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 1,279 records · Page 71Linked to original sources

PubMed2006

Auditory brainstem response classification: a hybrid model using time and frequency features.

OBJECTIVE: The auditory brainstem response (ABR) is an evoked response obtained from brain electrical activity when an auditory stimulus is applied to the ear. An audiologist can determine the threshold level of hearing by applying stimuli at reducing levels of intensity, and can also diagnose various otological, audiological, and neurological abnormalities by examining the morphology of the waveform and the latencies of the individual waves. This is a subjective process requiring considerable expertise. The aim of this research was to develop software classification models to assist the audiologist with an automated detection of the ABR waveform and also to provide objectivity and consistency in this detection. MATERIALS AND METHODS: The dataset used in this study consisted of 550 waveforms derived from tests using a range of stimulus levels applied to 85 subjects ranging in hearing ability. Each waveform had been classified by a human expert as 'response=Yes' or 'response=No'. Individual software classification models were generated using time, frequency and cross-correlation measures. Classification employed both artificial neural networks (NNs) and the C5.0 decision tree algorithm. Accuracies were validated using six-fold cross-validation, and by randomising training, validation and test datasets. RESULTS: The result was a two stage classification process whereby strong responses were classified to an accuracy of 95.6% in the first stage. This used a ratio of post-stimulus to pre-stimulus power in the time domain, with power measures at 200, 500 and 900Hz in the frequency domain. In the second stage, outputs from time, frequency and cross-correlation classifiers were combined using the Dempster-Shafer method to produce a hybrid model with an accuracy of 85% (126 repeat waveforms). CONCLUSION: By combining the different approaches a hybrid system has been created that emulates the approach used by an audiologist in analysing an ABR waveform. Interpretation did not rely on one particular feature but brought together power and frequency analysis as well as consistency of subaverages. This provided a system that enhanced robustness to artefacts while maintaining classification accuracy.

Acoustic Stimulation↗

PubMed2001

The use of information theory and numerical taxonomy methods for evaluating the quality of thin-layer chromatographic separations of flavonoid constituents of Matricariae flos.

A methanol extract of Matricariae flos was analysed with regard to the flavonoid composition. Rational selection of a restricted set from eight chromatographic systems tested for the separation of these compounds is discussed. Series of mathematical techniques for the evaluation of solvents and solvent combinations in thin-layer chromatography of flavonoid constituents have been explored. The chromatographic systems are classified according to their mutual resemblance by numerical taxonomy techniques. The selection criterion in the groups, obtained by numerical taxonomy classification, is the information content or the discriminating power. The most suitable mobile phases for TLC separation of flavonoid constituents of Matricariae flos are: ethylacetate-methanol-water (75:15:0 v/v), ethylacetate-formic acid-water (80:10:10 v/v) and ethylacetate-formic acid-acetic acid-water (100:11:11:27 v/v).

Algorithms↗

PubMed2005

Evaluation of fusion beat detection with a new ventricular automatic capture algorithm in ICDs.

This study evaluated a newly developed automatic capture verification scheme for implantable cardioverter defibrillators (ICDs) regarding discrimination of capture, fusion, and noncapture beats, with an emphasis on fusion detection. The algorithm uses evoked response detection based on a sensing vector from right ventricular shocking coil to Can. Patients undergoing ICD implant or replacement were enrolled in this study. An external system was used for pacing and data acquisition. To provoke ventricular fusion beats, VVI patients were paced close to the rate of their intrinsic rhythm and DDD patients were paced close at their intrinsic PR interval. Surface ECG and wideband filtered intracardiac electrograms were recorded for off-line analysis. Each paced beat was independently classified visually by surface ECG and by the automatic detection algorithm. The algorithm performance was then evaluated by comparing the classification results. Twenty-seven patients (22 males, 5 females; 63.8 +/- 12.5 years) were analyzed. Device and lead demographics were: 18 DDD/9 VVI; 16 dedicated bipolar, 11 integrated bipolar leads; 18 acute, 9 chronic (3.7 +/- 2.0 years) leads. In total, 2064 beats were analyzed, including 1,477 fusion beats and 587 capture beats. Fusion detection sensitivity and specificity were 99.5% and 99.0%, respectively. Seven true-fusion beats (0.5%) were classified as capture and 6 capture beats (1.0%) were identified as fusions. Capture or fusion beats were never detected as non-capture beats. It is concluded that the algorithm was effective in detecting fusion beats. It could potentially be used in ICD applications that need accurate fusion detection.

Algorithms↗

PubMed2003

Evolutionary computing for knowledge discovery in medical diagnosis.

One of the major challenges in medical domain is the extraction of comprehensible knowledge from medical diagnosis data. In this paper, a two-phase hybrid evolutionary classification technique is proposed to extract classification rules that can be used in clinical practice for better understanding and prevention of unwanted medical events. In the first phase, a hybrid evolutionary algorithm (EA) is utilized to confine the search space by evolving a pool of good candidate rules, e.g. genetic programming (GP) is applied to evolve nominal attributes for free structured rules and genetic algorithm (GA) is used to optimize the numeric attributes for concise classification rules without the need of discretization. These candidate rules are then used in the second phase to optimize the order and number of rules in the evolution for forming accurate and comprehensible rule sets. The proposed evolutionary classifier (EvoC) is validated upon hepatitis and breast cancer datasets obtained from the UCI machine-learning repository. Simulation results show that the evolutionary classifier produces comprehensible rules and good classification accuracy for the medical datasets. Results obtained from t-tests further justify its robustness and invariance to random partition of datasets.

Adolescent↗

PubMed2006

A simple method to combine multiple molecular biomarkers for dichotomous diagnostic classification.

BACKGROUND: In spite of the recognized diagnostic potential of biomarkers, the quest for squelching noise and wringing in information from a given set of biomarkers continues. Here, we suggest a statistical algorithm that--assuming each molecular biomarker to be a diagnostic test--enriches the diagnostic performance of an optimized set of independent biomarkers employing established statistical techniques. We validated the proposed algorithm using several simulation datasets in addition to four publicly available real datasets that compared i) subjects having cancer with those without; ii) subjects with two different cancers; iii) subjects with two different types of one cancer; and iv) subjects with same cancer resulting in differential time to metastasis. RESULTS: Our algorithm comprises of three steps: estimating the area under the receiver operating characteristic curve for each biomarker, identifying a subset of biomarkers using linear regression and combining the chosen biomarkers using linear discriminant function analysis. Combining these established statistical methods that are available in most statistical packages, we observed that the diagnostic accuracy of our approach was 100%, 99.94%, 96.67% and 93.92% for the real datasets used in the study. These estimates were comparable to or better than the ones previously reported using alternative methods. In a synthetic dataset, we also observed that all the biomarkers chosen by our algorithm were indeed truly differentially expressed. CONCLUSION: The proposed algorithm can be used for accurate diagnosis in the setting of dichotomous classification of disease states.

Algorithms↗

PubMed2004

A knowledge-based clustering algorithm driven by Gene Ontology.

We have developed an algorithm for inferring the degree of similarity between genes by using the graph-based structure of Gene Ontology (GO). We applied this knowledge-based similarity metric to a clique-finding algorithm for detecting sets of related genes with biological classifications. We also combined it with an expression-based distance metric to produce a co-cluster analysis, which accentuates genes with both similar expression profiles and similar biological characteristics and identifies gene clusters that are more stable and biologically meaningful. These algorithms are demonstrated in the analysis of MPRO cell differentiation time series experiments.

Algorithms↗

PubMed2005

Towards precise classification of cancers based on robust gene functional expression profiles.

BACKGROUND: Development of robust and efficient methods for analyzing and interpreting high dimension gene expression profiles continues to be a focus in computational biology. The accumulated experiment evidence supports the assumption that genes express and perform their functions in modular fashions in cells. Therefore, there is an open space for development of the timely and relevant computational algorithms that use robust functional expression profiles towards precise classification of complex human diseases at the modular level. RESULTS: Inspired by the insight that genes act as a module to carry out a highly integrated cellular function, we thus define a low dimension functional expression profile for data reduction. After annotating each individual gene to functional categories defined in a proper gene function classification system such as Gene Ontology applied in this study, we identify those functional categories enriched with differentially expressed genes. For each functional category or functional module, we compute a summary measure (s) for the raw expression values of the annotated genes to capture the overall activity level of the module. In this way, we can treat the gene expressions within a functional module as an integrative data point to replace the multiple values of individual genes. We compare the classification performance of decision trees based on functional expression profiles with the conventional gene expression profiles using four publicly available datasets, which indicates that precise classification of tumour types and improved interpretation can be achieved with the reduced functional expression profiles. CONCLUSION: This modular approach is demonstrated to be a powerful alternative approach to analyzing high dimension microarray data and is robust to high measurement noise and intrinsic biological variance inherent in microarray data. Furthermore, efficient integration with current biological knowledge has facilitated the interpretation of the underlying molecular mechanisms for complex human diseases at the modular level.

Algorithms↗

PubMed2005

Evaluation of serum protein profiling by surface-enhanced laser desorption/ionization time-of-flight mass spectrometry for the detection of prostate cancer: I. Assessment of platform reproducibility.

BACKGROUND: Protein expression profiling for differences indicative of early cancer has promise for improving diagnostics. This report describes the first stage of a National Cancer Institute/Early Detection Research Network-sponsored multiinstitutional evaluation and validation of this approach for detection of prostate cancer. METHODS: Two sequential experimental phases were conducted to establish interlaboratory calibration and standardization of the surface-enhanced laser desorption (SELDI) instrumental and assay platform output. We first established whether the output from multiple calibrated Protein Biosystem II SELDI-ionization time-of-flight mass spectrometry (TOF-MS) instruments demonstrated acceptable interlaboratory reproducibility. This was determined by measuring mass accuracy, resolution, signal-to-noise ratio, and normalized intensity of three m/z "peaks" present in a standard pooled serum sample. We next evaluated the ability of the calibrated and standardized instrumentation to accurately differentiate between selected cases of prostate cancer and control by use of an algorithm developed from data derived from a single site 2 years earlier. RESULTS: When the described standard operating procedures were established at all laboratory sites, the across-laboratory measurements revealed a CV for mass accuracy of 0.1%, signal-to-noise ratio of approximately 40%, and normalized intensity of 15-36% for the three pooled serum peaks. This was comparable to the intralaboratory measurements of the same peaks. The instrument systems were then challenged with sera from a selected group of 14 cases and 14 controls. The classification agreement between each site and the established decision algorithm were examined by use of both raw peak intensity boosting and ranked peak intensity boosting. All six sites achieved perfect blinded classification for all samples when boosted alignment of raw intensities was used. Four of six sites achieved perfect blinded classification with ranked intensities, with one site passing the criteria of 26 of 28 correct and one site failing with 19 of 28 correct. CONCLUSIONS: These results demonstrate that "between-laboratory" reproducibility of SELDI-TOF-MS serum profiling approaches that of "within-laboratory" reproducibility as determined by measuring discrete m/z peaks over time and across laboratories.

Calibration↗

PubMed2005

Gene expression data classification with Kernel principal component analysis.

One important feature of the gene expression data is that the number of genes M far exceeds the number of samples N. Standard statistical methods do not work well when N < M. Development of new methodologies or modification of existing methodologies is needed for the analysis of the microarray data. In this paper, we propose a novel analysis procedure for classifying the gene expression data. This procedure involves dimension reduction using kernel principal component analysis (KPCA) and classification with logistic regression (discrimination). KPCA is a generalization and nonlinear version of principal component analysis. The proposed algorithm was applied to five different gene expression datasets involving human tumor samples. Comparison with other popular classification methods such as support vector machines and neural networks shows that our algorithm is very promising in classifying gene expression data.

Journal Article↗

PubMed1996

Automated classification of renal interstitium and tubules by local texture analysis and a neural network.

OBJECTIVE: To segment renal interstitial space in order to automatically quantify renal cortical interstitial volume fraction (Vvint/cortex) by means of image analysis techniques. STUDY DESIGN: The study group consisted of 35 renal biopsies with different degrees of chronic interstitial damage. Biopsies were stained with Sirius red and digitized under polarized light. Two methods were employed to segment interstitial space: (1) interstitial bright particles were thresholded, and afterwards interstitial space was reconstructed with a morphologic operation, and (2) the texture of the surroundings of each pixel was quantified by means of local granulometry, and this information was employed as the input of a neural network in order to classify interstitial and tubular pixels. RESULTS: The correlation between Vvint/cortex obtained manually and both methods was r = .92. The first method produced some deformation of tubular contours and underestimated Vvint/cortex (beta = .70) when compared to the second approach (beta = .95) (P < .05). CONCLUSION: Two different algorithms based on image analysis techniques allow the classification of renal interstitial and tubular structures and consequently allow the automated and precise estimation of renal Vvint/cortex.

Adult↗

PubMedDate not supplied

A support vector machine using the lazy learning approach for multi-class classification.

Support vector machines can be used in a new machine learning technique based on statistical learning. In this paper, we develop least squares support vector machines (LS-SVMs) using the lazy learning approach to classify data in unclassifiable regions in the case of multi-class classification. LS-SVMs use a set of linear equations while SVMs use a quadratic programming problem. The lazy learning approach is a local and memory-based technique. Therefore, it is an alternative technique to fuzzy inference systems. Our studies show that LS-SVMs with the lazy learning approach can give comparable results to fuzzy LS-SVMs for multi-class classification.

Algorithms↗

PubMed2006

Detecting non-orthology in the COGs database and other approaches grouping orthologs using genome-specific best hits.

Correct orthology assignment is a critical prerequisite of numerous comparative genomics procedures, such as function prediction, construction of phylogenetic species trees and genome rearrangement analysis. We present an algorithm for the detection of non-orthologs that arise by mistake in current orthology classification methods based on genome-specific best hits, such as the COGs database. The algorithm works with pairwise distance estimates, rather than computationally expensive and error-prone tree-building methods. The accuracy of the algorithm is evaluated through verification of the distribution of predicted cases, case-by-case phylogenetic analysis and comparisons with predictions from other projects using independent methods. Our results show that a very significant fraction of the COG groups include non-orthologs: using conservative parameters, the algorithm detects non-orthology in a third of all COG groups. Consequently, sequence analysis sensitive to correct orthology assignments will greatly benefit from these findings.

Algorithms↗

PubMed2000

Generalized discriminant analysis using a kernel approach.

We present a new method that we call generalized discriminant analysis (GDA) to deal with nonlinear discriminant analysis using kernel function operator. The underlying theory is close to the support vector machines (SVM) insofar as the GDA method provides a mapping of the input vectors into high-dimensional feature space. In the transformed space, linear properties make it easy to extend and generalize the classical linear discriminant analysis (LDA) to nonlinear discriminant analysis. The formulation is expressed as an eigenvalue problem resolution. Using a different kernel, one can cover a wide class of nonlinearities. For both simulated data and alternate kernels, we give classification results, as well as the shape of the decision function. The results are confirmed using real data to perform seed classification.

Algorithms↗

PubMed2002

Constructing and testing a framework for dynamic risk assessment.

This paper describes the construction and testing of a framework for dynamic risk assessment. A review of previous studies identified 4 domains into which dynamic risk factors for sexual offending seem to fall. These were sexual interests, distorted attitudes, socioaffective functioning, and self-management. Psychometric indicators for 3 of the domains were identified, and 2 studies are reported using these indicators to test the framework. Study 1 divided men serving a prison sentence for a sexual offense against a child into 2 groups--those with a previous conviction of this kind (Repeaters) and those for whom this was the only time they had been sentenced for such an offense (Current Only). The Repeaters were found to show more distorted attitudes, worse socioaffective functioning, and poorer self-management than did the Current Only group. Study 2 used a simple algorithm to combine these psychometric indicators into an overall "Deviance" classification. Reconviction data was obtained for offenders classified as high, moderate, or low on Deviance. Sexual reconviction was found to be monotonically associated with the Deviance classification. Logistic regression analysis showed that both static variables (Static-99) and the Deviance classification made independent contributions to prediction. It is suggested that risk assessment procedures should combine these 2 approaches.

Algorithms↗

PubMed2006

An optimization methodology for neural network weights and architectures.

This paper introduces a methodology for neural network global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques.

Algorithms↗

PubMed2004

Using convex hulls to extract interaction interfaces from known structures.

MOTIVATION: Protein interactions provide an important context for the understanding of function. Experimental approaches have been complemented with computational ones, such as PSIMAP, which computes domain-domain interactions for all multi-domain and multi-chain proteins in the Protein Data Bank (PDB). PSIMAP has been used to determine that superfamilies occurring in many species have many interaction partners, to show examples of convergent evolution through shared interaction partners and to uncover complexes in the interaction map. To determine an interaction, the original PSIMAP algorithm checks all residue pairs of any domain pair defined by classification systems such as SCOP. The computation takes several days for the PDB. The computation of PSIMAP has two shortcomings: first, the original PSIMAP algorithm considers only interactions of residue pairs rather than atom pairs losing information for detailed analysis of contact patterns. At the atomic level the original algorithm would take months. Second, with the superlinear growth of PDB, PSIMAP is not sustainable. RESULTS: We address these two shortcomings by developing a family of new algorithms for the computation of domain-domain interactions based on the idea of bounding shapes, which are used to prune the search space. The best of the algorithms improves on the old PSIMAP algorithm by a factor of 60 on the PDB. Additionally, the algorithms allow a distributed computation, which we carry out on a farm of 80 Linux PCs. Overall, the new algorithms reduce the computation at atomic level from months to 20 min. The combination of pruning and distribution makes the new algorithm scalable and sustainable even with the superlinear growth in PDB.

Algorithms↗

PubMed1993

Kakadu--a low power analogue neural network classifier.

An analogue neural network VLSI chip designed for low power operation is presented. This chip consists of 84 synapse elements arranged as arrays of size 10 x 6 and 6 x 4 and was fabricated using a standard 1.2 micron double metal single poly CMOS process. The synapses are digitally programmable and static weight storage is provided. The chip has a typical power consumption of tens of microwatts. It has been successfully trained and tested on a range of classification problems including 4-bit parity, character recognition and morphological-based classification of intracardiac electrogram signals.

Algorithms↗

PubMed1998

A review of methods for spike sorting: the detection and classification of neural action potentials.

The detection of neural spike activity is a technical challenge that is a prerequisite for studying many types of brain function. Measuring the activity of individual neurons accurately can be difficult due to large amounts of background noise and the difficulty in distinguishing the action potentials of one neuron from those of others in the local area. This article reviews algorithms and methods for detecting and classifying action potentials, a problem commonly referred to as spike sorting. The article first discusses the challenges of measuring neural activity and the basic issues of signal detection and classification. It reviews and illustrates algorithms and techniques that have been applied to many of the problems in spike sorting and discusses the advantages and limitations of each and the applicability of these methods for different types of experimental demands. The article is written both for the physiologist wanting to use simple methods that will improve experimental yield and minimize the selection biases of traditional techniques and for those who want to apply or extend more sophisticated algorithms to meet new experimental challenges.

Action Potentials↗