Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “classifier”

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 865 records · Page 48Linked to original sources
PubMed2004

Confocal scanning laser ophthalmoscopy classifiers and stereophotograph evaluation for prediction of visual field abnormalities in glaucoma-suspect eyes.

PURPOSE: To determine whether Heidelberg Retina Tomograph (HRT; Heidelberg Engineering, Dossenheim, Germany) classification techniques and investigational support vector machine (SVM) analyses can detect optic disc abnormalities in glaucoma-suspect eyes before the development of visual field abnormalities. METHODS: Glaucoma-suspect eyes (n = 226) were classified as converts or nonconverts based on the development of repeatable (either two or three consecutive) standard automated perimetry (SAP)-detected abnormalities over the course of the study (mean follow-up, approximately 4.5 years). Hazard ratios for development of SAP abnormalities were calculated based on baseline classification results, follow-up time, and end point status (convert, nonconvert). Classification techniques applied were HRT classification (HRTC), Moorfields Regression Analysis, forward-selection optimized SVM (SVM fwd) and backward elimination-optimized SVM (SVM back) analysis of HRT data, and stereophotograph assessment. RESULTS: Univariate analyses indicated that all classification techniques were predictors of the development of two repeatable abnormal SAP results, with hazards ratios (95% confidence interval [CI]) ranging from 1.32 (1.00-1.75) for HRTC to 2.0 (1.48-2.76) for stereophotograph assessment (all P < or = 0.05). Only SVM (SVM fwd and SVM back) analysis of HRT data and stereophotograph assessment were univariate predictors of the development of three repeatable abnormal SAP results, with hazard ratios (95% CI) ranging from 1.73 (1.16-2.82) for SVM fwd to 1.82 (1.19-3.12) for SVM back (both P < 0.007). Multivariate analyses including each classification technique individually in a model with age, baseline SAP pattern standard deviation [PSD], and baseline IOP indicated that all classification techniques except HRTC (P = 0.06) were predictors of the development of two repeatable abnormal SAP results with hazards ratios ranging from 1.30 (0.99, 1.73) for HRTC to 1.90 (1.37, 2.69) for stereophotograph assessment. Only SVM (SVM fwd and SVM back) analysis of HRT data and stereophotograph assessment were significant predictors of the development of three repeatable abnormal SAP results in multivariate analyses; hazard ratios of 1.57 (1.03, 2.59) and 1.70 (1.18, 2.51), respectively. SAP PSD was a significant predictor of two repeatable abnormal SAP results in multivariate models with all classification techniques, with hazard ratios ranging from 3.31 (1.39, 7.89) to 4.70 (2.02, 10.93) per 1-dB increase. CONCLUSIONS: HRT classifications techniques and stereophotograph assessment can detect optic disc topography abnormalities in glaucoma-suspect eyes before the development of SAP abnormalities. These data support strongly the importance of optic disc examination for early glaucoma diagnosis.

Adult↗
PubMed2001

Use of visual evoked-potential studies and EEG data to classify aggressive, explosive behavior of youths.

OBJECTIVE: Data from electroencephalograms (EEGs), including data from visual evoked-potential studies, were analyzed to assess their association with a specific type of explosive behavior in children and adolescents. METHODS: Data for 326 children and adolescents treated in a psychiatric clinic were examined. Eighty-two percent exhibited behavior consistent with intermittent explosive disorder, although diagnosis was not an inclusion criterion for the study. The presence of explosive behaviors was indicated by reports from the legal system, schools, parents, health care workers, and psychiatric intake interviews. A quantitative EEG and a series of pattern-reversal evoked-potential studies were administered to each patient. In these studies, children are shown a rapidly reversing checkerboard pattern or rapid flashes of light, and their brain waves (evoked potentials) are measured. RESULTS: Logistic regression indicated that patients who exhibited explosive behaviors were significantly more likely to produce high-amplitude P100 wave forms in the evoked-potential studies than patients who did not exhibit explosive behaviors. Forty-six percent of those with explosive behaviors met the clinically defined electrophysiological criteria for the high-amplitude P100 wave forms. CONCLUSIONS: The use of visual evoked-potential studies helped us classify a large subset of youths who exhibited out-of-control explosive behaviors. The findings suggest that a subgroup of individuals exhibiting explosive behaviors may have a predisposition for violent or explosive behavior that is an innate characteristic of their central nervous system. An understanding of the etiology of explosive behaviors permits the use of more appropriate intervention and treatment strategies.

Adolescent↗
PubMed2000

Vertical partial laryngectomy versus supracricoid partial laryngectomy for selected carcinomas of the true vocal cord classified as T2N0.

From an inception cohort of 204 patients with squamous cell carcinoma of the true vocal cord classified as T2N0 and a minimum of 3 years of follow-up, the authors compare the oncological and functional outcomes following vertical partial laryngectomy (group 1; 85 patients) and supracricoid partial laryngectomy (group 2; 119 patients). The 10-year actuarial survival estimate was 46.2% for group 1 and 66.4% for group 2. Survival was statistically more likely to be reduced (p = .019) in group 1 than in group 2. The 10-year actuarial local control estimate was 69.3% for group 1 and 94.6% for group 2. Local recurrence was statistically more likely to occur (p < .0001) in group 1 than in group 2. Salvage treatment resulted in an overall 94.1% local control rate and a 78.1% laryngeal preservation rate for group 1 and an overall 99.2% local control rate and a 94.9% laryngeal preservation rate for group 2. The 10-year actuarial nodal control estimate was 81.7% for group 1 and 93.7% for group 2. Nodal recurrence was statistically more likely to occur (p = .028) in group 1 than in group 2. The 10-year actuarial estimate for patients without distant metastasis was 84.6% for group 1 and 95.1% for group 2. Distant metastasis was statistically more likely to occur (p = .05) in group 1 than in group 2. The hospital mortality rate was 1.2% for group 1 and 0.8% for group 2. The incidence of permanent gastrostomy was 0% for group 1 and 2.4% for group 2. The incidence of permanent tracheostomy was 1.2% for group 1 and 2.4% for group 2. The incidence of completion laryngectomy due to functional problems was 1.2% for group 1 and 0.8% for group 2.

Actuarial Analysis↗
PubMedDate not supplied

Students classified as LD who received course substitutions for the college foreign language requirement: a replication study.

This replication study examined whether 158 college students classified as learning disabled (LD) who were granted course substitutions for the foreign language (FL) requirement would display significant cognitive and academic achievement differences when grouped by levels of IQ-achievement and achievement-achievement discrepancy and by level of performance on an FL aptitude test (Modern Language Aptitude Test; MLAT), phonological/orthographic processing measures, and in FL courses. The results showed that there were few differences among groups with differing levels of IQ-achievement or achievement-achievement discrepancy (i.e., < 1.0 SD, 1.0-1.49 SD, and > 1.50 SD) on MLAT and American College Testing (ACT) scores, graduating grade point average (GPA), or college FL GPA. The results also showed that between groups who scored at or above versus below the 15th percentile (i.e., < 1.0 SD) on the MLAT, there were no differences on measures of graduating GPA, college FL GPA, native language skill, ACT score, and Verbal IQ. Demographic findings showed that 44% of these petition students met a minimum IQ-achievement discrepancy criterion (> or = 1.0 SD) for classification as LD. These findings suggest that many traditional assumptions about LD and FL learning are likely to be false.

Adult↗
PubMedDate not supplied

Students classified as LD and the college foreign language requirement: a quantitative analysis.

This study was conducted to determine whether students classified as learning disabled (LD) who were permitted to substitute courses for the college foreign language (FL) requirement at one university would display significant cognitive and academic achievement differences when grouped by level of discrepancy between IQ and achievement, by discrepancy between achievement according to different measures, and by level of performance on phonological-orthographic processing measures, on the Modern Language Aptitude Test (MLAT), and in FL courses. Results showed that there were no differences among students with different levels of discrepancy (i.e., < 1.0 SD, 1.0-1.49 SD, and > 1.50 SD) on MLAT and American College Testing (ACT) scores, graduating grade point average (GPA) or college FL GPA. Results also showed that among students who scored below versus at or above the 25th percentile on phonological-orthographic processing measures, there were no differences on measures of IQ, ACT, MLAT, and GPA, as well as most measures of academic achievement. Implications for the use of the LD label to grant FL course substitutions or waivers, use of the MLAT in the diagnostic and course substitution/waiver process, and the validity and reliability of traditional criteria for the classification as LD are discussed.

Achievement↗
PubMedDate not supplied

The use of fixed- and random-effects models for classifying hospitals as mortality outliers: a Monte Carlo assessment.

BACKGROUND: There is an increasing movement towards the release of hospital "report-cards. "However, there is a paucity of research into the abilities of the different methods to correctly classify hospitals as performance outliers. OBJECTIVE: To examine the ability of risk-adjusted mortality rates computed using conventional logistic regression and random-effects logistic regression models to correctly identify hospitals that have higher than acceptable mortality. RESEARCH DESIGN: Monte Carlo simulations. MEASURES: Sensitivity, specificity, and positive predictive value of a classification as a high-outlier for identifying hospitals with higher than acceptable mortality rates. RESULTS: When the distribution of hospital specific log-odds of death was normal, random-effects models had greater specificity and positive predictive value than fixed-effects models. However, fixed-effects models had greater sensitivity than random-effects models. CONCLUSIONS: Researchers and policy makers need to carefully consider the balance between false positives and false negatives when choosing statistical models for determining which hospitals have higher than acceptable mortality in performance profiling.

Hospital Mortality↗
PubMedDate not supplied

Classifying binormal diagnostic tests using separation-asymmetry diagrams with constant-performance curves.

A method is proposed for classifying diagnostic tests that have underlying binormal distributions. The method involves using the parameters that characterize these distributions as axes of a two-dimensional graph called a separation-asymmetry (S-A) diagram. Each point on an S-A diagram corresponds to a possible diagnostic test. The diagram also has superimposed on it any of three possible families of curves of constant performance: curves of constant area under the ROC graph (iso-AUR), curves of constant overlap area (iso-OA), and curves of constant maximum information (iso-MaxInfo). Thus, the performance of any test can be determined immediately by identifying the iso-performance curve of the desired type that passes through the corresponding point of the S-A diagram. The concept of "eccentric" diagnostic tests is defined and incorporated into the S-A diagrams. The classification scheme is applied to 28 diagnostic tests. Excellent agreement is found in the ranking between the iso-OA and iso-MaxInfo measures of performance, but the iso-AUR produces markedly different results. Only three of the 28 tests were found to be eccentric. Several other interesting patterns emerged.

Bias↗
PubMed1995

Defining and classifying learning disabilities and attention-deficit/hyperactivity disorder.

This paper provides an overview of current conceptualizations of learning disabilities and ADHD, a conceptual framework critical for defining and classifying each disorder and for distinguishing each disorder from the other and from other, less common problems of childhood. At a most basic level, reading disability or dyslexia (the most common and best defined of the learning disabilities) and ADHD represent two distinct disorders that may frequently cooccur in the same unfortunate child but that can be clearly distinguished from one another. Reading disability represents a disorder of cognitive functioning. In contrast, ADHD is defined by the child's behavior as perceived by the child's parents and teachers; ADHD thus refers to a disorder affecting primarily the behavioral domain. Within the last decade, considerable progress has been made in our understanding of reading and reading disability. Converging evidence from several lines of investigation now indicates that reading ability conforms to a normal distribution model, so that there is a continuum of reading ability and reading disability. Children along this continuum differ by degree but not in kind. Cutoff points may be instituted to segment this continuous distribution, but these will be arbitrary and will not reflect any natural joints in nature; there is no second mode or "hump" in the distribution of reading ability. The normal model of reading and reading disability indicates that reading disability is related to normal reading ability, that there is a seamless transition from good to poor reading ability. Awareness of this relationship is critical to our approach to understanding the basis of reading disability.(ABSTRACT TRUNCATED AT 250 WORDS)

Adolescent↗
PubMed2003

Classifying the findings in qualitative studies.

A key task in conducting research integration studies is determining what features to account for in the research reports eligible for inclusion. In the course of a methodological project, the authors found a remarkable uniformity in the way findings were produced and presented, no matter what the stated or implied frame of reference or method. They describe a typology of findings, which they developed to bypass the discrepancy between method claims and the actual use of methods, and efforts to ascertain its utility and reliability. The authors propose that the findings in journal reports of qualitative studies in the health domain can be classified on a continuum of data transformation as no finding, topical survey, thematic survey, conceptual/thematic description, or interpretive explanation.

Data Interpretation, Statistical↗
PubMedDate not supplied

Classifying the effectiveness of Veterans Affairs guideline implementation approaches.

Hospitals use numerous guideline implementation approaches with varying success. Approaches have been classified as consistently, variably, or minimally effective, with multiple approaches being most effective. This project assesses the Department of Veterans Affairs (VA) use of effective guideline implementation approaches. A survey of 123 VA quality managers assessed the approaches used to implement the chronic obstructive pulmonary disease, diabetes mellitus, congestive heart failure, and major depressive disorder guidelines. Approaches were categorized based on their effectiveness, and the total number of approaches used was calculated. Commonly used approaches were clinical meetings, summaries, and revised forms. Consistently and minimally effective approaches were used most frequently. Most hospitals used 4-7 approaches. Odds ratios demonstrated that consistently effective approaches were paired with minimally and variably effective approaches. The frequent use of consistently effective approaches and multiple approaches benefits VA adherence. However, VA hospitals should consider selective combinations of approaches to ensure the use of the most effective implementation methods.

Aged↗
PubMedDate not supplied

Work organization, area labor-market characteristics, and depression among U.S. nursing home workers: a cross-classified multilevel analysis.

Associations between forms of work organization that follow globalization and depression were examined in U.S. nursing home assistants. A cross-sectional study of 539 nurse assistants in 49 nursing homes in three states in 2000 assessed nursing home ownership type, managerial style, wage policy, nurse assistants' emotional stresses, and area labor-market characteristics (county income inequality, median household income, and social capital) in relation to the prevalence of depression among the nurse assistants. A cross-classified multilevel analysis was used. For-profit ownership, emotional strain, managerial pressure, and lack of seniority pay increases were associated with depression. Labor-market characteristics were not associated with depression once work organization was taken into account. The deregulation of the nursing home industry that accompanies globalization is likely to adversely affect the mental health of nursing home assistants.

Adult↗
PubMed2005

Classifying health-related quality of life outcomes of total hip arthroplasty.

BACKGROUND: Primary total hip arthroplasty (THA) is an effective treatment for hip osteoarthritis, assessed by whatever distribution-based measures of responsiveness. Yet, the group level evaluation has provided very little evidence contributes to our understanding of the large variation of treatment outcome. The objective is to develop criteria that classify individual treatment health related quality of life (HRQOL) outcome after primary THA, adjusted by preoperative scores. METHODS: We prospectively measured 147 patients' disease specific HRQOL on the date of consultation and 12 months post operation by Western Ontario McMaster Universities Osteoarthritis Index (WOMAC). Regression models were used to determine the "expected" outcome for a certain individual baseline score. The ceiling effect of WOMAC measurement is addressed by implementing a left-censoring method. RESULTS: The classification criteria are chosen to be the lower boundary of the 95% confidence interval (CI) of the estimated median from the regression. The robustness of the classification criteria was demonstrated using the Monte-Carlo simulation. CONCLUSION: The classification criteria are robust and can be applied in general orthopaedic research when the sample size is reasonable large (over 500).

Aged↗
PubMed2004

An approach to classifying human resources constraints to attaining health-related Millennium Development Goals.

BACKGROUND: For any wide-ranging effort to scale up health-related priority interventions, human resources for health (HRH) are likely to be a key to success. This study explores constraints related to human resources in the health sector for achieving the Millennium Development Goals (MDGs) in low-income countries. METHODS AND FRAMEWORK: The analysis drew on information from a variety of publicly-available sources and principally on data presented in published papers in peer-reviewed journals. For classifying HRH constraints an analytical framework was used that considers constraints at five levels: individual characteristics, the health service delivery level, the health sector level, training capacities and the sociopolitical and economic context of a country. RESULTS AND DISCUSSION: At individual level, the decision to enter, remain and serve in the health sector workforce is influenced by a series of social, economic, cultural and gender-related determinants. For example, to cover the health needs of the poorest it is necessary to employ personnel with specific social, ethnic and cultural characteristics. At health-service level, the commitment of health staff is determined by a number of organizational and management factors. The workplace environment has a great impact not only on health worker performance, but also on the comprehensiveness and efficiency of health service delivery. At health-sector level, the use of monetary and nonmonetary incentives is of crucial importance for having the accurate skill mix at the appropriate place. Scaling up of priority interventions is likely to require significant investments in initial and continuous training. Given the lead time required to produce new health workers, such investments must occur in the early phases of scaling up. At the same time coherent national HRH policies are required for giving direction on HRH development and linking HRH into health-sector reform issues, the scaling-up of priority interventions, poverty reduction strategies, and training approaches. Multisectoral collaboration and the sociopolitical and economic context of a country determine health sector workforce development and potential emigration. CONCLUSIONS: Key determinants of success for achieving international development goals are closely related to human-resource development.

Journal Article↗
PubMed2006

Mining, compressing and classifying with extensible motifs.

BACKGROUND: Motif patterns of maximal saturation emerged originally in contexts of pattern discovery in biomolecular sequences and have recently proven a valuable notion also in the design of data compression schemes. Informally, a motif is a string of intermittently solid and wild characters that recurs more or less frequently in an input sequence or family of sequences. Motif discovery techniques and tools tend to be computationally imposing, however, special classes of "rigid" motifs have been identified of which the discovery is affordable in low polynomial time. RESULTS: In the present work, "extensible" motifs are considered such that each sequence of gaps comes endowed with some elasticity, whereby the same pattern may be stretched to fit segments of the source that match all the solid characters but are otherwise of different lengths. A few applications of this notion are then described. In applications of data compression by textual substitution, extensible motifs are seen to bring savings on the size of the codebook, and hence to improve compression. In germane contexts, in which compressibility is used in its dual role as a basis for structural inference and classification, extensible motifs are seen to support unsupervised classification and phylogeny reconstruction. CONCLUSION: Off-line compression based on extensible motifs can be used advantageously to compress and classify biological sequences.

Journal Article↗
PubMed2001

Diagnoses and treatments in health-classified fattening herds rearing pigs all in-all out.

This study describes diseases encountered, medications used and veterinary involvement in all in--all out finishing herds belonging to one pork production system. The finishing herds had a particular management and housing regime. The pigs originated from health classified farrowing units. Information on 207,442 pigs was collected from 595 log books. Altogether 91% of the pigs received no treatments. Four percent of the batches of pigs were given antimicrobial mass medications. The local veterinarian visited the herds on average 2.6 times during the finishing period and made the diagnoses in more than half of the cases. At least one pig was affected with arthritis or tail biting in more than half of the batches, whereas locomotory diseases were recorded in one third of the batches. All other diagnoses were encountered in 1%-13% of the batches. Only a few pigs were treated individually in the affected groups. Antimicrobial drugs were given to 8% and other medicines to 0.7% of the pigs. The diagnosis was missing at least for one pig in 29% of the batches and the information about the medicine use in 8% of the treatments was missing. The study shows that it is possible to rear finishing pigs with only a small proportion of the animals needing treatments. The need of mass medications was low, because infectious diseases affecting the whole herd were uncommon. The recommendations for antimicrobial use given by the authorities had been followed quite well. The farmers and the veterinarians should be educated in order to realise the importance of proper record keeping.

Animal Husbandry↗
PubMed2006

Mechanisms of critical illness--classifying microcirculatory flow abnormalities in distributive shock.

Over 30 years ago Weil and Shubin proposed a re-classification of shock states and identified hypovolemic, cardiogenic, obstructive and distributive shock. The first three categories have in common that they are associated with a fall in cardiac output. Distributive shock, such as occurs during sepsis and septic shock, however, is associated with an abnormal distribution of microvascular blood flow and metabolic distress in the presence of normal or even supranormal levels of cardiac output. This Bench-to-bedside review looks at the recent insights that have been gained into the nature of distributive shock. Its pathophysiology can best be described as a microcirculatory and mitochondrial distress syndrome, where time and therapy form an integral part of the definition. The clinical introduction of new microcirculatory imaging techniques, such as orthogonal polarization spectral and side-stream dark-field imaging, have allowed direct observation of the microcirculation at the bedside. Images of the sublingual microcirculation during septic shock and resuscitation have revealed that the distributive defect of blood flow occurs at the capillary level. In this paper, we classify the different types of heterogeneous flow patterns of microcirculatory abnormalities found during different types of distributive shock. Analysis of these patterns gave a five class classification system to define the types of microcirculatory abnormalities found in different types of distributive shock and indicated that distributive shock occurs in many other clinical conditions than just sepsis and septic shock. It is likely that different mechanisms defined by pathology and treatment underlie these abnormalities observed in the different classes. Functionally, however, they all cause a distributive defect resulting in microcirculatory shunting and regional dysoxia. It is hoped that this classification system will help in the identification of mechanisms underlying these abnormalities and indicate optimal therapies for resuscitating septic and other types of distributive shock.

Critical Illness↗
PubMed2017

Drug target ontology to classify and integrate drug discovery data.

BACKGROUND: One of the most successful approaches to develop new small molecule therapeutics has been to start from a validated druggable protein target. However, only a small subset of potentially druggable targets has attracted significant research and development resources. The Illuminating the Druggable Genome (IDG) project develops resources to catalyze the development of likely targetable, yet currently understudied prospective drug targets. A central component of the IDG program is a comprehensive knowledge resource of the druggable genome. RESULTS: As part of that effort, we have developed a framework to integrate, navigate, and analyze drug discovery data based on formalized and standardized classifications and annotations of druggable protein targets, the Drug Target Ontology (DTO). DTO was constructed by extensive curation and consolidation of various resources. DTO classifies the four major drug target protein families, GPCRs, kinases, ion channels and nuclear receptors, based on phylogenecity, function, target development level, disease association, tissue expression, chemical ligand and substrate characteristics, and target-family specific characteristics. The formal ontology was built using a new software tool to auto-generate most axioms from a database while supporting manual knowledge acquisition. A modular, hierarchical implementation facilitate ontology development and maintenance and makes use of various external ontologies, thus integrating the DTO into the ecosystem of biomedical ontologies. As a formal OWL-DL ontology, DTO contains asserted and inferred axioms. Modeling data from the Library of Integrated Network-based Cellular Signatures (LINCS) program illustrates the potential of DTO for contextual data integration and nuanced definition of important drug target characteristics. DTO has been implemented in the IDG user interface Portal, Pharos and the TIN-X explorer of protein target disease relationships. CONCLUSIONS: DTO was built based on the need for a formal semantic model for druggable targets including various related information such as protein, gene, protein domain, protein structure, binding site, small molecule drug, mechanism of action, protein tissue localization, disease association, and many other types of information. DTO will further facilitate the otherwise challenging integration and formal linking to biological assays, phenotypes, disease models, drug poly-pharmacology, binding kinetics and many other processes, functions and qualities that are at the core of drug discovery. The first version of DTO is publically available via the website http://drugtargetontology.org/ , Github ( http://github.com/DrugTargetOntology/DTO ), and the NCBO Bioportal ( http://bioportal.bioontology.org/ontologies/DTO ). The long-term goal of DTO is to provide such an integrative framework and to populate the ontology with this information as a community resource.

Biological Ontologies↗