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 109 records · Page 6Linked to original sources

PubMed1991

[Rough sets theory in structure-activity relationship analysis of quaternary pyridinium compounds].

Relationship between chemical structure and antimicrobial activity of 53 quaternary pyridinium compounds is analysed using the theory of rough sets. The compounds are described by 8 attributes concerning structure and are divided into 5 classes of activity. The description builds up an information system. Using the rough sets approach a smallest set of attributes significant for a high quality of classification has been found. A decision algorithm has been derived from the information system showing important relations between structure and activity. It may be helpful in supporting decisions concerning synthesis of new antimicrobial compounds.

Algorithms↗

PubMed1991

[Semi-automatic TNM classification of malignant tumors with the ESTER system exemplified by the larynx].

Classification of tumours according to the TNM scheme has been accepted worldwide. However, vague baseline assessments and borderline cases render a comparison of the outcome on the basis of TNM classification impossible. Therefore we integrated the TNM rules as a new algorithm into an existing expert system for determining therapy. Thus, every tumour documented with the ESTHER system is automatically classified according to current TNM rules. The program is designed to cope with future changes of the TNM system: raw data are used for classification so that only the algorithms need to be modified.

Expert Systems↗

PubMedDate not supplied

[Assessment of the degree of severity of radiation lesions in dogs using densitometric-geometric parameters of the blood lymphocytes].

Changes in densitometric-geometric parameters of lymphocyte nuclei of dog peripheral blood detected at early times (6 and 24 H) following gamma irradiation with 2.5 and 6.0 Gy are given a composite description. Using densitometric-geometric parameters the authors have developed an algorithm allowing for a 90% accuracy in the classification of objects according to the severity of radiation affection.

Algorithms↗

PubMed1979

A national study of medical and surgical specialties. III. An empirical approach to the classification of patient care.

A major feature of a national survey of medical and surgical specialties is the development and application of an algorithm for classifying patient care services provided by physicians. The care classification reflects much of prevailing opinion regarding what constitutes primary and nonprimary care. The classification system provides a powerful tool for the analysis of patient care services, since it is based on conditions of access to care, the physician's role in providing the care, measures associated with continuity of care, and a proxy measure of comprehensiveness of care. Furthermore, it is based on the recordings by physicians of actual patient-encounter characteristics and is not operationally dependent on physician characteristics or propensities.

Cardiology↗

PubMed2025

Hierarchical Multi-Label Classification With Gene-Environment Interactions in Disease Modeling.

In biomedical studies, gene-environment (G-E) interactions have been demonstrated to have important implications for analyzing disease outcomes beyond the main G and main E effects. Many approaches have been developed for G-E interaction analysis, yielding important findings. However, hierarchical multi-label classification, which provides insightful information on disease outcomes, remains unexplored in G-E analysis literature. Moreover, unlabeled data are commonly observed in practical settings but omitted by many existing methods of hierarchical multi-label classification. In this study, we consider a semi-supervised scenario and develop a novel approach for the two-layer hierarchical response with G-E interactions. A two-step penalized estimation is then proposed using an efficient expectation-maximization (EM) algorithm. Simulation shows that it has superior performance in classification and feature selection. The analysis of The Cancer Genome Atlas (TCGA) data on lung cancer demonstrates the practical utility of the proposed method. Overall, this study can fill the important knowledge gap in G-E interaction analysis by providing a widely applicable framework for hierarchical multi-label classification of complex disease outcomes.

Humans↗

PubMedDate not supplied

[Numerical taxonomy of the genus Desulfovibrio by group analysis].

The Desulfovibrio genus has a particular interest because it includes the microorganisms connected with the corrosion produced microbiologically. The taxonomy of the genus shows disadvantages due to its metabolical and physiological characteristics. In this paper, 14 strains of the Desulfovibrio type were studied from the metabolical point of view. Numeric taxonomy was carried out according to the Group Analysis method, using and comparing the change possibilities of the method. The Consensus Method was also applied. The results obtained indicate a low metabolic activity of the strains with regard to the number of compounds which can be used as energy source. The taxonomic method showed a better structure with more clear divisions, corresponding to Simple Matching coefficient (which coincides with other symmetric coefficients and with the distance coefficient) with average bond (UPGMA). It is estimated that the present classification will vary in time with new strains with different metabolic characteristics. The two groups of bacteria correspond to those with more and less degrading ability.

Algorithms↗

PubMed2026

A nonlinear multi-omics data integration and classification model based on pathway self-attention and graph convolutional networks.

The abundance of omics data has significantly advanced the development of multi-omics data integration techniques. Non-linear embedding approaches for data integration have gradually become the mainstream in multi-omics research, as these approaches can substantially improve cancer analysis by enhancing the quality of the embeddings. However, current multi-omics data integration methods are typically confined to omics measurements, neglecting domain-specific prior knowledge encompassing biological pathways. In this study, we proposed a multi-omics integrated classification model, PathTransGCN, based on pathway self-attention and graph convolutional networks (GCN). The model integrated biological pathway information into multi-omics data analysis with the aim of enhancing the accuracy of cancer classification. Multi-omics data for breast cancer (BRCA), non-small cell lung cancer (NSCLC), and low-grade glioma (LGG) were obtained from The Cancer Genome Atlas (TCGA) and UCSC Xena databases. These data included gene mutations, DNA methylation, copy number variations, and gene expression, and were used to assess the model's generalizability across different cancers. First, PathTransGCN employed a pathway self-attention module to learn latent representations of samples across different pathways, thereby obtaining multi-omics integration vectors. Concurrently, a patient similarity network (PSN) was constructed using the similarity network fusion (SNF) approach. Second, the integrated vectors and the PSN were jointly fed into a GCN for end-to-end training, enabling precise classification of cancer subtypes. Through multi-omics data analysis of the BRCA dataset, PathTransGCN outperformed several popular algorithms (such as MoGCN and DeePathNet) in the five-class classification of cancer subtypes, achieving an accuracy rate of 87.6% and an F1 score of 86.4%. Moreover, the model demonstrated robust generalization capabilities across both NSCLC and LGG datasets, while effectively identifying key disease-associated biomarkers at the pathway level. Experimental results demonstrate that PathTransGCN exhibits outstanding performance in integrating omics data and delivering interpretable classification outcomes, presenting significant potential for clinical applications.

Humans↗

PubMedDate not supplied

Structure analysis and classification of cervical cells using a processing system based on TV.

This paper presents preliminary results of a cell classification experiment using a new approach for feature extraction. The algorithm takes into account the special requirements of a fast parallel processing system (processor-oriented algorithms). A cell image is described by several hundred features derived from the nucleus only. The most significant features with respect to classification are determined by statistical analysis. Applying principal axis transform, a new feature set is computed, reduced considerably in dimensions. The data base (1,925 cell images of Papanicolaou-stained cervical specimens) was divided into a training set (963 images) and a test set (962 images). The classification results of the test set show that the recognition rate for the two-class problem (normal, suspicious) is better than 91%, using only ten morphologic features.

Cervix Mucus↗

PubMed1990

[Large bowel cancer: prognostic factors, surgical treatments and their results].

Although the classification proposed by Dukes has been repeatedly modified, causing unnecessary confusion, his original concept remains unrefuted; cancer penetration through the bowel wall and lymph node metastasis are two major prognostic factors, of which nodal metastasis represents a more advanced stage. However, the results of our exhaustive computer analyses did not support this concept, and better classifications may be developed using our computer algorithm, enabling us to refine the indication for extensive surgery or limited resection. There are two trends of surgical treatment in Japan. One is an attempt to extend the area of resection including the paraaortic and parailiac nodes, and also iliac vessels. Patients treated by this method show a higher survival rate if compared with historical controls in Japan. However, extensive surgery of the rectum is associated with poor quality of life with bladder and anal dysfunctions as well as sexual impotence. The other trend is to limit the extent of resection and minimize the functional defect. The organs thus saved include the sphincter and autonomic nerves. The results are almost comparable with those of more radical surgery. With aggressive re-resection of recurrent tumors in the liver, lungs, lymph nodes and local areas, the number of long-term survivors is now increasing who would otherwise have died.

Colorectal Neoplasms↗

PubMed1989

Automated rule based graded analysis of ambulatory cassette EEGs.

We describe algorithms, developed on a PDP-11/73 microcomputer, which identify spikes/sharp waves (STs), spike-and-wave complexes (SSWs), artifacts and background activity in 4-channel ambulatory EEGs. The algorithms were trained using 40 database segments. Time domain/mimetic methods were used and semantic rules, based on morphology and multi-channel contextual information, were developed to mimic the principles used in visual interpretation. The likelihood of STs/SSWs being genuine was graded from 10 to 1. This approach avoids forced classification of each event as genuine ST/SSW or not. The algorithms were then evaluated using 60 independent segments. STs/SSWs graded greater than 7 had significantly higher probability (P less than 0.005) of being genuine than those graded less than or equal to 7. Less than 4% of STs/SSWs identified by both electroencephalographers were missed. None was distinct. All 113 artifacts resembling STs/WWs were graded less than or equal to 7. Classification of 969/1117 (86%) waves in the background matched that of one electroencephalographer. The algorithms can be extended to 8- or more-channel EEGs.

Algorithms↗

PubMed1975

Evaluation and selection of optimal solvents and solvent combinations in thin-layer chromatography. Application of the method to basic drugs.

A series of simple mathematical techniques for the evaluation of solvents and solvent combinations in thin-layer chromatography have been investigated. A strategy for the rapid selection of the optimum combination is proposed. It uses classification procedures based on calculation of the similarity between systems. The classification is carried out using a simple graph-theoretical procedure (Kruskal's algorithm) or numerical taxonomy. The selection of optimal sets from the clusters which appear in the classification is based on the information content as derived from Shannon's equation. The method has been applied to an RF data set for basic drugs. It is concluded that these methods indeed allow the selection of optimal systems or combination of systems.

Chromatography, Thin Layer↗

PubMed1991

Continuous personnel scheduling algorithms: a literature review.

Hospitals frequently use personnel scheduling options as recruiting and retention instruments. The successful application of these personnel scheduling tools, whether developed in-house or purchased from vendors, requires appreciation of the interrelationships of three basic manpower decisions--staffing, personnel scheduling, and allocation. This article introduces these basic relationships and their influence on the development of satisfactory personnel schedules. Next, it reviews published personnel scheduling algorithms, applicable to hospital operations, within the context of the three manpower decisions. It is proposed that scheduling algorithms be classified by type of schedule produced (cyclic or noncyclic); and technique used (heuristic, mathematical programming, or self-scheduling). The characteristics of each classification are discussed. Considerations for the development of new personnel scheduling algorithms are also presented.

Algorithms↗

PubMed2025

acmgscaler: an R package and Colab for standardized gene-level variant effect score calibration within the ACMG/AMP framework.

MOTIVATION: A genome-wide variant effect calibration method was recently developed under the guidelines of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology (ACMG/AMP), following ClinGen recommendations for variant classification. While genome-wide approaches offer clinical utility, emerging evidence highlights the need for gene- and context-specific calibration to improve accuracy. Building on previous work, we have developed an algorithm tailored to converting functional scores from both multiplexed assays of variant effects (MAVEs) and computational variant effect predictors (VEPs) into ACMG/AMP evidence strengths. RESULTS: Our method is designed to deliver consistent performance across different genes and score distributions, with all variables adaptively determined from the input data, preventing selective adjustments or overfitting that could inflate evidence strengths beyond empirical support. To facilitate adoption, we introduce acmgscaler, a lightweight R package and a plug-and-play Google Colab notebook for the calibration of custom datasets. This algorithmic framework bridges the gap between MAVEs/VEPs and clinically actionable variant classification. AVAILABILITY AND IMPLEMENTATION: The R package and Colab notebook are available at https://github.com/badonyi/acmgscaler.

Software↗

PubMed1989

A one-layer model of laser-induced fluorescence for diagnosis of disease in human tissue: applications to atherosclerosis.

This paper describes a general model of tissue fluorescence which can be used both to: 1) determine chemical and physical properties of the tissue, and 2) design an optimal algorithm for clinical diagnosis of tissue composition. This model is based on a picture of tissue as a single, optically thick layer, in which fluorophores and absorbing species are homogeneously distributed. As a specific example, the model is applied to the laser induced fluorescence (LIF) of normal and atherosclerotic human aorta using 476 nm excitation. Methods for determining the relevant attenuation and fluorescence lineshapes are detailed, and these lineshapes are used to apply the model to data from 148 samples. The model parameters are related to the concentrations of the major arterial chromophores: structural proteins, hemoglobin and ceroid. In addition, the model parameters are used to derive diagnostic algorithms for the presence of atherosclerosis. Utilizing a binary classification scheme, the presence or absence of pathology was determined correctly in 88 percent of cases.

Algorithms↗

PubMedDate not supplied

In vivo myeloarchitectonic analysis of human striate and extrastriate cortex using magnetic resonance imaging.

A primary goal of investigations into the organization of human cerebral cortex is to determine the functional specificity of architectonic regions. This includes the correlation of neurobehavioral deficits with neuropathological data for clinical diagnosis and treatment, and the identification of active brain regions using functional neural imaging techniques, such as positron emission tomography, electroencephalographic and magnetoencephalographic (EEG and MEG) source localization algorithms, and direct cortical stimulation. Currently, the architectonic classification of a cortical region identified by these methods is inferred from the comparison of its cerebral topographic position to cytoarchitectonic brain atlases. However, substantial intersubject variability in the position of cytoarchitectonic regions with respect to cerebral topographic landmarks may lead to errors in this procedure. An alternative method is presented here, which uses magnetic resonance (MR) imaging to identify myeloarchitectonic regions of isocortex directly by estimating the relative concentration of myelin within cortical laminae. This high-resolution MR protocol is used to identify striate cortex (Brodmann's area 17) and extrastriate cortex in vivo. Correspondence of MR signal intensity with myeloarchitectonic data from a postmortem brain confirms this identification. As MR imaging technology improves, this noninvasive method has the potential to identify and discriminate among at least 50 cortical regions in the living human brain.

Female↗

PubMed1992

Assessing and understanding patient risk.

Nonsteroidal anti-inflammatory drug (NSAID) gastropathy is the most frequent and one of the most severe drug side effects in the United States. NSAID-associated gastropathy has been estimated to account for at least 7600 deaths and 76000 hospitalizations each year in the United States alone. Hospitalizations in rheumatoid arthritis patients occurred in 1.6% of patients; for patients with osteoarthritis the incidence appears to be substantially lower. This is based on a consecutive series of 3000 patients with rheumatoid arthritis who were followed prospectively for an average of five years by ARAMIS, the Arthritis, Rheumatism and Aging Medical Information System. Multivariate analyses assessing risk factors for serious gastrointestinal (GI) events were performed on 1694 rheumatoid arthritis patients taking NSAIDs. The most important risk factors of higher age, use of prednisone, previous NSAID GI side effects, prior GI hospitalization, functional disability (based on the American Rheumatism Association classification), and NSAID dose are variables in an algorithm which estimates the risk of a serious GI event occurring in the next 12 months. Knowledge of risk factors and their interrelationships provides a tool for identifying patients at high risk and guides therapeutic decisions.

Aging↗

PubMed1990

Cluster analysis for automatic image segmentation in dynamic scintigraphies.

An original and entirely automatic algorithm is proposed to select regions of interest (ROIs) on dynamic scintigrams. This algorithm is based on factor analysis and on cluster analysis. It consists of first extracting the orthogonal factor images of the series using factor analysis of correspondence. These factor images are then automatically segmented in ROIs using a hierarchical ascendant classification procedure. The distance used for the classification is the 'minimum added intra-class variance' distance. This algorithm has been implemented on a fast computer dedicated to nuclear medicine (Nodecrest Micas V system). The time of calculation on 1000 pixels from 40 images is less than 5 min when three factor images are used. This algorithm is validated using a numerical phantom and is illustrated using renal (99Tcm DTPA) and cardiac (equilibrium gated angiography) dynamic scintigraphies. The results show that the algorithm is able to recognize the bladder, the renal cavities and the renal parenchyma on the renal series, and the ventricules and the atria on the cardiac series.

Algorithms↗

PubMed1991

An epidemiologic evaluation of two diagnostic classification schemes for temporomandibular disorders.

Few diagnostic classification schemes for temporomandibular disorders (TMD) have been applied systematically to examine the prevalence of various subtypes of TMD in clinic or community populations. In this study, computer algorithms were developed for classifying subjects according to the scheme of Eversole and Machado (1985) and a classification scheme recently developed in our own research at the University of Washington. The diagnostic algorithms were applied to clinical examination data for (1) persons without TMD pain (community controls) and (2) persons reporting TMD pain in the prior 6 months (community subjects with pain), identified in a random sample survey of a health maintenance organization (HMO) population, as well as (3) clinic patients seeking treatment for TMD through the same HMO. Prevalence rates for myofascial pain dysfunction in clinic patients were much higher under the University of Washington approach, whereas rates of internal derangement (type I) and degenerative joint disease were similar under the two schemes. These similar prevalence rates were not, however, accompanied by high concordance between the two schemes. These results highlight the complexities of differential diagnosis of TMD in field research, and suggest that further evaluation of alternative diagnostic schemes is warranted.

Adolescent↗