PubMed Health⌕ Search

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 973 records · Page 54Linked to original sources

Resolution of multiple green fluorescent protein color variants and dyes using two-photon microscopy and imaging spectroscopy.

The imaging of living cells and tissues using laser-scanning microscopy is offering dramatic insights into the spatial and temporal controls of biological processes. The availability of genetically encoded labels such as green fluorescent protein (GFP) offers unique opportunities by which to trace cell movements, cell signaling or gene expression dynamically in developing embryos. Two-photon laser scanning microscopy (TPLSM) is ideally suited to imaging cells in vivo due to its deeper tissue penetration and reduced phototoxicity; however, in TPLSM the excitation and emission spectra of GFP and its color variants [e.g., CyanFP (CFP); yellowFP (YFP)] are insufficiently distinct to be uniquely imaged by conventional means. To surmount such difficulties, we have combined the technologies of TPLSM and imaging spectroscopy to unambiguously identify CFP, GFP, YFP, and redFP (RFP) as well as conventional dyes, and have tested the approach in cell lines. In our approach, a liquid crystal tunable filter was used to collect the emission spectrum of each pixel within the TPLSM image. Based on the fluorescent emission spectra, supervised classification and linear unmixing analysis algorithms were used to identify the nature and relative amounts of the fluorescent proteins expressed in the cells. In a most extreme case, we have used the approach to separate GFP and fluorescein, separated by only 7 nm, and appear somewhat indistinguishable by conventional techniques. This approach offers the needed ability to concurrently image multiple colored, spectrally overlapping marker proteins within living cells.

Algorithms↗

Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification.

This paper presents segmentation and classification results of an automated algorithm for the detection of breast masses on digitized mammograms. Potential mass regions were first identified using density-weighted contrast enhancement (DWCE) segmentation applied to single-view mammograms. Once the potential mass regions had been identified, multiresolution texture features extracted from wavelet coefficients were calculated, and linear discriminant analysis (LDA) was used to classify the regions as breast masses or normal tissue. In this article the overall detection results for two independent sets of 84 mammograms used alternately for training and test were evaluated by free-response receiver operating characteristics (FROC) analysis. The test results indicate that this new algorithm produced approximately 4.4 false positive per image at a true positive detection rate of 90% and 2.3 false positives per image at a true positive rate of 80%.

Automation↗

Clinically silent electrocardiographic abnormalities and risk of primary cardiac arrest among hypertensive patients.

BACKGROUND: Whether continuous ECG indexes that reflect the severity of left ventricular hypertrophy (LVHI), myocardial injury (CIIS), and QT-interval prolongation (QTI) are associated with the risk of primary cardiac arrest among hypertensive patients, independent of conventional binary ECG criteria, remains unknown. METHODS AND RESULTS: We conducted a population-based case-control study among patients who were free of clinically recognized heart disease and who received care at a health maintenance organization. Cases (n = 131) were treated hypertensive patients who had had a primary cardiac arrest between 1977 and 1990. Controls (n = 562) were a stratified random sample of treated hypertensive patients. Resting ECGs were reviewed to estimate the severity of left ventricular hypertrophy, myocardial injury, and QT-interval prolongation on the basis of the algorithms of the Novacode ECG classification system. After adjustment for other risk factors and binary ECG criteria for the abnormalities, the LVHI, CIIS, and QTI scores were directly related to the risk of primary cardiac arrest. In a comparison of the 80th with the 20th percentile score for the LVHI, the risk was increased 40% (odds ratio, 1.4; 95% CI, 1.0 to 2.0); for the CIIS, the risk was increased 70% (odds ratio, 1.7; 95% CI, 1.2 to 2.5); and for the QTI, the risk was increased 80% (odds ratio, 1.8; 95% CI, 1.3 to 2.7). CONCLUSIONS: Our findings suggest that continuous ECG indexes that reflect left ventricular hypertrophy, myocardial injury, and QT-interval prolongation are directly related to the risk of primary cardiac arrest among hypertensive patients without clinically recognized heart disease. Binary ECG criteria may underestimate the prognostic importance of these pathophysiological abnormalities.

Adult↗

Finding the most powerful measures of the effectiveness of tissue plasminogen activator in the NINDS tPA stroke trial.

BACKGROUND AND PURPOSE: We sought to identify the most powerful binary measures of the treatment effect of tissue plasminogen activator (tPA) in the National Institute of Neurological Disorders and Stroke (NINDS) rTPA Stroke Trial. METHODS: Using the Classification and Regression Tree (CART) algorithm, we evaluated binary cut points and combination of binary cut points with the 4 clinical scales and head CT imaging measures in the NINDS tPA Stroke Trial at 4 times after treatment: 2 hours, 24 hours, 7 to 10 days, and 3 months. The first analysis focused on detecting evidence of "early activity" of tPA with the use of outcome measures derived from the 2-hour and 24-hour clinical and radiographic measures. The second analysis focused on longer-term outcome and "efficacy" and used outcome measures derived from 7- to 10-day and 3-month measures. After identifying the cut points with the ability to classify patients into the tPA and placebo groups using part I data from the trial, we then used data from part II of the trial to validate the results. RESULTS: Of the 5 most powerful outcome measures for early activity of tPA, 4 involved the National Institutes of Health Stroke Scale (NIHSS) score at 24 hours or changes in the NIHSS score from baseline to 24 hours. The best overall single outcome measure was an NIHSS score </=2 at 24 hours, which provided an odds ratio of 5.4 (95% CI, 2.4 to 12.1) and a projected sample size of 58 per treatment group assuming an alpha of 0.05 (2-sided test) and a power of 80% using part I data. The top 2 and 3 of the top 5 outcome measures for detecting the longer-term efficacy of tPA also involved the NIHSS score. A Rankin score of 0 or 1 at 3 months was the third most powerful outcome measure. Outcome measures identified by CART from part I data were not as sensitive in detecting the effectiveness of tPA when applied to part II data. CONCLUSIONS: Measures using the NIHSS and a Rankin score </=1 were the most sensitive discriminators of the effectiveness of tPA in the NINDS tPA Stroke Trial compared with the other clinical and radiological measures. The outcome measures identified in this exploratory analysis (eg, NIHSS score </=2 at 24 hours) would be best used as an outcome measure in future phase II trials of recanalization begun within the first 3 hours after stroke onset, with inclusion and exclusion criteria similar to those in the NINDS tPA Stroke Trial.

Algorithms↗

Comparative genomic analysis of the eight-membered ring cystine knot-containing bone morphogenetic protein antagonists.

TGF-beta family proteins with a cystine knot motif serve as ligands for diverse families of plasma membrane receptors. Bone morphogenetic protein (BMP) antagonists represent a subgroup of these proteins, some of which bind BMPs and antagonize their actions during development and morphogenesis. Availability of completed genome sequences from diverse organisms allows bioinformatic analysis of the evolution of BMP antagonists and facilitates their classification. Using a regular expression algorithm (http://BioRegEx.stanford.edu), an exhaustive search of the human genome identified all cystine knot-containing BMP antagonists. Based on the size of the cystine ring, these proteins were divided into three subfamilies: CAN (eight-membered ring), twisted gastrulation (nine-membered ring), as well as chordin and noggin (10-membered ring). The CAN family can be divided further into four subgroups based on a conserved arrangement of additional cysteine residues-gremlin and PRDC, cerberus and coco, and DAN, together with USAG-1 and sclerostin. We searched for orthologs of human BMP antagonists in the genomes of model organisms and analyzed their phylogenetic relationship. New human paralogs were identified together with the verification of orthologous relationships of known genes. We also discuss the physiological roles of the CAN subfamily of BMP antagonists and the associated genetic defects. Based on the known three-dimensional structure of key cystine knot proteins, we postulated disulfide bondings for eight-membered ring BMP antagonists to predict their potential folding and dimerization.

Animals↗

[Quality of life and occupational domain in schizophrenia: a gender comparison].

Schizophrenia has been associated with low quality of life in patients, and the impact can vary by gender. Knowing gender differences may help implement specific interventions. This study focuses on quality of life in male and female outpatients with schizophrenia, particularly examining the occupational domain. A cross-sectional study using the Quality of Life Scale (QLS-BR) was carried out. Comparisons of scores by gender used uni- and multivariate analyses by means of a classification tree through the CHAID algorithm and ordinal logistic regression. Women showed higher quality of life scores (p < 0.05). In the occupational domain, marital status was a relevant variable; single marital status (for men or women) was associated with lower quality of life as compared to married status, with OR = 10.0 (CI: 2.9-33.3) for men and OR = 4.5 (CI: 1.2-16.6) for women, respectively. Duration of illness (> 5 years) was another significant factor for lower scores. Women had better quality of life scores than men, suggesting that they have more occupational activities due to their greater participation in domestic and social activities.

Adolescent↗

Intrusion detection using rough set classification.

Recently machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, rough set classification (RSC), a modern learning algorithm, is used to rank the features extracted for detecting intrusions and generate intrusion detection models. Feature ranking is a very critical step when building the model. RSC performs feature ranking before generating rules, and converts the feature ranking to minimal hitting set problem addressed by using genetic algorithm (GA). This is done in classical approaches using Support Vector Machine (SVM) by executing many iterations, each of which removes one useless feature. Compared with those methods, our method can avoid many iterations. In addition, a hybrid genetic algorithm is proposed to increase the convergence speed and decrease the training time of RSC. The models generated by RSC take the form of "IF-THEN" rules, which have the advantage of explication. Tests and comparison of RSC with SVM on DARPA benchmark data showed that for Probe and DoS attacks both RSC and SVM yielded highly accurate results (greater than 99% accuracy on testing set).

Algorithms↗

[Automatic recognition of RR-intervals of sinus origin from real electrocardiographic signals].

A simple decisive rule for classifying RR-intervals of electrocardiograms by two types, sinusoidal and anomalous, is deduced using the theory of pattern recognition. Parameters of the decisive rule according to the minimum of the Buyess probability of the classification error are selected. The algorithm may be realized with microprocessors and used in cardiac rhythm monitors.

Arrhythmia, Sinus↗

The treatment of thoracolumbar fractures: one point of view.

Although much has been written regarding treatment of thoracolumbar fractures, questions remain concerning even the most basic issues. This article reviews classification systems, bony stability, the need for neural decompression in thoracolumbar spine fractures, and the literature comparing conservative treatment versus surgical treatment and evaluating various surgical approaches and fixation devices. Finally, data in the available literature and the results of the neurologic examination, radiographic studies, and the magnetic resonance imaging scan are used as the basis for a proposed classification system and a treatment algorithm.

Humans↗

[Quality assurance in trauma surgery--meaning, characteristics and methods].

For trauma surgeons the compliance with and keeping to well organized and planned courses of action is obligatory. This is valid as well for the highly sensitive areas of preclinical emergency treatment, the primary treatment in the hospital and the exceptional management in polytrauma, as for treatment of solitary injuries of the musculo-skeletal system. Despite considerable activities--so far voluntarily--(optimization of courses of action, classification systems for injury grades, algorithms and close-meshed further education) control mechanisms are demanded by politicians and insurance companies. Therefore, comprehensive quality control is strived for in all different types of insurance coverage systems. In spite of justifiable restraints against control mechanisms, which oppose increasingly medical freedom in diagnostics and treatment, only cooperation with and proficient guidance of the often self-appointed quality assurance personnel is useful.

Algorithms↗

Three-dimensional classification of spinal deformities using fuzzy clustering.

STUDY DESIGN: A prospective study of a large set of three-dimensional (3D) reconstructions of spinal deformities in adolescent idiopathic scoliosis (AIS). OBJECTIVES: To determine the value of fuzzy clustering techniques to automatically detect clinically relevant 3D curve patterns within this set of 3D spine models. SUMMARY OF BACKGROUND DATA: Classification is important for the assessment of AIS and has been mainly used to guide surgical treatment. Current classification systems are based on visual curve pattern identification using two-dimensional radiologic measurements but remain controversial because of their low interobserver and intraobserver reliability. A clinically useful 3D classification remains to be found. METHODS: An unsupervised learning algorithm, fuzzy k-means clustering, was applied on 409 3D spine models. Analysis of data distribution using clinical parameters was performed by studying similar curve patterns, near each cluster center identified. RESULTS: The algorithm determined that the entire sample of models could be segmented in five easily differentiated curve patterns similar to those of the Lenke and King classifications. Furthermore, a system with 12 classes made possible the identification of subpatterns of spinal deformity with true 3D components. CONCLUSIONS: Automatic and clinically relevant 3D classification of AIS is possible using an unsupervised learning algorithm. This approach can now be used to build a relevant 3D classification of AIS using appropriate key features of 3D models selected by a panel of expert spinal deformity surgeons.

Adolescent↗

Theory for the systemic definition of metabolic pathways and their use in interpreting metabolic function from a pathway-oriented perspective.

Cellular metabolism is most often described and interpreted in terms of the biochemical reactions that make up the metabolic network. Genomics is providing near complete information regarding the genes/gene products participating in cellular metabolism for a growing number of organisms. As the true functional units of metabolic systems are its pathways, the time has arrived to define metabolic pathways in the context of whole-cell metabolism for the analysis of the structural design and capabilities of the metabolic network. In this study, we present the theoretical foundations for the identification of the unique set of systemically independent biochemical pathways, termed extreme pathways, based on system stochiometry and limited thermodynamics. These pathways represent the edges of the steady-state flux cone derived from convex analysis, and they can be used to represent any flux distribution achievable by the metabolic network. An algorithm is presented to determine the set of extreme pathways for a system of any complexity and a classification scheme is introduced for the characterization of these pathways. The property of systemic independence is discussed along with its implications for issues related to metabolic regulation and the evolution of cellular metabolic networks. The underlying pathway structure that is determined from the set of extreme pathways now provides us with the ability to analyse, interpret, and perhaps predict metabolic function from a pathway-based perspective in addition to the traditional reaction-based perspective. The algorithm and classification scheme developed can be used to describe the pathway structure in annotated genomes to explore the capabilities of an organism.

Algorithms↗

A generalization of the PST algorithm: modeling the sparse nature of protein sequences.

MOTIVATION: A central problem in genomics is to determine the function of a protein using the information contained in its amino acid sequence. Variable length Markov chains (VLMC) are a promising class of models that can effectively classify proteins into families and they can be estimated in linear time and space. RESULTS: We introduce a new algorithm, called Sparse Probabilistic Suffix Trees (SPST), that identifies equivalence between the contexts of a VLMC. We show that, in many cases, the identification of these equivalence can improve the classification rate of the classical Probabilistic Suffix Trees (PST) algorithm. We also show that better classification can be achieved by identifying representative fingerprints in the amino acid chains, and this variation in the SPST algorithm is called F-SPST.

Algorithms↗

Classification of genetic sequences with backpropagation.

A backpropagation algorithm is used to train a neural net with the goal of distinguishing between two groups of biological species: prokaryotic and eukaryotic, based on frequencies of all 16 doublets in DNA sequences. An improvement of about 15% is obtained compared to statistical analysis based on one doublet only. This is done first by presenting sequences of species to the network with known classification (the training phase) and then showing species which the neural net has never seen before, and looking for the response. A brief discussion of the speed of training is given.

Algorithms↗

A 100-channel system for real time detection and storage of extracellular spike waveforms.

As extracellular electrode arrays with 100 or more active recording sites become more widely used for simultaneous recording of neural ensembles, practical data acquisition systems that can efficiently accommodate high electrode counts are needed. To reduce the high data rates associated with extracellular recordings from these arrays, various algorithms and systems have been designed to provide complete online detection and classification of extracellular spike waveforms. However, many of these algorithms require significant user supervision to ensure accurate performance. In this paper, we discuss the design and validation of a 100-channel PC-based system that can be used with arrays of extracellular electrodes such as the Utah Electrode Array. Instead of comprehensive online spike analysis, the system performs online detection and storage of the spike waveforms for offline classification. This strategy preserves the data of interest, reduces system complexity, and requires less user supervision during experiments.

Action Potentials↗

Recognition of translation initiation sites of eukaryotic genes based on an EM algorithm.

With the rapid increase of DNA databases of human and other eukaryotic model organisms, a large great number of genes need to be distinguished from the DNA databases. Exact recognition of translation initiation sites (TISs) of eukaryotic genes is very important to understand the translation initiation process, predict the detailed structure of eukaryotic genes, and annotate uncharacterized sequences. The problem has not been solved satisfactorily, especially for recognizing TISs of the eukaryotic genes with shorter first exons. It is an important task for extracting new features and finding new powerful algorithms for recognizing TISs of eukaryotic genes. In this paper, the important characteristics of shorter flanking fragments around TISs are extracted and an expectation-maximization (EM) algorithm based on incomplete data is used to recognize TISs of eukaryotic genes. The accuracy is up to 87.8% over a six-fold cross-validation test. The result shows that the identification variables are effectively extracted and the EM algorithm is a powerful tool to predict the TISs of eukaryotic genes. The algorithm also can be applied to other classification or clustering tasks in bioinformatics.

Algorithms↗

Effect of analytic uncertainty of conventional and point-of-care assays of activated partial thromboplastin time on clinical decisions in heparin therapy.

The authors assessed the capability of assays of activated partial thromboplastin time (aPTT) for supporting clinical decision algorithms for heparin therapies of varying complexity. Blood samples were collected prospectively in three explicit management strategies from 100 sequential patients for whom heparin dosage was adjusted for therapeutic monitoring, femoral venous sheath removal after cardiac catheterization, or heparinization after thrombolytic therapy. In two- and three-way decision algorithms, conventional and point-of-care aPTT assays agreed with heparin assays in approximately two thirds of cases, and the two aPTT assays agreed in 80% or more of all cases. In six-way decision algorithms, the two aPTT assays agreed in only about half of all cases. The authors conclude that the reliability of point-of-care aPTT assays is similar to that of conventional assays. Both techniques can support two- and three-way decision algorithms but not some more complex patient classifications.

Algorithms↗

Analysis of biomedical text for chemical names: a comparison of three methods.

At the National Library of Medicine (NLM), a variety of biomedical vocabularies are found in data pertinent to its mission. In addition to standard medical terminology, there are specialized vocabularies including that of chemical nomenclature. Normal language tools including the lexically based ones used by the Unified Medical Language System (UMLS) to manipulate and normalize text do not work well on chemical nomenclature. In order to improve NLM's capabilities in chemical text processing, two approaches to the problem of recognizing chemical nomenclature were explored. The first approach was a lexical one and consisted of analyzing text for the presence of a fixed set of chemical segments. The approach was extended with general chemical patterns and also with terms from NLM's indexing vocabulary, MeSH, and the NLM SPECIALIST lexicon. The second approach applied Bayesian classification to n-grams of text via two different methods. The single lexical method and two statistical methods were tested against data from the 1999 UMLS Metathesaurus. One of the statistical methods had an overall classification accuracy of 97%.

Algorithms↗