged 18 months to 18 years (mean 9.5 years). Brain parenchymal injury resulting in functional deficit occurred in 5 patients (36 percent), 2 patients suffered bilateral blindness, and 1 suffered unilateral loss of vision. A classification system and treatment algorithm based on the clinical fracture pattern seen by computed tomography are introduced. Type I, central, is confined to the upper nasoethmoidal complex, central frontal bone, and medial third of the superior orbital rims. Type II, unilateral, involves the entire supraorbital rim and the upper lateral orbital wall, extending into the squamosa of the temporal bone and ipsilateral frontal bone. Type III, bilateral, involves fractures of the upper nasal ethmoidal complex, bilateral supraorbital and upper lateral orbital wall fractures, and bilateral frontal bone fractures. This classification was utilized to plan elective orbital and cranial osteotomies, similar to those used for frontal orbital advancement at the time of acute fracture repair. Frontal orbital osteotomies were used to access the anterior cranial fossa, orbital apices, and nasofrontal ducts and to obtain an intact bony template for side-table reassembly of the fracture fragments. There was no significant operative morbidity, one late cerebrospinal fluid leak, and no infections. Reoperation was necessary in four patients (29 percent) for aesthetic indications.

Adolescent↗

PubMed2006

Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma.

The degree of malignancy in brain glioma is assessed based on magnetic resonance imaging (MRI) findings and clinical data before operation. These data contain irrelevant features, while uncertainties and missing values also exist. Rough set theory can deal with vagueness and uncertainty in data analysis, and can efficiently remove redundant information. In this paper, a rough set method is applied to predict the degree of malignancy. As feature selection can improve the classification accuracy effectively, rough set feature selection algorithms are employed to select features. The selected feature subsets are used to generate decision rules for the classification task. A rough set attribute reduction algorithm that employs a search method based on particle swarm optimization (PSO) is proposed in this paper and compared with other rough set reduction algorithms. Experimental results show that reducts found by the proposed algorithm are more efficient and can generate decision rules with better classification performance. The rough set rule-based method can achieve higher classification accuracy than other intelligent analysis methods such as neural networks, decision trees and a fuzzy rule extraction algorithm based on Fuzzy Min-Max Neural Networks (FRE-FMMNN). Moreover, the decision rules induced by rough set rule induction algorithm can reveal regular and interpretable patterns of the relations between glioma MRI features and the degree of malignancy, which are helpful for medical experts.

Adolescent↗

PubMed1993

The logic of imaging in spine surgery.

Spinal imaging has rapidly evolved into a complex diagnostic field requiring specialized expertise. While many imaging modalities reveal portions of a topographic map of the spine necessary for surgery, only magnetic resonance imaging emerges as the imaging modality of widest and most efficacious first choice. With the increasing high-technology sophistication of modern imaging modalities, the spine surgeon must become completely conversant with the radiologic data produced by these imaging techniques. The authors present a logical approach to spinal imaging--an algorithm--based on etiologic classification and aimed at conserving medical resources and developing an optimal diagnostic pathway for spine injury and disease. Spine surgeons are urged to incorporate the interpretative insights of radiologists into the diagnostic process.

Algorithms↗

PubMed1992

Recognition of multiunit neural signals.

An essential step in studying nerve cell interaction during information processing is the extracellular microelectrode recording of the electrical activity of groups of adjacent cells. The recording usually contains the superposition of the spike trains produced by a number of neurons in the vicinity of the electrode. It is therefore necessary to correctly classify the signals generated by these different neurons. This paper considers this problem, and a new classification scheme is developed, which does not require human supervision. A learning stage is first applied on the beginning portion of the recording to estimate the typical spike shapes of the different neurons. As for the classification stage, a method is developed, which specifically considers the case when spikes overlap temporally. The method minimizes the probability of error, taking into account the statistical properties of the discharges of the neurons. The method is tested on a real recording as well as on synthetic data.

Action Potentials↗

PubMed2005

A sequence sub-sampling algorithm increases the power to detect distant homologues.

Searching databases for distant homologues using alignments instead of individual sequences increases the power of detection. However, most methods assume that protein evolution proceeds in a regular fashion, with the inferred tree of sequences providing a good estimation of the evolutionary process. We investigated the combined HMMER search results from random alignment subsets (with three sequences each) drawn from the parent alignment (Rand-shuffle algorithm), using the SCOP structural classification to determine true similarities. At false-positive rates of 5%, the Rand-shuffle algorithm improved HMMER's sensitivity, with a 37.5% greater sensitivity compared with HMMER alone, when easily identified similarities (identifiable by BLAST) were excluded from consideration. An extension of the Rand-shuffle algorithm (Ali-shuffle) weighted towards more informative sequence subsets. This approach improved the performance over HMMER alone and PSI-BLAST, particularly at higher false-positive rates. The improvements in performance of these sequence sub-sampling methods may reflect lower sensitivity to alignment error and irregular evolutionary patterns. The Ali-shuffle and Rand-shuffle sequence homology search programs are available by request from the authors.

Algorithms↗

PubMed2001

Women's readiness to follow milk product consumption recommendations: design and evaluation of a 'stage of change' algorithm.

OBJECTIVE: To investigate readiness to follow milk product consumption recommendations in two random samples of New Zealand women, using an algorithm designed and evaluated to assess the stage of change construct of the Transtheoretical Model. PROTOCOL: Women were classified according to stage of readiness to perform two goal behaviours: consumption of two or four servings of milk products per day. Stage classification, as determined by the algorithm, was evaluated by estimating mean calcium intake in each stage using a validated food frequency questionnaire. This was undertaken in two independent samples of women randomly selected from the electoral rolls of two cities in New Zealand's South Island. RESULTS: Over 60% of women were classified as maintaining an intake of two servings of milk products per day. Of those women not meeting the goal of two servings per day, 73% had no intention of increasing their consumption. Over 80% of women were in the precontemplation stage for consuming four servings of milk products per day. Mean calcium intakes were significantly higher in women classified in action and maintenance stages than in preaction stages of change for both goal behaviours. CONCLUSION: Of those women not currently meeting the recommendation for two servings of milk products per day, most are in precontemplation, a stage characterized by resistance to change. Use of the staging algorithm developed in this study makes possible the classification of women according to their readiness to change, and thus the provision of appropriate stage-tailored advice.

Adult↗

PubMed1999

Blocks+: a non-redundant database of protein alignment blocks derived from multiple compilations.

MOTIVATION: As databanks grow, sequence classification and prediction of function by searching protein family databases becomes increasingly valuable. The original Blocks Database, which contains ungapped multiple alignments for families documented in Prosite, can be searched to classify new sequences. However, Prosite is incomplete, and families from other databases are now available to expand coverage of the Blocks Database. RESULTS: To take advantage of protein family information present in several existing compilations, we have used five databases to construct Blocks+, a unified database that is built on the PROTOMAT/BLOSUM scoring model and that can be searched using a single algorithm for consistent sequence classification. The LAMA blocks-versus-blocks searching program identifies overlapping protein families, making possible a non-redundant hierarchical compilation. Blocks+ consists of all blocks derived from PROSITE, blocks from Prints not present in PROSITE, blocks from Pfam-A not present in PROSITE or Prints, and so on for ProDom and Domo, for a total of 1995 protein families represented by 8909 blocks, doubling the coverage of the original Blocks Database. A challenge for any procedure aimed at non-redundancy is to retain related but distinct families while discarding those that are duplicates. We illustrate how using multiple compilations can minimize this potential problem by examining the SNF2 family of ATPases, which is detectably similar to distinct families of helicases and ATPases. AVAILABILITY: http://blocks.fhcrc.org/

Adenosine Triphosphatases↗