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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 397 records · Page 22Linked to original sources

PubMedDate not supplied

Nephronophthisis in Finland: epidemiology and comparison of genetically classified subgroups.

Nephronophthisis--medullary cystic kidney disease is a progressive chronic tubulointerstitial nephritis leading to terminal renal failure. About two thirds of the patients with familial juvenile nephronophthisis, an autosomal recessive disease, have a homozygous deletion at the gene locus on 2q13. Through a nationwide search, 59 patients were ascertained in Finland. The incidence was 1:61,800 live births when calculated over a 20-year period. Of the patients, 17 came from four families showing dominant inheritance and 37 patients from 28 apparently recessive families when classified by family history, clinical features or presence of a deletion on 2q13. Two were considered as new dominant mutations; three sporadic patients could not be classified. The most significant difference between the patients with deletions, patients without deletions but having recessive family history, and patients belonging to families with dominant inheritance was the age at first symptoms, at the start of dialysis and at transplantation. These facts will be of help in determining the mode of inheritance of a sporadic patient without a deletion.

Adult↗

PubMed2004

Gene-expression profiling reveals distinct expression patterns for Classic versus Variant Merkel cell phenotypes and new classifier genes to distinguish Merkel cell from small-cell lung carcinoma.

Merkel cell carcinoma (MCC) is a rare aggressive skin tumor which shares histopathological and genetic features with small-cell lung carcinoma (SCLC), both are of neuroendocrine origin. Comparable to SCLC, MCC cell lines are classified into two different biochemical subgroups designated as 'Classic' and 'Variant'. With the aim to identify typical gene-expression signatures associated with these phenotypically different MCC cell lines subgroups and to search for differentially expressed genes between MCC and SCLC, we used cDNA arrays to profile 10 MCC cell lines and four SCLC cell lines. Using significance analysis of microarrays, we defined a set of 76 differentially expressed genes that allowed unequivocal identification of Classic and Variant MCC subgroups. We assume that the differential expression levels of some of these genes reflect, analogous to SCLC, the different biological and clinical properties of Classic and Variant MCC phenotypes. Therefore, they may serve as useful prognostic markers and potential targets for the development of new therapeutic interventions specific for each subgroup. Moreover, our analysis identified 17 powerful classifier genes capable of discriminating MCC from SCLC. Real-time quantitative RT-PCR analysis of these genes on 26 additional MCC and SCLC samples confirmed their diagnostic classification potential, opening opportunities for new investigations into these aggressive cancers.

Biomarkers, Tumor↗

PubMed2005

Concentrations, enrichment and predominant sources of Sb and other trace elements in size classified airborne particulate matter collected in Tokyo from 1995 to 2004.

APM was collected and trace elements existing in the particles were monitored since May 1995 in this study. APM sample was collected separately by size (d < 2 microm, 2-11 microm and >11 microm) on the roof of the university building (45 m above ground) in the campus of Faculty of Science and Engineering, Chuo University, Tokyo, Japan, using an Anderson low volume air sampler. The collected sample was digested by HNO3, H2O2 and HF using a microwave oven, and major elements (Na, Mg, Al, K, Ca and Fe) were measured by ICP-AES, and trace elements (Li, Be, Ti, V, Cr, Mn, Co, Ni, Cu, Zn, As, Se, Mo, Cd, Sb, Ba and Pb) were measured by ICP-MS. It was observed that the APM concentration was higher between the winter and the spring, compared to during the summer. The enrichment factor was calculated for each element in each set of APM (d < 2 microm, 2-11 microm and >11 microm). Seasonal trends of enrichment factors were examined, and the elements were classified into 3 groups according to the common seasonal behavior. It is likely that the elements in the same group have common origins. Toxic pollutant elements (Sb, Se, Cd, Pb and As) were found in small particles with d of <2 microm in concentrated levels. Antimony (Sb) had the highest enrichment factor, and the results suggested that Sb level in APM was extremely high. The origins of Sb were sought, and wastes from plastic incineration and brake pad wears of automobiles were suspected. Each set of APM (d < 2 microm, 2-11 microm and >11 microm) was classified by the shape, and the shape-dependent constituents of a single APM particle were quantitatively measured by SEM-EDX. High concentration of Sb was found in APM <2 microm and square particles. Particles less than 2 microm and square shaped particles were major particles produced by actual car braking experiments. From these experimental results it was concluded that the source of Sb in squared APM <2 microm is considered to be from brake pad wear.

Air Pollutants↗

PubMed2003

Tool to classify stool consistency: content validity and use by persons of diverse cultures.

Developing and testing the quality of a research instrument, including its ability to be used by culturally diverse persons, is an important methodological objective. The present study determined the content validity and feasibility of culturally diverse persons to use an instrument to classify stool consistency that has been employed in research on fecal incontinence. Five multidisciplinary clinicians experienced in assessing stool consistency determined the tool to possess content validity. Twenty-four foreign nationals of diverse cultures who spoke English as a second language (ESL) classified the consistency of nine stools using word only or word plus diagram descriptions. The agreement of the ratings of the participants were compared with the those of an experienced investigator. There was no significant difference between the ratings of participants using either type of description. There was good agreement between the classifications of the participants and those of the investigator. The findings of this study contribute to the quality of our instrument and support its use by culturally diverse persons.

Adult↗

PubMed2000

How the public classify complementary medicine: a factor analytic study.

OBJECTIVES: To see how lay people group or classify various CAM therapies. DESIGN: Nearly 600 adults rated 39 relatively familiar branches of complementary medicine on four dimensions: whether they had heard of it, whether they think they know how it works; whether they had tried it; and a rating of efficacy on a 10-point scale. RESULTS: As predicted those most heard of were acupuncture, aromatherapy, herbal medicine, hypnosis, massage and yoga while those with lowest ratings were autogenic training, ayurveda, biochemic tissue salts, chelation cell therapy and ozone therapy. A number of multivariate statistical techniques were used to attempt to investigate the perceived dimensional structure of the different therapies. Slightly different structures emerged depending on the question asked and the analysis computed. CONCLUSION: The 'bottom-up' empirically derived taxonomization of therapies was interpretable and showed 10 different factors. The issue of classifying or taxonomizing complementary medicines is discussed.

Adult↗

PubMed2002

Classifying seizures and epilepsy: a synopsis.

Seizures can have a number of clinical presentations. Epilepsy, the condition of recurrent unprovoked seizure, can also be categorized in a variety of ways and is associated with several conditions. Seizures and the epilepsies are classified most commonly by a system devised by the International League Against Epilepsy (ILAE) that employs clinical, electroencephalographic, and imaging data. The system has two broad divisions: focal and generalized for seizures and localization related and generalized for the epilepsies. This article surveys all seizure and epilepsy types according to the ILAE scheme. Limitations of the current categorization are discussed, and a recent new proposal for classifying seizures and epilepsy is demonstrated.

Epilepsy↗

PubMed1987

Histological features and recurrence of completely and incompletely healed gastric ulcers classified by the methylene blue dye method.

Histological features and recurrence of gastric ulcers classified as completely or incompletely healed by the methylene blue dye method were investigated. On chromo-endoscopic examination, complete healing was defined as a scarred area completely covered with granular patterns, while incomplete healing was defined as a scarred area surrounded only marginally by granular patterns. The methylene blue dye method was significantly more accurate than routine endoscopy for determining the histological completeness of healing. Recurrences were significantly more frequent in incompletely healed ulcers classified by the dye method than in completely healed ulcers. Heavy smoking, male sex, and location of ulcers were closely related to recurrence. Therapy should be continued until the healed ulcers are wholly covered by granular patterns, and physicians should encourage their patients to stop smoking.

Diagnostic Errors↗

PubMed1990

[The clinical manifestations of histologically classified malignant lymphomas in the ENT area].

For an optimum therapy of malignant lymphomas in the ENT region an extensive analysis of the interrelations of exact histological classification, clinical manifestation and prognosis is desirable. We therefore classified, according to various criteria, 57 patients (34 male, 23 female) aged between 17 and 88, in whom the first diagnosis of a malignant lymphoma was established at our department between 1970 and April 1989. Histologically, in 52 cases (91%) this concerned a non-Hodgkin lymphoma (NHL), in the other 5 cases Hodgkin's disease (HL). According to the "Kiel classification", 60% of the NHL displayed a high degree of malignancy, 36% a low one, while 4% could not be exactly classified histologically. Clinically (Ann Arbor classification), 27 patients with NHL were at stage I (with 21 at stage IE), 16 patients at stage II (with 14 at stage II E), and 9 patients at stage IV. The first manifestation was often extranodular (9 patients tonsil, 8 parotid gland, 8 base of tongue, 7 nasopharynx). A cervical lymph node enlargement was the first sign in 12 patients only. Four patients with NHL additionally developed a second malignancy (squamous cell carcinoma) of another localization. The 5-year survival rate was 81% at stage I, but there were no meaningful differences between stage II (51%) and stage IV (40%). Our study demonstrated that malignant lymphomas of the head and neck are primarily NHL which frequently affect an extranodular organ as a first manifestation. Moreover, malignant lymphomas in the ENT region seem to have a relatively good survival prognosis even in an advanced stage.

Adolescent↗

PubMed1988

The International Classification of Impairments, Disabilities and Handicaps: its usefulness in classifying and understanding biopsychosocial phenomena.

The International Classification of Impairments, Disabilities and Handicaps (ICIDH) was developed because of the growing awareness that ICD-9 failed to reflect many of the problems that people bring to health care systems. The ICIDH was designed to classify the consequences of disease such as the disruption of daily activity and the social disadvantage that accompany illness. However, since its introduction, the ICIDH has largely been ignored by psychiatry, despite its conceptual strength. In particular, it provides a framework for applying the biopsychosocial model and studying the phenomena of mental illness. The latter is an important issue because of clinical psychiatry's inherent weakness in distinguishing between symptoms of disease and the psychosocial consequences, a particular inadequacy of the DSM-III diagnostic criteria. The utility of the ICIDH is shown in the study of the phenomena of panic disorder and agoraphobia, where I conclude that agoraphobia should be classified as a disability/handicap and not a disorder.

Activities of Daily Living↗

PubMed1998

An observational method for classifying exposure to repetitive movements of the upper limbs.

This article presents and discusses a model for describing and evaluating the principal risk factors characterizing occupational exposure: frequency and repetitiveness of movements; use of force; type of posture and movements; distribution of recovery periods; and presence of other influential (additional) factors. For each risk factor, the author proposes a method of practical detection in the field, as well as criteria for classifying and interpreting the results based on a critical review of the available literature on the subject. Numerous examples are supplied to better illustrate the concepts presented. The various factors considered are classified using numbers or indexes, so that they can be integrated into a concise exposure index.

Arm↗

PubMed2002

Pre-menopausal women, classified as hypo- or hyperresponders, do not alter their LDL/HDL ratio following a high dietary cholesterol challenge.

BACKGROUND: Cholesterol is the dietary component that has elicited the most public interest in conjunction with coronary heart disease. However, the impact of excess dietary cholesterol intake on plasma cholesterol levels cannot be accurately predicted; therefore, its role in disease progression is not straightforward. Individual response variation can be due to factors such as ethnicity, hormonal status, obesity and genetic predisposition. OBJECTIVE: The purpose of this study was to evaluate the differences that occur within the plasma compartment of normolipidemic pre-menopausal women, classified based on their response to a high dietary cholesterol challenge. DESIGN: We recruited 51 pre-menopausal women (29 Caucasian and 22 of Hispanic origin) aged 18 to 49 years with initial plasma cholesterol concentrations ranging from 3.62 to 5.17 mmol/L. Using a cross-over research design, women were randomly allocated to an egg (640 mg additional dietary cholesterol per day) or placebo group (0 mg additional dietary cholesterol per day) initially, and the two 30 day periods were separated by a three-week washout. RESULTS: An initial evaluation of the ethnicity effects revealed elevations in both plasma LDL-C (p < 0.0001) and HDL-C (p < 0.001) concentrations in both Hispanics and Caucasians during the high dietary cholesterol period. However, these increases were not accompanied by a change in the LDL/HDL ratio. Subjects were then classified as hypo- (< 0.05 mmol/L increase in total plasma cholesterol per each additional 100 mg of dietary cholesterol consumed per day) or hyper-responders (> or =0.06 mmol/L increase in total blood cholesterol per each additional 100 mg of dietary cholesterol consumed per day), based on their reaction to the additional dietary cholesterol provided. Hypo-responders did not experience an increase in LDL-C or HDL-C during the egg period, while both lipoproteins were elevated in hyper-responders. However, the LDL/HDL ratio, an important parameter of coronary heart disease risk, was maintained for all subjects during the egg period independent of response. Furthermore, hyper-responders had higher concentrations of apo C-III (p < 0.001), apo B (p < 0.001) and cholesterol ester transfer protein (CETP) (p < 0.05) during this period. CONCLUSION: These data revealed that excess dietary cholesterol does not increase the risk of developing an atherogenic lipoprotein profile in pre-menopausal women, regardless of their response classification. Although the addition of 640 mg of cholesterol to the diet did result in an increase in plasma cholesterol in hyperresponders, the LDL/HDL ratio was maintained. This result, accompanied by increases in CETP activity, leads to the speculation that hyper-responders may process the excess cholesterol in the plasma compartment through an enhancement of the reverse cholesterol transport pathway. With this mechanism identified, further measurement of additional parameters is needed to verify this conclusion.

Adolescent↗

PubMed2004

A new approach in the BCI research based on fractal dimension as feature and Adaboost as classifier.

High rate classification of imagery tasks is still one of the hot topics among the brain computer interface (BCI) groups. In order to improve this rate, a new approach based on fractal dimension as feature and Adaboost as classifier is presented for five subjects in this paper. To have a comparison, features such as band power, Hjorth parameters along with LDA classifier have been taken into account. Fractal dimension as a feature with Adaboost and LDA can be considered as alternative combinations for BCI applications.

Algorithms↗

PubMed2001

Immunostaining for Met/HGF receptor may be useful to identify malignancies in thyroid lesions classified suspicious at fine-needle aspiration biopsy.

The receptor for hepatocyte growth factor (Met) is not expressed in the normal thyroid but it is overexpressed in most thyroid carcinomas. We evaluated whether Met immunostaining of cytological smears from fine-needle aspiration biopsy (FNAB) may be useful for the preoperative diagnosis of thyroid cancer. Notably, routine cytological examination often fails to distinguish well-differentiated follicular carcinomas and a proportion of papillary carcinomas (low-grade papillary carcinomas and papillary carcinomas follicular variant [FVPTC]) from benign lesions: all these lesions are usually classified as suspicious. We examined 80 thyroid lesions diagnosed as suspicious at cytology that had subsequently undergone surgery. The histologic diagnosis had been: papillary carcinomas (n = 14), FVPTC (n = 11), follicular carcinomas (n = 25), atypical follicular adenomas (n = 5), follicular adenomas (n = 20), and nodular goiters (n = 5). We also studied typical papillary carcinomas (n = 30) and nodular goiters (n = 10), all correctly diagnosed at cytology. In lesions classified suspicious at routine cytology, Met immunostaining was positive in 12 of 14 (85.7%) papillary carcinomas, 8 of 11 (72.7%) FVPTC, 7 of 25 (28%) follicular carcinomas, and 5 of 5 atypical adenomas. In contrast, none of the 25 lesions cytologically suspicious but benign at histology were positive. These data suggest that Met immunostaining of suspicious cytological smears are useful for identifying malignant lesions, especially those with a papillary histotype.

Adenocarcinoma, Follicular↗

PubMed2003

Estimating dataset size requirements for classifying DNA microarray data.

A statistical methodology for estimating dataset size requirements for classifying microarray data using learning curves is introduced. The goal is to use existing classification results to estimate dataset size requirements for future classification experiments and to evaluate the gain in accuracy and significance of classifiers built with additional data. The method is based on fitting inverse power-law models to construct empirical learning curves. It also includes a permutation test procedure to assess the statistical significance of classification performance for a given dataset size. This procedure is applied to several molecular classification problems representing a broad spectrum of levels of complexity.

Algorithms↗

PubMed2002

Paradigms of health and disease: a framework for classifying and understanding complementary and alternative medicine.

The number of complementary and alternative medicines (CAMs) being utilized by North America health care consumers is growing at an astounding rate. There is a need by both health care providers and consumers to categorize CAM in order to make meaningful comparisons and informed decisions on their use. Four paradigms of health and illness are proposed that classify medicines according to the basic assumptions of health and disease associated with each medicine. CAMs classified in the body paradigm are those that work through biologic mechanisms, or in other words, target biologic factors as the primary determinants of health. The mind-body paradigm extends the body paradigm to include factors such as stress, psychologic coping styles, and social supports as primary determinants of health and disease. The body-energy paradigm assumes health and disease are functions of the flow and balances of life energies. The body-spirit paradigm assumes that one or more transcendental aspects or personalities existing outside the limitations of the material universe can influence health and disease. It is postulated that there is a hierarchical relation among the four paradigms, such that each paradigm essentially subsumes the assumptions of the previous ones, but adds additional assumptions that qualify the previous ones. Implications of this framework for clarifying many contemporary issues in health care are discussed.

Attitude to Health↗

PubMed1983

Free erythrocyte protoporphyrin (FEP) II. The FEP test is clinically useful in classifying microcytic RBC disorders in adults.

Microcytic red blood cells (RBC) are commonly encountered in clinical medicine and are caused by disorders of heme synthesis [usually iron deficiency anemia (IDA) or anemia of chronic disease (ACD)] or disorders of globin synthesis (usually thalassemia syndromes or HbE). Using the clinical history and standard laboratory tests (hematocrit, per cent saturation of transferrin (% sat), serum ferritin, Hb electrophoresis, HBA2, and HbF) we classified 198 adults with microcytic RBC as follows: 48 IDA, 11 probable IDA, 11 iron-deficient erythropoiesis without anemia, 13 ACD, 42 alpha-thalassemia trait, 35 probable alpha-thalassemia trait, 20 beta-thalassemia trait, and 15 unclassified. In addition, we demonstrated that the FEP test reliably (83-90% of the time, depending on FEP methodology) classifies microcytic RBC states into disorders of heme synthesis vs. disorders of globin synthesis. Because of reliability and ease of measurement, we recommend the hematofluorometer FEP as the first step in the clinical laboratory evaluation of microcytic RBC disorders in both adults and children.

Adolescent↗

PubMed1993

Dot-plot comparisons by multivariate analysis (DOCMA): a tool for classifying protein sequences.

A method aimed at classifying protein sequences without resorting to pairwise alignment is presented. Called DOCMA (DOt-plot Comparisons by Multivariate Analysis), it is based on a multivariate analysis of the pairwise dot-plots between all the sequences in the set. The dot-plots are first simplified by considering only the projections of the 'diagonal' segments of similarity onto the axes. From these projections a data matrix is built, in which each column is representative of the comparisons of one given sequence with all the other ones. This data matrix is then transformed into a distance matrix by a chi-squared analysis, from which the coordinates of the sequences in an orthonormal Euclidean space are obtained. The sequences are finally classified by a dynamic clustering procedure followed by a search for strong clusters. Application of this method to protein families such as the globins, the cytochromes c and the aminoacyl-tRNA synthetases shows that it is quite effective in delineating subgroups that contain even distantly related sequences.

Algorithms↗

PubMed2006

Enhancing instance-based classification with local density: a new algorithm for classifying unbalanced biomedical data.

MOTIVATION: Classification is an important data mining task in biomedicine. In particular, classification on biomedical data often claims the separation of pathological and healthy samples with highest discriminatory performance for diagnostic issues. Even more important than the overall accuracy is the balance of a classifier, particularly if datasets of unbalanced class size are examined. RESULTS: We present a novel instance-based classification technique which takes both information of different local density of data objects and local cluster structures into account. Our method, which adopts the basic ideas of density-based outlier detection, determines the local point density in the neighborhood of an object to be classified and of all clusters in the corresponding region. A data object is assigned to that class where it fits best into the local cluster structure. The experimental evaluation on biomedical data demonstrates that our approach outperforms most popular classification methods. AVAILABILITY: The algorithm LCF is available for testing under http://biomed.umit.at/upload/lcfx.zip.

Algorithms↗