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 253 records · Page 14Linked to original sources
PubMed2003

CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames.

In this paper, we present CoLD (colorectal lesions detector) an innovative detection system to support colorectal cancer diagnosis and detection of pre-cancerous polyps, by processing endoscopy images or video frame sequences acquired during colonoscopy. It utilizes second-order statistical features that are calculated on the wavelet transformation of each image to discriminate amongst regions of normal or abnormal tissue. An artificial neural network performs the classification of the features. CoLD integrates the feature extraction and classification algorithms under a graphical user interface, which allows both novice and expert users to utilize effectively all system's functions. It has been developed in close cooperation with gastroenterology specialists and has been tested on various colonoscopy videos. The detection accuracy of the proposed system has been estimated to be more than 95%. As it has been resulted, it can be used as a supplementary diagnostic tool for colorectal lesions.

Algorithms↗
PubMed1996

Differentiation between emboli and artefacts using dual-gated transcranial Doppler ultrasound.

It is well documented that transcranial Doppler ultrasound has the ability to detect cerebral emboli. During intraoperative patient monitoring studies, many signals due to artefact (probe motion, patient movement or surgical manipulation) are also detected and can be difficult to distinguish from genuine embolic events. We have constructed a Doppler system that can simultaneously range-gate at two separate depths, in order to test the hypothesis that it should be possible to distinguish between emboli and artefact by comparing the signal from the two separate regions within the vessel. The classification algorithm is based on the principle that emboli propagate with blood motion (whereas artefacts do not) and thus will be detected sequentially at different depths along the insonated cerebral artery. One hundred thirty-eight (presumed) embolic and 170 artefact signals were analysed. The median (interquartile range) gate separation was 10.01 mm (7.41-10.78 mm). The time delay between detection of embolic signals in the two channels was 11.04 ms (6.24-16.41 ms, but was only 0.08 ms (-0.48(-)+0.64 ms) for artefact (p < 0.0001). Dual-gated Doppler ultrasound is a conclusive and independent method that differentiates emboli from artefact. Incorporation of this system for long-term monitoring may eliminate the need for an experienced observer to be present.

Artifacts↗
PubMed2003

A multiple classifier system for early melanoma diagnosis.

Melanoma is the most dangerous skin cancer and early diagnosis is the key factor in its successful treatment. Well-trained dermatologists reach a diagnosis via visual inspection, and reach sensitivity and specificity levels of about 80%. Several computerised diagnostic systems were reported in the literature using different classification algorithms. In this paper, we will illustrate a novel approach by which a suitable combination of different classifiers is used in order to improve the diagnostic performances of single classifiers. We used three different kinds of classifiers, namely linear discriminant analysis (LDA), k-nearest neighbour (k-NN) and a decision tree, the inputs of which are 38 geometric and colorimetric features automatically extracted from digital images of skin lesions. Multiple classifiers were generated by combining the diagnostic outputs of single classifiers with appropriate voting schemata. This approach was evaluated on a set of 152 digital skin images. We compared the performances of multiple classifiers (2- and 3-classifier groups) between them and with respect to single ones (1-classifier group). We further compared the classifiers' performances with those of eight dermatologists. Classifiers' performances were measured in terms of distance from the ideal classifier. Compared with 1- and 2-classifier groups, performances of 3-classifier systems were significantly higher (P<0.0005 and P<0.001, respectively). No statistically significant differences were found between the 1- and 2-classifier groups (P=0.352). While the dermatologists group showed a level of performances significantly higher than the 1-classifier systems (P<0.020), no differences were found between the multiple classifier groups and the dermatologists groups, indicating comparable performances. This work suggests that a suitable combination of different kinds of classifiers can improve the performances of an automatic diagnostic system.

Algorithms↗
PubMed2004

Sample classification based on Bayesian spectral decomposition of metabonomic NMR data sets.

1H NMR spectra of biofluids provides a wealth of biochemical information on the metabolic status of an organism. Through the application of pattern recognition and classification algorithms, the data have been shown to provide information on disease diagnosis and the beneficial and adverse effects of potential therapeutics. Here, a novel approach is described for identifying subsets of spectral patterns in databases of NMR spectra, and it is shown that the intensities of these spectral patterns can be related to the onset and recovery from a toxic lesion in both a time-related and dose-related fashion. These patterns form a new type of combination biomarker for the biological effect under study. The approach is illustrated with a study of liver toxicity in rats using NMR spectra of urine following administration of a model hepatotoxin hydrazine.

Animals↗
PubMedDate not supplied

Molecular similarity analysis and virtual screening by mapping of consensus positions in binary-transformed chemical descriptor spaces with variable dimensionality.

A novel compound classification algorithm is described that operates in binary molecular descriptor spaces and groups active compounds together in a computationally highly efficient manner. The method involves the transformation of continuous descriptor value ranges into a binary format, subsequent definition of simplified descriptor spaces, identification of consensus positions of specific compound sets in these spaces, and iterative adjustments of the dimensionality of the descriptor spaces in order to discriminate compounds sharing similar activity from others. We term this approach Dynamic Mapping of Consensus positions (DMC) because the definition of reference spaces is tuned toward specific compound classes and their dimensionality is increased as the analysis proceeds. When applied to virtual screening, sets of bait compounds are added to a large screening database to identify hidden active molecules. In these calculations, molecules that map to consensus positions after elimination of most of the database compounds are considered hit candidates. In a benchmark study on five biological activity classes, hits for randomly assembled sets of bait molecules were correctly identified in 95% of virtual screening calculations in a source database containing more than 1.3 million molecules, thus providing a measure of the sensitivity of the DMC technique.

Journal Article↗
PubMedDate not supplied

Lead hopping using SVM and 3D pharmacophore fingerprints.

The combination of 3D pharmacophore fingerprints and the support vector machine classification algorithm has been used to generate robust models that are able to classify compounds as active or inactive in a number of G-protein-coupled receptor assays. The models have been tested against progressively more challenging validation sets where steps are taken to ensure that compounds in the validation set are chemically and structurally distinct from the training set. In the most challenging example, we simulate a lead-hopping experiment by excluding an entire class of compounds (defined by a core substructure) from the training set. The left-out active compounds comprised approximately 40% of the actives. The model trained on the remaining compounds is able to recall 75% of the actives from the "new" lead series while correctly classifying >99% of the 5000 inactives included in the validation set.

Computer Simulation↗
PubMed1998

Predicting patients' utilities from quality of life items: an improved scoring system for the UBQ-H.

The Utility-based Quality of Life--Heart Questionnaire (UBQ-H) is a cardiovascular extension of the Health Measurement Questionnaire. It is a multidimensional instrument that can be scored to yield a utility estimate using the Rosser Index and a classification algorithm developed for the Health Measurement Questionnaire. The aim of this study was to employ a statistical modelling approach to devise an improved scoring system. A sample of 201 cardiovascular patients completed the UBQ-H and assessed the utility of their own health state using standard gamble and time trade-off questions in an interview. Two new scoring methods were devised by regressing the UBQ-H data against patients' self-assessed utilities. The new methods gave utility estimates that correlated with angina/dyspnoea grades, life satisfaction scores and General Health Questionnaire (GHQ) scores. In a second sample of 1,112 cardiovascular patients, the UBQ-H utilities were able to distinguish between patients who had/had not experienced an adverse event (e.g. myocardial infarction) and were responsive to changes in health over time. The new scoring methods were not particularly more sensitive to quality of life effects than the original method based on the Rosser Index. However, they produced significantly lower estimates and more accurately reflected patients' self-assessed utilities.

Cardiovascular Diseases↗
PubMed1996

Multicolour spectral karyotyping of mouse chromosomes.

Murine models of human carcinogenesis are exceedingly valuable tools to understand genetic mechanisms of neoplastic growth. The identification of recurrent chromosomal rearrangements by cytogenetic techniques serves as an initial screening test for tumour specific aberrations. In murine models of human carcinogenesis, however, karyotype analysis is technically demanding because mouse chromosomes are acrocentric and of similar size. Fluorescence in situ hybridization (FISH) with mouse chromosome specific painting probes can complement conventional banding analysis. Although sensitive and specific, FISH analyses are restricted to the visualization of only a few mouse chromosomes at a time. Here we apply a novel imaging technique that we developed recently for the visualization of human chromosomes to the simultaneous discernment of all mouse chromosomes. The approach is based on spectral imaging to measure chromosome-specific spectra after FISH with differentially labelled mouse chromosome painting probes. Utilizing a combination of Fourier spectroscopy, CCD-imaging and conventional optical microscopy, spectral imaging allows simultaneous measurement of the fluorescence emission spectrum at all sample points. A spectrum-based classification algorithm has been adapted to karyotype mouse chromosomes. We have applied spectral karyotyping (SKY) to chemically induced plasmocytomas, mammary gland tumours from transgenic mice overexpressing the c-myc oncogene and thymomas from mice deficient for the ataxia telangiectasia (Atm) gene. Results from these analyses demonstrate the potential of SKY to identify complex chromosomal aberrations in mouse models of human carcinogenesis.

Animals↗
PubMed2006

A novel approach for accurate prediction of spontaneous passage of ureteral stones: support vector machines.

The objective of this study was to optimally predict the spontaneous passage of ureteral stones in patients with renal colic by applying for the first time support vector machines (SVM), an instance of kernel methods, for classification. After reviewing the results found in the literature, we compared the performances obtained with logistic regression (LR) and accurately trained artificial neural networks (ANN) to those obtained with SVM, that is, the standard SVM, and the linear programming SVM (LP-SVM); the latter techniques show an improved performance. Moreover, we rank the prediction factors according to their importance using Fisher scores and the LP-SVM feature weights. A data set of 1163 patients affected by renal colic has been analyzed and restricted to single out a statistically coherent subset of 402 patients. Nine clinical factors are used as inputs for the classification algorithms, to predict one binary output. The algorithms are cross-validated by training and testing on randomly selected train- and test-set partitions of the data and reporting the average performance on the test sets. The SVM-based approaches obtained a sensitivity of 84.5% and a specificity of 86.9%. The feature ranking based on LP-SVM gives the highest importance to stone size, stone position and symptom duration before check-up. We propose a statistically correct way of employing LR, ANN and SVM for the prediction of spontaneous passage of ureteral stones in patients with renal colic. SVM outperformed ANN, as well as LR. This study will soon be translated into a practical software toolbox for actual clinical usage.

Algorithms↗
PubMed2005

A quantitative genomic expression analysis platform for multiplexed in vitro prediction of drug action.

Genomic expression signatures provide high-content biomarkers of cellular physiology, including the diverse responses to therapeutic drugs. To recognize these signatures, we devised a method of biomarker evaluation called 'sampling over gene space' (SOGS) that imparts superior predictive performance to existing supervised classification algorithms. Applied to microarray data from drug-treated human cortical neuron 1A cell cultures, this method predicts whether individual compounds possess anticonvulsant, antihypertensive, cyclooxygenase inhibitor, or opioid action. Thus, stable cell lines can be suitable for expression signature-based screening of a diverse range of activities. A SOGS-based system also discriminates physiologically active from inactive compounds, identifies drugs with off-target side effects, and incorporates a quantitative method for assigning confidence to individual predictions that, at its most stringent, approaches 100% accuracy. The capacity to resolve multiple distinct drug activities while simultaneously discriminating inactive and potential false-positive compounds in a cell line presents a unified framework for streamlined chemical genomic drug discovery.

Algorithms↗
PubMed2001

Identification of counterfeit drugs using near-infrared spectroscopy.

This work was aimed at the investigation of the use of near-infrared spectroscopy (NIRS) for the identification of counterfeit drugs. The identification is based on the comparison of the NIR spectrum of a sample with typical spectra of the authentic drug using multivariate modelling and classification algorithms (PCA/SIMCA). Initially, NIRS was evaluated for spectrum acquisition of various drugs, selected in order to observe the diversity of physico-chemical characteristics found among commercial products. The parameters which could affect the spectra of a given drug (especially if presented in solid form) were investigated and the results showed that the first derivative can minimise spectral changes associated with tablet geometry, physical differences in their faces and position in relation to the probe beam. The power of NIRS in distinguishing among similar pharmaceuticals was demonstrated and a protocol is proposed to construct a multivariate model and to include it in a library allowing testing for drug authenticity. The methodology was evaluated with real samples of counterfeit drugs and was able to recognise all those presenting changes in composition as false. The results show unequivocally the potential of NIRS for rapid, on-site and non-destructive identification of counterfeit pharmaceuticals.

Algorithms↗
PubMed2005

Identification and analysis of alternative splicing events conserved in human and mouse.

Alternative pre-mRNA splicing affects a majority of human genes and plays important roles in development and disease. Alternative splicing (AS) events conserved since the divergence of human and mouse are likely of primary biological importance, but relatively few of such events are known. Here we describe sequence features that distinguish exons subject to evolutionarily conserved AS, which we call alternative conserved exons (ACEs), from other orthologous human/mouse exons and integrate these features into an exon classification algorithm, acescan. Genome-wide analysis of annotated orthologous human-mouse exon pairs identified approximately 2,000 predicted ACEs. Alternative splicing was verified in both human and mouse tissues by using an RT-PCR-sequencing protocol for 21 of 30 (70%) predicted ACEs tested, supporting the validity of a majority of acescan predictions. By contrast, AS was observed in mouse tissues for only 2 of 15 (13%) tested exons that had EST or cDNA evidence of AS in human but were not predicted ACEs, and AS was never observed for 11 negative control exons in human or mouse tissues. Predicted ACEs were much more likely to preserve the reading frame and less likely to disrupt protein domains than other AS events and were enriched in genes expressed in the brain and in genes involved in transcriptional regulation, RNA processing, and development. Our results also imply that the vast majority of AS events represented in the human EST database are not conserved in mouse.

Alternative Splicing↗
PubMed2005

Serum protein markers for early detection of ovarian cancer.

Early diagnosis of epithelial ovarian cancer (EOC) would significantly decrease the morbidity and mortality from this disease but is difficult in the absence of physical symptoms. Here, we report a blood test, based on the simultaneous quantization of four analytes (leptin, prolactin, osteopontin, and insulin-like growth factor-II), that can discriminate between disease-free and EOC patients, including patients diagnosed with stage I and II disease, with high efficiency (95%). Microarray analysis was used initially to determine the levels of 169 proteins in serum from 28 healthy women, 18 women newly diagnosed with EOC, and 40 women with recurrent disease. Evaluation of proteins that showed significant differences in expression between controls and cancer patients by ELISA assays yielded the four analytes. These four proteins then were evaluated in a blind cross-validation study by using an additional 106 healthy females and 100 patients with EOC (24 stage I/II and 76 stage III/IV). Upon sample decoding, the results were analyzed by using three different classification algorithms and a binary code methodology. The four-analyte test was further validated in a blind binary code study by using 40 additional serum samples from normal and EOC cancer patients. No single protein could completely distinguish the cancer group from the healthy controls. However, the combination of the four analytes exhibited the following: sensitivity 95%, positive predictive value (PPV) 95%, specificity 95%, and negative predictive value (NPV) 94%, a considerable improvement on current methodology.

Aged↗
PubMed2006

Detection of hypopharyngeal squamous cell carcinoma using serum proteomics.

CONCLUSIONS: The combination of surface-enhanced laser desorption/ionization (SELDI) with bioinformatics tools could help find serum proteome biomarkers and establish a predictive model for early detection of hypopharyngeal squamous cell carcinoma (HSCC). OBJECTIVES: Proteomic profiling of serum using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS) is an emerging technique to identify new biomarkers in biological fluids and to establish clinically useful diagnostic computational models. We used it to find new potential biomarkers and to establish a predictive model for early detection of HSCC. MATERIALS AND METHODS: One hundred serum samples including 48 from HSCC patients and 52 from normal controls which were divided into a training set and a blind testing set were treated on WCX2 and IMAC3 protein chip, and serum protein or peptide patterns were detected by SELDI-TOF-MS. The data of spectra were analyzed by Biomarker Wizard software to screen serum proteome biomarkers of HSCC. A decision tree classification algorithm and blind validation were determined by Biomarker Pattern Software (BPS). RESULTS: Ranging from 2 to 30 kDa, 45 potential biomarkers could differentiate HSCC patients from normal controls (p < 0.05). Among them four candidate protein peaks with m/z values of 7796, 4216, 5927, and 5361Da were selected to establish a predictive model by BPS with sensitivity of 94% and specificity of 89%. A sensitivity of 92% and specificity of 82% were validated in the blind testing set.

Adult↗
PubMed2003

Combining pairwise sequence similarity and support vector machines for detecting remote protein evolutionary and structural relationships.

One key element in understanding the molecular machinery of the cell is to understand the structure and function of each protein encoded in the genome. A very successful means of inferring the structure or function of a previously unannotated protein is via sequence similarity with one or more proteins whose structure or function is already known. Toward this end, we propose a means of representing proteins using pairwise sequence similarity scores. This representation, combined with a discriminative classification algorithm known as the support vector machine (SVM), provides a powerful means of detecting subtle structural and evolutionary relationships among proteins. The algorithm, called SVM-pairwise, when tested on its ability to recognize previously unseen families from the SCOP database, yields significantly better performance than SVM-Fisher, profile HMMs, and PSI-BLAST.

Algorithms↗
PubMed2006

Computational aspects of systematic biology.

We review the resources available to systematic biologists who wish to use computers to build classifications. Algorithm development is in an early stage, and only a few examples of integrated applications for systematic biology are available. The availability of data is crucial if systematic biology is to enter the computer age.

Algorithms↗
PubMed2002

Multi-class cancer classification via partial least squares with gene expression profiles.

MOTIVATION: Discrimination between two classes such as normal and cancer samples and between two types of cancers based on gene expression profiles is an important problem which has practical implications as well as the potential to further our understanding of gene expression of various cancer cells. Classification or discrimination of more than two groups or classes (multi-class) is also needed. The need for multi-class discrimination methodologies is apparent in many microarray experiments where various cancer types are considered simultaneously. RESULTS: Thus, in this paper we present the extension to the classification methodology proposed earlier Nguyen and Rocke (2002b; Bioinformatics, 18, 39-50) to classify cancer samples from multiple classes. The methodologies proposed in this paper are applied to four gene expression data sets with multiple classes: (a) a hereditary breast cancer data set with (1) BRCA1-mutation, (2) BRCA2-mutation and (3) sporadic breast cancer samples, (b) an acute leukemia data set with (1) acute myeloid leukemia (AML), (2) T-cell acute lymphoblastic leukemia (T-ALL) and (3) B-cell acute lymphoblastic leukemia (B-ALL) samples, (c) a lymphoma data set with (1) diffuse large B-cell lymphoma (DLBCL), (2) B-cell chronic lymphocytic leukemia (BCLL) and (3) follicular lymphoma (FL) samples, and (d) the NCI60 data set with cell lines derived from cancers of various sites of origin. In addition, we evaluated the classification algorithms and examined the variability of the error rates using simulations based on randomization of the real data sets. We note that there are other methods for addressing multi-class prediction recently and our approach is along the line of Nguyen and Rocke (2002b; Bioinformatics, 18, 39-50). CONTACT: dnguyen@stat.tamu.edu; dmrocke@ucdavis.edu

Algorithms↗
PubMed1990

Object-centered representation for species systematics and identification in living systems in nature.

An artificial intelligence application to identification in biological taxonomy is presented. An object-centered representation is described using SHIRKA, a knowledge-based system developed in France. The capacities of this system, relating to a classification algorithm, are described. An application to the identification of the trees and lianas of the evergreen forests of the Western Ghats (India) is presented to illustrate the problems encountered in the development of the knowledge base. A model of a systematist's reasoning, using evolutionary principles, is the basis of this work. Finally the efficiency of the system is discussed.

Artificial Intelligence↗