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 253 records · Page 14Linked to original sources
PubMed1989

A microcomputer-based sleep stage analyzer.

A microcomputer-based sleep stage analysis system for laboratory use is described. Rapid spectral analysis of the electroencephalogram (EEG) is achieved through hardware; subsequent analysis, including determination of the relative power in user-defined EEG frequency bands is provided through software. A decision matrix, based on standard sleep state analysis criteria, enables these spectral data, in conjunction with integrated electromyogram (EMG) power, to determine sleep stages. The system has been configured here to quantify standard sleep stages, but the algorithm can also identify, and provide information about, EEG states which are not easily classified according to earlier criteria used for visual classification of polygraphic records. This low-cost, user-friendly system thus achieves flexible, quantitative analysis of EEG and EMG signals.

Animals↗
PubMed2026

Integrating Next-Generation Sequencing into von Willebrand Disease Diagnostics: Insights from the PCM-EVW-ES Multicenter Project.

Von Willebrand disease (VWD) is the most common inherited bleeding disorder, caused by quantitative or qualitative defects in von Willebrand factor (VWF). Diagnosis is challenging and requires integrating bleeding history, VWF antigen and activity measurements, FVIII assays, and specialized phenotyping. Genetic testing is increasingly recognized as a key component. Here, we review current concepts in VWD diagnostics and highlight the Spanish Clinical and Molecular Profile of von Willebrand Disease (PCM-EVW-ES) project as a model for genomics-enabled precision medicine. PCM-EVW-ES is a multicenter initiative involving 48 hospitals, centralized phenotypic testing, and next-generation sequencing of the VWF coding region, enabling definitive classification in 730 individuals with VWD to date. Harmonized recruitment criteria and standardized workflows improve subtype assignment, uncover complex genotypes, refine genotype-phenotype correlations, and facilitate the identification of asymptomatic carriers. The PCM-EVW-ES variant spectrum highlights recurrent disease-causing variants in Spain and underscores the value of coordinated national registries for variant curation. Building on these data, we propose a diagnostic algorithm in which bleeding assessment and first-line VWF/FVIII assays, combined with, early VWF molecular testing increases diagnostic accuracy and guides targeted second-line investigations to confirm and refine VWD subtype classification. We also outline persisting challenges, including the interpretation of variants of uncertain significance and patients without identifiable pathogenic VWF variants, and future directions integrating third-generation sequencing, expanded gene panels, functional studies, and artificial-intelligence-driven multiomic approaches. Together, these advances illustrate how robust multicenter studies can bridge the gap between complex diagnostics and clinical practice in VWD.

Humans↗
PubMedDate not supplied

Computer-aided analysis of the epileptic EEG.

An introductory review of a comprehensive approach to the problem of automatic evaluation of the epileptic EEG in the frame of syntactic analysis is presented. The aims and merits of the syntactic approach are discussed and the viability of the method is demonstrated on a few chosen examples. Working procedures for automatic segmentation and classification of patterns in single- as well as in multi-channel case of the epileptic EEG are briefly described. These include algorithms for segmentation by a finite-state automaton technique (single channel) and, in multi-channel case, a sparsely updated Kalman filter algorithm. Inherent possibilities of the approach presented are shown to open the way for a global description of a seizure in terms of the Markov chains theory.

Animals↗
PubMed1988

Automatic classification of two-dimensional gel electrophoresis pictures by heuristic clustering analysis: a step toward machine learning.

The interpretation of two-dimensional gel electrophoresis (2-DGE) profiles can be facilitated by artificial intelligence and machine learning programs. We have incorporated into our 2-DGE computer analysis system (termed MELANIE-Medical Electrophoresis Analysis Interactive Expert system) a program which automatically classifies 2-DGE patterns using heuristic clustering analysis. This program is a step toward machine learning. In this publication, we describe the classification method and the preliminary results obtained with liver biopsy electrophoretograms. Heuristic clustering is also compared to other classification techniques.

Algorithms↗
PubMed1992

Blood analysis using black and white digital images.

Image processing offers a powerful tool for medical diagnosis by visual inspection. Our proposed system considers the blood analysis problem. The system processes black and white blood images obtained from a CCD camera through a microscope. Different categories of cells are recognized, counted and classified into white cells, red cells and blood petals. The white cells are further treated for their classification, according to the morphological characteristics of their nuclei. The final classification is printed in special format for the physician.

Algorithms↗
PubMed1988

Tuberculous ulcer of the skin.

A case of tuberculous skin ulcer is reported. The biopsy specimen did not reveal acid-fast bacteria but cultures grew Mycobacterium tuberculosis. A high index of suspicion is needed to diagnose mycobacterial ulcers correctly. The classification of the cutaneous tuberculoses is discussed.

Adult↗
PubMed1991

Segmentation of brain CT images using the concept of region growing.

A method is described for extracting and isolating cerebrospinal fluid and tissue areas of brain images obtained with computed tomography. The classification of the pixels into components is based on region growing and nearest neighbor principles. To aid the performance of this method, the algorithm utilizes a priori information on the anatomic composition of the brain, and reduces the 'cupping effect' in the CT image that is attributed to beam hardening artifacts. In order to avoid subjectivity, the performance of the algorithm was tested by superimposing five computer-simulated circular lesions on different areas of the original CT scans, 8 mm thick. These images were taken at different levels in the brain, thereby accommodating different anatomy as well as the apical artifact of CT scanning. In this exploratory investigation, the false negative error of segmentation for lesions having diameter of 20 pixels was found in the order of 25% at an estimated partial volume (PV) effect of 50% that decrease further to about 5% for a PV of 80%. At that point the false positive error becomes the dominant error in the analysis.

Algorithms↗
PubMed1992

Influence of cell cycle synchronization on digital image analysis of HL-60 granulopoiesis.

Retinoic acid (RA)-treated HL-60 cells subjected to density arrest (DA) and double thymidine block (TB) synchronization demonstrated image feature changes associated with cellular proliferation and differentiation. RA-treated TB cells demonstrated an increased level of morphologic differentiation (assessed by differential counts and quantitation of nuclear shape) and more rapid functional differentiation (assessed by superoxide production and expression of complement receptors) than RA-treated DA cells. By comparison to DA cells, TB cells had less variation in virtually all image features values. A Kruskal-Wallis test of image features ranked total optical density (TOD) of Feulgen-stained cells, nuclear area and shape factor as the top three features regardless of synchronization method. Statistically significant changes in image feature values of RA-treated cells were first noted on day 1. The computer-assisted ability to discriminate RA-treated cells on a given day after induction from paired controls by means of an unsupervised learning algorithm increased over a seven-day period for both DA and TB cells. However, in the dichotomous (RA-treated versus untreated) classification scheme employed, which did not account for continuous levels of morphologic differentiation, there was no advantage in the use of the TB over DA procedure.

Cell Count↗
PubMedDate not supplied

[A system of the means of genetic information transfer and the possible routes of viral evolution].

A system of means of genetic information transmission (MGIT) modeling the main features of modes of virus reproduction as well as an algorithmic approach to its construction and means of its schematic representation are proposed. The system may be used as the basis for virus classification including taxonomic categories above the family level and for the study of possible evolution relationships between virus groups. One of the variants of virus macroevolution model is described.

Biological Evolution↗
PubMed1991

Classification tree prediction models for dental caries from clinical, microbiological, and interview data.

Caries prediction by Classification And Regression Tree (CART) analysis is an appropriate and powerful alternative or complement to the commonly used classification methods of logistic regression and discriminant analysis, both parametric and nonparametric. The binary classification tree method discussed in this article is designed for complex data and does not require assumptions about the predictor variables or about the presence or absence of interactions among the predictor variables. Furthermore, the results give insight into the structures and interactions in the data and are easy to interpret and apply. In preliminary applications of the CART algorithms to data from The University of North Carolina Caries Risk Assessment Study, the method produced prediction rules having sensitivities and specificities that were similar to or slightly better than those associated with logistic and discriminant analyses. The classification trees constructed tended to involve far fewer predictor variables than required for adequate logistic and discriminant models. For example, for first-grade children in Aiken, South Carolina, nine variables were used to define a prediction rule having 64% sensitivity and 86% specificity. Ten-fold cross-validation estimates for future data were 58% and 79%, respectively. For first-grade children in Portland, Maine, two variables were used to define a prediction rule having 62% sensitivity and 77% specificity. The cross-validation estimates for future data were 58% and 78%, respectively. A brief, and previously unavailable, explanation of the CART method is given for the special case of a dichotomous outcome variable.

Child↗
PubMed1990

Use of hidden Markov models for electrocardiographic signal analysis.

Hidden Markov modelling (HMM) is a powerful stochastic modelling technique that has been successfully applied to automatic speech recognition problems. We are currently investigating the application of HMM to electrocardiographic signal analysis with the goal of improving ambulatory ECG analysis. The HMM approach specifies a Markov chain to model a "hidden" sequence that in this case is the underlying state of the heart. Each state of the Markov chain has an associated output function that describes the statistical characteristics of measurement samples generated during that state. Given a measurement sequence and HMM parameter estimates, the most likely underlying state sequence can be determined and used to infer beat classification. Advantages of this approach include resistance to noise, ability to model low-amplitude waveforms such as the P wave, and availability of an algorithm for automatically estimating model parameters from training data. We have applied the HMM approach to QRS complex detection and to arrhythmia analysis with encouraging results.

Algorithms↗
PubMed1990

Therapeutic risk-assessment model for identifying patients with adverse drug reactions.

The association between factors that place patients at risk for adverse drug reactions (ADRs) and the occurrence of ADRs was examined, and a therapeutic risk-assessment model was developed. Theoretical risk factors for ADRs to digoxin and theophylline were identified through the literature by researchers at a private tertiary-care hospital. Data were then collected from two groups of 67 patient charts each during a 15-month period. One group of charts represented patients who had experienced an ADR to digoxin or theophylline. The other group represented matched control patients who had not experienced an ADR to either drug. ICD-9-CM (International Classification of Diseases, 9th Revision, Clinical Modifications) ADR codes were assigned by medical records department personnel, and the ADRs were verified by using the Naranjo algorithm. Seven risk factors for each drug were found to be significantly associated with ADRs. A serum digoxin concentration greater than 2.5 ng/mL and elevated blood urea nitrogen were the two best predictors of an ADR to digoxin. The probability of experiencing an ADR to digoxin was 94.1% for a patient with both of these risk factors. A serum theophylline concentration greater than 25 micrograms/mL was the greatest predictor of an ADR to theophylline; the probability of experiencing an ADR to theophylline was 85.2% if a patient had that risk factor. The sensitivity and specificity of the therapeutic risk-assessment model were 92.9% and 61.8%, respectively, for digoxin and 95.8% and 84.0%, respectively, for theophylline. Several laboratory-based screening criteria demonstrated an ability to predict ADRs to digoxin and theophylline.

Digoxin↗
PubMedDate not supplied

[Eight types of stacking interaction in dinucleotides. Conformational analysis of ApA, ApC, CpA, CpC, GpG].

On the basis of general stereochemical considerations the classification of the stacking state of dinucleoside phosphate (DNP) including eight types of stacks of nucleic bases has been suggested. With the use of the algorithm, which makes possible determination of the backbone conformation for the given nucleic bases arrangement, the stacking conformes of DNP were analysed by atom-atom potential method. For all compounds different types of stacking conformes were obtained with energy values lower than that for the unstacking state. It follows from the results of calculations that for description of the conformational situation of DNP in solution the "non-canonical" conformers should be born in mind. In particular the forms having different sugar conformations in Np- and in pN-parts of the dimers are of interest. The effect of choice of the atom-atom potential functions on optimal conformation of DNP is discussed. For single-stranded RNA several regular and non-regular structures are proposed.

Adenine Nucleotides↗
PubMed1990

SCAN. Schedules for Clinical Assessment in Neuropsychiatry.

After more than 12 years of development, the ninth edition of the Present State Examination (PSE-9) was published, together with associated instruments and computer algorithm, in 1974. The system has now been expanded, in the framework of the World Health Organization/Alcohol, Drug Abuse, and Mental Health Administration Joint Project on Standardization of Diagnosis and Classification, and is being tested with the aim of developing a comprehensive procedure for clinical examination that is also capable of generating many of the categories of the International Classification of Diseases, 10th edition, and the Diagnostic and Statistical Manual of Mental Disorders, revised third edition. The new system is known as SCAN (Schedules for Clinical Assessment in Neuropsychiatry). It includes the 10th edition of the PSE as one of its core schedules, preliminary tests of which have suggested that reliability is similar to that of PSE-9. SCAN is being field tested in 20 centers in 11 countries. A final version is expected to be available in January 1990.

Algorithms↗
PubMed1990

Transformation of multitrait to unitrait mixed model analysis of data with multiple random effects.

An algorithm for transforming a multitrait into a unitrait analysis was presented for a mixed model that has equal design matrices for t traits and contains more than one random classification. The class of models was restricted to those in which the covariance matrices for all random effects including the residual can be diagonalized simultaneously. A variation of this assumption was called the common principal component by Flury. As a result of the transformation, setting up and solving the laborious t trait mixed model equations becomes a simple matter of setting up and solving the unitrait mixed model equations separately for each of the t transformed traits. The present procedure would not only simplify computer programming but more importantly it would drastically reduce central processing unit time and computer space requirements. A numerical example was given to illustrate this procedure of indirect multitrait analysis in comparison with direct multitrait analysis.

Algorithms↗
PubMed1979

Texture analysis of cervical cell nuclei by segmentation of chromatin patterns.

Texture parameters of the nuclear chromatin pattern can contribute to the automated classification of specimens on the basis of single cell analysis in cervical cytology. Current texture parameters are abstract and therefore hamper understanding. In this paper texture parameters are described that can be derived from the chromatin pattern after segmentation of the nuclear image. These texture parameters are more directly related to the visual properties of the chromatin pattern. The image segmentation procedure is based on a region grow algorithm which specifically isolates high chromatin density. The texture analysis method has been tested on a data set of images of 112 cervical nuclei on photographic negatives digitized with a step size of 0.125 micron. The preliminary results of a classification trial indicate that these visually interpretable parameters have promising discriminatory power for the distinction between negative and positive specimens.

Carcinoma↗
PubMed1992

Numerical classification and identification of Aeromonas genospecies.

A total of 176 Aeromonas strains representing all currently characterized genospecies were tested for 329 biochemical characters. Overall similarities of all strains were determined by numerical taxonomic techniques, the UPGMA algorithm and the SSM and the SJ coefficients as measures of similarity. Sixteen clusters (two or more strains) and seven unclustered strains were recovered at the 93.5% similarity level (SSM). Genospecies 1, 4, 5, 6, 7, 9, 12 and 13 were largely represented by single phena, whereas strains of genospecies 2 and 3 were found in closely-related phena. Strains belonging to genospecies 8 formed two distinct biotypes. Strains belonging to genospecies 11 formed a subcluster within a cluster representing different genospecies. In general, similar groupings were obtained with the Jaccard coefficient at a similarity level of 80.0% (SJ) with minor changes in the definition of clusters. The phenetic data showed good correlation with the taxa defined by DNA/DNA hybridization and those obtained by multilocus enzyme analysis. For all genospecies (independent from cluster assignment) 30 diagnostic characters were selected to construct a matrix for probabilistic identification. The correct identification rate of the matrix was 71.51% taking a Willcox probability greater than 0.99, and 83.7% taking a Willcox probability greater than 0.9 as identification threshold levels.

Aeromonas↗