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 1,783 records · Page 99Linked to original sources
PubMed1981

Metabolic abnormalities associated with diabetes mellitus, as investigated by gas chromatography and pattern-recognition analysis of profiles of volatile metabolites.

Patterns of volatile metabolites in urine, as obtained by glass-capillary gas chromatography, were investigated by use of a nonparametric pattern-recognition method, in an effort to detect abnormalities associated with diabetes. We used threshold logic unit analysis on a data set consisting of normal subjects and those with diabetes mellitus, and could predict patterns for volatile metabolites as belonging to the proper class in 94.83% of the cases examined. In addition, a feature-extraction algorithm isolated those volatile constituents that are most useful in making the normal/diabetic classification. We used gas chromatography/mass spectrometry to identify important profile constituents. Finally, these same pattern-recognition methods indicated strong sex-related patterns in these volatiles.

Chromatography, Gas↗
PubMed2004

Statistical modeling of complex backgrounds for foreground object detection.

This paper addresses the problem of background modeling for foreground object detection in complex environments. A Bayesian framework that incorporates spectral, spatial, and temporal features to characterize the background appearance is proposed. Under this framework, the background is represented by the most significant and frequent features, i.e., the principal features, at each pixel. A Bayes decision rule is derived for background and foreground classification based on the statistics of principal features. Principal feature representation for both the static and dynamic background pixels is investigated. A novel learning method is proposed to adapt to both gradual and sudden "once-off" background changes. The convergence of the learning process is analyzed and a formula to select a proper learning rate is derived. Under the proposed framework, a novel algorithm for detecting foreground objects from complex environments is then established. It consists of change detection, change classification, foreground segmentation, and background maintenance. Experiments were conducted on image sequences containing targets of interest in a variety of environments, e.g., offices, public buildings, subway stations, campuses, parking lots, airports, and sidewalks. Good results of foreground detection were obtained. Quantitative evaluation and comparison with the existing method show that the proposed method provides much improved results.

Algorithms↗
PubMed1999

Quantitative follow-up of patients with multiple sclerosis using MRI: technical aspects.

A highly reproducible automated procedure for quantitative analysis of serial brain magnetic resonance (MR) images was developed for use in patients with multiple sclerosis (MS). The intracranial cavity (ICC) was identified on standard dual-echo spin-echo brain MR images using a supervised automated procedure. MR images obtained from one MS patient at 24 time points in the course of a 1-year follow-up were aligned with the images of one of the time points. Next, the contents of the ICC in each MR exam were segmented into four tissues, using a self-adaptive statistical algorithm. Misclassifications due to partial voluming were corrected using a combination of morphologic operators and connectivity criteria. Finally, a connectivity detection algorithm was used to separate the tissue classified as lesions into individual entities. Registration, classification of the contents of the ICC, and identification of individual lesions are fully automatic. Only identification of the ICC requires operator interaction. In each MR exam, the program estimated volumes for the ICC, gray matter (GM), white matter (WM), white matter lesions (WML), and cerebrospinal fluid (CSF). The reproducibility of the system was superior to that of supervised segmentation, as evidenced by the coefficient of variation: CSF supervised 45.9% vs. automated 7.7%, GM 16.0% vs. 1.4%, WM 15.7% vs. 1.3%, and WML 39.5% vs 52.0%. Our results demonstrate that this computerized procedure allows routine reproducible quantitative analysis of large serial MRI data sets.

Adult↗
PubMed2003

A data-analytic strategy for protein biomarker discovery: profiling of high-dimensional proteomic data for cancer detection.

With recent advances in mass spectrometry techniques, it is now possible to investigate proteins over a wide range of molecular weights in small biological specimens. This advance has generated data-analytic challenges in proteomics, similar to those created by microarray technologies in genetics, namely, discovery of 'signature' protein profiles specific to each pathologic state (e.g. normal vs. cancer) or differential profiles between experimental conditions (e.g. treated by a drug of interest vs. untreated) from high-dimensional data. We propose a data-analytic strategy for discovering protein biomarkers based on such high-dimensional mass spectrometry data. A real biomarker-discovery project on prostate cancer is taken as a concrete example throughout the paper: the project aims to identify proteins in serum that distinguish cancer, benign hyperplasia, and normal states of prostate using the Surface Enhanced Laser Desorption/Ionization (SELDI) technology, a recently developed mass spectrometry technique. Our data-analytic strategy takes properties of the SELDI mass spectrometer into account: the SELDI output of a specimen contains about 48,000 (x, y) points where x is the protein mass divided by the number of charges introduced by ionization and y is the protein intensity of the corresponding mass per charge value, x, in that specimen. Given high coefficients of variation and other characteristics of protein intensity measures (y values), we reduce the measures of protein intensities to a set of binary variables that indicate peaks in the y-axis direction in the nearest neighborhoods of each mass per charge point in the x-axis direction. We then account for a shifting (measurement error) problem of the x-axis in SELDI output. After this pre-analysis processing of data, we combine the binary predictors to generate classification rules for cancer, benign hyperplasia, and normal states of prostate. Our approach is to apply the boosting algorithm to select binary predictors and construct a summary classifier. We empirically evaluate sensitivity and specificity of the resulting summary classifiers with a test dataset that is independent from the training dataset used to construct the summary classifiers. The proposed method performed nearly perfectly in distinguishing cancer and benign hyperplasia from normal. In the classification of cancer vs. benign hyperplasia, however, an appreciable proportion of the benign specimens were classified incorrectly as cancer. We discuss practical issues associated with our proposed approach to the analysis of SELDI output and its application in cancer biomarker discovery.

Algorithms↗
PubMed1999

Classification of premature ventricular complexes using filter bank features, induction of decision trees and a fuzzy rule-based system.

The classification of heart beats is important for automated arrhythmia monitoring devices. The study describes two different classifiers for the identification of premature ventricular complexes (PVCs) in surface ECGs. A decision-tree algorithm based on inductive learning from a training set and a fuzzy rule-based classifier are explained in detail. Traditional features for the classification task are extracted by analysing the heart rate and morphology of the heart beats from a single lead. In addition, a novel set of features based on the use of a filter bank is presented. Filter banks allow for time-frequency-dependent signal processing with low computational effort. The performance of the classifiers is evaluated on the MIT-BIH database following the AAMI recommendations. The decision-tree algorithm has a gross sensitivity of 85.3% and a positive predictivity of 85.2%, whereas the gross sensitivity of the fuzzy rule-based system is 81.3%, and the positive predictivity is 80.6%.

Decision Trees↗
PubMed1996

[Usefulness of headache classification in the planning of radiological studies].

Neurologists can only classify headaches, not patients. Doing that, they are well aware that this is partially arbitrary. But classification is essential, especially for primary headaches (migraine, tension type headache, cluster headache) to achieve epidemiological and physiopathological studies. The criteria of definition for each type of headache must be established with pertinence. Neurologists, general practitioners as well as radiologists can then use these criteria to imagine an algorithm for the diagnostic procedure of headache patients. The aim of this publication is to describe the IHS classification as well as some common clinical situations (migraine, subarachnoidal haemorrhage, brain tumor, mild head injury.

Brain Neoplasms↗
PubMed1997

Learning systems in biosignal analysis.

In biosignal analysis, the utility of artificial neural networks (ANN) in classifying electromyographic (EMG) data trained with the momentum back propagation algorithm has recently been demonstrated. In the current study, the self-organizing feature map algorithm, the genetics-based machine learning (GBML) paradigm, and the K-means nearest neighbour clustering algorithm are applied on the same set of data. The aim of this exercise is to show how these three paradigms can be used in practice, given that their diagnostic performance is problem- and parameter-dependent. A total of 720 macro EMG recordings were carried out from four groups, from seven normal, nine motor neuron disease, 14 Becker's muscular dystrophy, and six spinal muscular atrophy subjects, respectively. Twenty-three of the subjects were used for training and 13 for evaluating the various models. For each subject, the mean and the standard deviation of the parameters (i) amplitude, (ii) area, (iii) average power and (iv) duration were extracted. The feature vector was structured in two different ways for input to the models: an eight-input feature vector that consisted of both the mean and the standard deviation of the four parameters measured, and a four-input feature vector that included only the mean of the parameters. Also, due to the heterogenous nature of the spinal muscular atrophy group, three class models that excluded this group were investigated. In general, self-organizing feature map and GBML models resulted in comparable diagnostic performance of the order of 80-90% correct classifications (CCs) score for the evaluation set, whereas the K-means nearest neighbour algorithm models gave lower percentage CCs. Furthermore, for all three learning paradigms: better diagnostic performance was obtained for the three class models compared with the four class models; similar diagnostic performance was obtained for both the eight- and four-input feature vectors. Finally, it is claimed that the proposed methodology followed in this work can be applied for the development of diagnostic systems in the analysis of biosignals.

Algorithms↗
PubMed2002

Protein structure comparison using bipartite graph matching and its application to protein structure classification.

A measure of protein structure similarity is calculated from the matching of pairs of secondary structure elements between two proteins. The interaction of each pair was estimated from their axial line segments and combined with other geometric features to produce an optimal discrimination between intrafamily and interfamily relationships. The matching used a fast bipartite graph-matching algorithm that avoids the computational complexity of searching for the full subgraph isomorphism between the two sets of interactions. The main algorithm used was the "stable marriage" algorithm, which works on the ranked "preferences" of one interaction for another. The method takes 1/10 of a second for a typical comparison making it suitable as a fast pre-filter for slower, more exhaustive approaches. An application to protein structure classification is described.

Algorithms↗
PubMed2000

A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders.

Neural networks have been widely used as tools for prediction in medicine. We expect to see even more applications of neural networks for medical diagnosis as recently developed neural network rule extraction algorithms make it possible for the decision process of a trained network to be expressed as classification rules. These rules are more comprehensible to a human user than the classification process of the networks which involves complex nonlinear mapping of the input data. This paper reports the results from two neural network rule extraction techniques, NeuroLinear and NeuroRule applied to the diagnosis of hepatobiliary disorders. The dataset consists of nine measurements collected from patients in a Japanese hospital and these measurements have continuous values. NeuroLinear generates piece-wise linear discriminant functions for this dataset. The continuous measurements have previously been discretized by domain experts. NeuroRule is applied to the discretized dataset to generate symbolic classification rules. We compare the rules generated by the two techniques and find that the rules generated by NeuroLinear from the original continuously valued dataset to be slightly more accurate and more concise than the rules generated by NeuroRule from the discretized dataset.

Algorithms↗
PubMed1998

Approaches to the automatic discovery of patterns in biosequences.

This paper surveys approaches to the discovery of patterns in biosequences and places these approaches within a formal framework that systematises the types of patterns and the discovery algorithms. Patterns with expressive power in the class of regular languages are considered, and a classification of pattern languages in this class is developed, covering the patterns that are the most frequently used in molecular bioinformatics. A formulation is given of the problem of the automatic discovery of such patterns from a set of sequences, and an analysis is presented of the ways in which an assessment can be made of the significance of the discovered patterns. It is shown that the problem is related to problems studied in the field of machine learning. The major part of this paper comprises a review of a number of existing methods developed to solve the problem and how these relate to each other, focusing on the algorithms underlying the approaches. A comparison is given of the algorithms, and examples are given of patterns that have been discovered using the different methods.

Algorithms↗
PubMed2004

Performance of a genetic algorithm for mass spectrometry proteomics.

BACKGROUND: Recently, mass spectrometry data have been mined using a genetic algorithm to produce discriminatory models that distinguish healthy individuals from those with cancer. This algorithm is the basis for claims of 100% sensitivity and specificity in two related publicly available datasets. To date, no detailed attempts have been made to explore the properties of this genetic algorithm within proteomic applications. Here the algorithm's performance on these datasets is evaluated relative to other methods. RESULTS: In reproducing the method, some modifications of the algorithm as it is described are necessary to get good performance. After modification, a cross-validation approach to model selection is used. The overall classification accuracy is comparable though not superior to other approaches considered. Also, some aspects of the process rely upon random sampling and thus for a fixed dataset the algorithm can produce many different models. This raises questions about how to choose among competing models. How this choice is made is important for interpreting sensitivity and specificity results as merely choosing the model with lowest test set error rate leads to overestimates of model performance. CONCLUSIONS: The algorithm needs to be modified to reduce variability and care must be taken in how to choose among competing models. Results derived from this algorithm must be accompanied by a full description of model selection procedures to give confidence that the reported accuracy is not overstated.

Algorithms↗
PubMed2006

The Rhythm ID Going Head to Head Trial (RIGHT): design of a randomized trial comparing competitive rhythm discrimination algorithms in implantable cardioverter defibrillators.

BACKGROUND: The implantable cardioverter defibrillator (ICD) has become primary therapy for the prevention of sudden death. One of the major morbidities of ICD use remains inappropriate therapy for supraventricular arrhythmias (SVA). Detection enhancements have increased therapy specificity, but their impact on inappropriate therapy is not well studied. Moreover, ICD manufacturers have developed unique algorithms to meet this goal, with no previous clinical direct comparisons. RIGHT is a randomized, prospective study that will assess the differential efficacy of ICDs from two different manufacturers. It is the first trial to compare directly competitive ICD rhythm discrimination algorithms on a large scale. OBJECTIVE: The primary objective of this study is to assess arrhythmia discrimination in Guidant versus Medtronic ICDs by comparing the time to first inappropriate therapy after the predischarge visit. METHODS: The study will enroll approximately 2,000 patients in 100 centers. Patients will be randomized to Guidant or Medtronic using a permuted block design, stratified by center and by single/dual chamber device types. Patients will receive a commercially available Guidant VITALITY 2 family ICD with Rhythm ID or a Medtronic ICD using the Enhanced PR Logic or Wavelet discrimination algorithms, and will be followed according to the schedule shown until a common closing date with a minimum follow-up of 12 months. All events will be reviewed by an independent committee to determine the appropriateness of rhythm classification and therapy delivery. CONCLUSION: RIGHT is the first randomized, large scale, head-to-head comparison of ICD discrimination algorithms.

Algorithms↗
PubMed2004

Detection of single and clustered microcalcifications in mammograms using fractals models and neural networks.

Microcalcifications (microCas) are often early signs of breast cancer. However, detecting them is a difficult visual task and recognizing malignant lesions is a complex diagnostic problem. In recent years, several research groups have been working to develop computer-aided diagnosis (CAD) systems for X-ray mammography. In this paper, we propose a method to detect and classify microcalcifications. In order to discover the presence of microCas clusters, particular attention is paid to the analysis of the spatial arrangement of detected lesions. A fractal model has been used to describe the mammographic image, thus, allowing the use of a matched filtering stage to enhance microcalcifications against the background. A region growing algorithm, coupled with a neural classifier, detects existing lesions. Subsequently, a second fractal model is used to analyze their spatial arrangement so that the presence of microcalcification clusters can be detected and classified. Reported results indicate that fractal models provide an adequate framework for medical image processing; consequently high correct classification rates are achieved.

Algorithms↗
PubMed1997

Association of positive Chlamydia trachomatis and Chlamydia pneumoniae immunoglobulin-gamma titers with increasing age.

STUDY OBJECTIVES: To use Chlamydia trachomatis immunoglobulin-gamma (IgG) titers to investigate the possibility of their association with ovarian cancer, and to evaluate the effectiveness of this titer in algorithmic protocols in infertility. DESIGN: Prospective, age-matched, pilot study (Canadian Task Force classification II-2). SETTING: University and university-affiliated office practice. PATIENTS: The original 30 patients were seen for follow-up of ovarian cancer (19) and at yearly examination for nonmalignant disease (10). An additional group of 21 women seen for pelvic pain and infertility was added to clarify questions that arose during the study. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Chlamydia trachomatis IgG titers were positive in 15 (79%) of 19 of women with ovarian cancer, 9 (90%) of 10 age-matched controls, and 14 (67%) of 21 patients with infertility and pain. When analyzed by age, 4 (40%) of 10 patients under 30 years and 34 (85%) of 40 patients 30 years of age or older had positive titers (p = 0.007). Of 21 women with positive Chlamydia pneumoniae titers, 17 (81 %) had positive C. trachomatis titers, and 17 (85%) of 20 with positive C. trachomatis titers had positive C. pneumoniae titers. CONCLUSION: The test kit used in this study may not be adequate in older patients due to cross-reaction with C. pneumoniae titers. Further evaluation of C. trachomatis IgG titers as a marker in the study of ovarian cancer will require titers that are more specific than those we used. Although these titers may be useful as an immunologic screening marker in infertile patients, results should be interpreted with caution. A positive test may not be evidence of C. trachomatis infection and is not an indication for specific therapy. Successful use of some currently available C. trachomatis IgG titers in algorithms for infertility may be related to a patient's age.

Adolescent↗
PubMed1999

ProtoMap: automatic classification of protein sequences, a hierarchy of protein families, and local maps of the protein space.

We investigate the space of all protein sequences in search of clusters of related proteins. Our aim is to automatically detect these sets, and thus obtain a classification of all protein sequences. Our analysis, which uses standard measures of sequence similarity as applied to an all-vs.-all comparison of SWISSPROT, gives a very conservative initial classification based on the highest scoring pairs. The many classes in this classification correspond to protein subfamilies. Subsequently we merge the subclasses using the weaker pairs in a two-phase clustering algorithm. The algorithm makes use of transitivity to identify homologous proteins; however, transitivity is applied restrictively in an attempt to prevent unrelated proteins from clustering together. This process is repeated at varying levels of statistical significance. Consequently, a hierarchical organization of all proteins is obtained. The resulting classification splits the protein space into well-defined groups of proteins, which are closely correlated with natural biological families and superfamilies. Different indices of validity were applied to assess the quality of our classification and compare it with the protein families in the PROSITE and Pfam databases. Our classification agrees with these domain-based classifications for between 64.8% and 88.5% of the proteins. It also finds many new clusters of protein sequences which were not classified by these databases. The hierarchical organization suggested by our analysis reveals finer subfamilies in families of known proteins as well as many novel relations between protein families.

Algorithms↗
PubMed1999

Accuracy of clinical assessment in the diagnosis of pulmonary embolism.

To provide clinical diagnostic criteria for pulmonary embolism (PE), we evaluated 750 consecutive patients with suspected PE who were enrolled in the Prospective Investigative Study of Acute Pulmonary Embolism Diagnosis (PISA-PED). Prior to perfusion lung scanning, patients were examined independently by six pulmonologists according to a standardized diagnostic protocol. Study design required pulmonary angiography in all patients with abnormal scans. Patients are reported as two distinct groups: a first group of 500, whose data were analyzed to derive a clinical diagnostic algorithm for PE, and a second group of 250 in whom the diagnostic algorithm was validated. PE was diagnosed by angiography in 202 (40%) of the 500 patients in the first group. A diagnostic algorithm was developed that includes the identification of three symptoms (sudden onset dyspnea, chest pain, and fainting) and their association with one or more of the following abnormalities: electrocardiographic signs of right ventricular overload, radiographic signs of oligemia, amputation of hilar artery, and pulmonary consolidations compatible with infarction. The above three symptoms (singly or in some combination) were associated with at least one of the above electrocardiographic and radiographic abnormalities in 164 (81%) of 202 patients with confirmed PE and in only 22 (7%) of 298 patients without PE. The rate of correct clinical classification was 88% (440/500). In the validation group of 250 patients the prevalence of PE was 42% (104/250). In this group, the sensitivity and specificity of the clinical diagnostic algorithm for PE were 84% (95% CI: 77 to 91%) and 95% (95% CI: 91 to 99%), respectively. The rate of correct clinical classification was 90% (225/250). Combining clinical estimates of PE, derived from the diagnostic algorithm, with independent interpretation of perfusion lung scans helps restrict the need for angiography to a minority of patients with suspected PE.

Adolescent↗