SEARCH · PubMed Health

Results for “Multiple Classification Analysis”

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 343 records · Page 19Linked to original sources

PubMed2006

Gender differences in self-rated and partner-rated multiple intelligences: a Portuguese replication.

The authors examined gender differences and the influence of intelligence quotient (IQ) test experience in the self and partner estimation of H. Gardner's (1999) 10 multiple intelligences. Portuguese students (N = 190) completed a brief questionnaire developed on the basis of an instrument used in previous research (A. Furnham, 2001). Three of the 10 self-estimates yielded significant gender differences. Men believed they were more intelligent than were women on mathematical (logical), spatial, and naturalistic intelligence. Those who had previously completed an IQ test gave higher self-estimates on 2 of the 10 estimates. Factor analysis of the 10 and then 8 self-estimated scores did not confirm Gardner's 3-factor classification of multiple intelligences in this sample.

Adult↗

PubMed2003

Applications of image analysis to anatomic pathology: realities and promises.

Image Analysis in Pathology is viewed as an ancillary method meant to provide objective support in the resolution of difficult problems. Its Achilles heel is the process of nuclear segmentation (delimitation of the nuclear membrane) which is extremely difficult in pathology materials. Although interactive segmentation procedures are available no reliable fully automatic method has been described. The only application of image analysis that has truly succeeded in Pathology is DNA ploidy measurement. A very desirable application is the quantitation of immunohistochemical markers, which is technically challenging, has been resolved only in certain cases and is unlikely to have a general solution. Nuclear quantitation has repeatedly proven to be helpful in reaching differential diagnoses, in particular when based on size distributions of nuclear profiles rather than its average, but is hampered by the segmentation problem discussed above. Texture analysis of chromatin is an exciting, mathematically complex application likely to succeed, for which many approaches have been described. Finally a diagnosis (classification) can be obtained based on algorithms applied to multiple descriptors of tumor cells (for instance nuclear sizes, chromatin texture, shape, etc). The best classificatory approaches are neural networks (a form of artificial intelligencee), multivariate analysis, and logistic regression (statistical).

Algorithms↗

PubMed2005

A theoretical and experimental analysis of linear combiners for multiple classifier systems.

In this paper, a theoretical and experimental analysis of linear combiners for multiple classifier systems is presented. Although linear combiners are the most frequently used combining rules, many important issues related to their operation for pattern classification tasks lack a theoretical basis. After a critical review of the framework developed in works by Tumer and Ghosh on which our analysis is based, we focus on the simplest and most widely used implementation of linear combiners, which consists of assigning a nonnegative weight to each individual classifier. Moreover, we consider the ideal performance of this combining rule, i.e., that achievable when the optimal values of the weights are used. We do not consider the problem of weights estimation, which has been addressed in the literature. Our theoretical analysis shows how the performance of linear combiners, in terms of misclassification probability, depends on the performance of individual classifiers, and on the correlation between their outputs. In particular, we evaluate the ideal performance improvement that can be achieved using the weighted average over the simple average combining rule and investigate in what way it depends on the individual classifiers. Experimental results on real data sets show that the behavior of linear combiners agrees with the predictions of our analytical model. Finally, we discuss the contribution to the state of the art and the practical relevance of our theoretical and experimental analysis of linear combiners for multiple classifier systems.

Algorithms↗

PubMed1988

Internal Consistency Analysis: a method for studying the accuracy of function assessment for health outcome and quality of life evaluation.

Social, mental and physical function are major components of health outcomes and health related life quality, but the accuracy of function measurement is difficult to study rigorously. Internal Consistency Analysis (ICA) uses multiple sources of evidence from a survey interview to study the accuracy of a classification. It was developed to study function classifications for a general health outcome measure, the Quality of Well-being (QWB) scale. ICA is described and evidence of its utility in improving the classifications needed for the QWB is presented.

Aged↗

PubMed1979

A numerical scoring system for the classification of multiple sclerosis.

A simple, numerical system for the classification of multiple sclerosis into probable and definite categories is proposed. This system is based upon the analysis of the clinical symptomatology of 111 autopsy-proved cases of the disease from England, Norway and the United States. It is not designed to be used as an aid in the diagnosis and should be applied only to those cases where multiple sclerosis is suspected. It permits the incorporation of data obtained by means of evoked responses studies, psychological evaluations and other methods for confirming anamnestic information or delineating some asymptomatic lesions. The numerical system also provides a means for plotting the temporal evolution of the disease strictly in terms of the appearance of new signs and symptoms since recurrences of previously experienced symptoms cannot be scored; thus it has the advantage of not allowing so-called exacerbation due to physiological or psychological factors to falsely suggest disease progression or activity. The major use of this scoring system is to provide a reasonably reliable means of comparing epidemiologic data from different investigators by more clearly defining the probable and definite categories.

Adolescent↗

PubMed1992

Classification of nonspecific low back pain. I. Psychological involvement in low back pain. A clinical, descriptive approach.

An unselected sample of outpatient subjects (n = 330) with localized nonspecific low back pain (LBP) was studied. Investigation consisted of clinical assessment, physical examination, and psychiatric interview based on the DSM-III classification. A psychiatric disorder, according to the DSM-III criteria (axis I) was found in 41% of the subjects. Multiple correspondence analysis and cluster analysis were used to objectively identify clinical subtypes without preconceived theoretical models. Correspondence analyses suggested the existence of a 'psychological pain' syndrome consisting of several of the following symptoms: diffuse back pain, impossibility to assess intensity of pain on a pain scale, aggravation of pain by changing climate, by domestic activities or by psychological factors and dysesthesias in the back. Cluster analysis provided support for a four-group classification of low back pain, which may be interpreted through the relationships between psychological disturbances and the LBP clinical features. The results call for further investigation of the complex relationship between psychological disturbances and back pain. However, clinicians must be aware of the interest of a minimal psychiatric assessment in low back pain patients: psychiatric disorders frequently appear in these patients and an appropriate treatment of the psychiatric syndrome may reduce back pain.

Adolescent↗

PubMed2000

Classification of osteoporosis and osteopenia in men is dependent on site-specific analysis.

To examine the diagnosis of osteoporosis and osteopenia in men based on bone density measurements at single or multiple sites using central and peripheral measurements, we studied 206 ambulatory, community-dwelling men over age 50. Bone mineral density of the hip, PA spine, forearm, and finger were assessed by dual-energy X-ray absorptiometry. The diagnosis of osteoporosis based on a single measurement ranged from 1% using the trochanter to 39% using Ward's triangle. Twenty-one percent of men had osteoporosis if the diagnosis was based on at least one osteoporotic value at three central sites (PA spine, total hip, femoral neck). Among these men using T-scores provided by the manufacturers, 51% of osteoporotic patients would be misclassified as normal using the accuDEXA((R)) (finger), and 37% of osteoporotic men would be misclassified as normal using the PA spine. We conclude depending on the number and selection of sites there is considerable variability in the classification and misclassification of osteoporosis and osteopenia in men.

Absorptiometry, Photon↗

PubMed1985

Analyzing the joint effects of two antibodies and the design of molecularly engineered vaccines.

A new analytical approach to determine how antibodies relate to each other in producing immunity is presented. One purpose of this analysis is to decide on the antigenic composition of vaccines. Regression analyses and single discrete analyses are shown to be inappropriate to this task. The proposed analyses makes multiple cut points on two pre-exposure antibody levels. At each resulting discrete classification, additive and multiplicative interaction parameters are calculated. Various models of joint antibody action are shown to produce two general patterns of interaction terms with this type of analysis. One pattern characterizes situations where each antibody, or something substituting for the action of each antibody, is always needed to eliminate all infections. This may be because the antigens to which the antibodies are directed are on separate microbes or because microbes can only be neutralized by the joint action of both antibodies. A second pattern characterizes situations where both antibodies act cooperatively but given high enough levels only one may be needed. This may be because the antibodies have the same molecular effect or because they act by separate means against the same organisms in an innoculum.

Antibodies↗

PubMed2006

The many faces of protein-protein interactions: A compendium of interface geometry.

A systematic classification of protein-protein interfaces is a valuable resource for understanding the principles of molecular recognition and for modelling protein complexes. Here, we present a classification of domain interfaces according to their geometry. Our new algorithm uses a hybrid approach of both sequential and structural features. The accuracy is evaluated on a hand-curated dataset of 416 interfaces. Our hybrid procedure achieves 83% precision and 95% recall, which improves the earlier sequence-based method by 5% on both terms. We classify virtually all domain interfaces of known structure, which results in nearly 6,000 distinct types of interfaces. In 40% of the cases, the interacting domain families associate in multiple orientations, suggesting that all the possible binding orientations need to be explored for modelling multidomain proteins and protein complexes. In general, hub proteins are shown to use distinct surface regions (multiple faces) for interactions with different partners. Our classification provides a convenient framework to query genuine gene fusion, which conserves binding orientation in both fused and separate forms. The result suggests that the binding orientations are not conserved in at least one-third of the gene fusion cases detected by a conventional sequence similarity search. We show that any evolutionary analysis on interfaces can be skewed by multiple binding orientations and multiple interaction partners. The taxonomic distribution of interface types suggests that ancient interfaces common to the three major kingdoms of life are enriched by symmetric homodimers. The classification results are online at http://www.scoppi.org.

Amino Acid Sequence↗

PubMed2006

Clinical and radiological features related to the growth potential of meningioma.

Clinical and radiological features that help predict the growth potential of meningioma would be beneficial. The purpose of this study is to clarify the characteristics related to proliferating potential using the MIB-1 staining index. We analyzed the relationship of MIB-1 staining indices to characteristics of 342 consecutive patients with meningioma surgically removed between 1995 and 2004 by logistic regression analysis. One hundred and forty-nine of the patients with meningioma were >or=60 in age; 89 male; 48 recurrent; 203 symptomatic; 157 at the skull base; 124 over 20 cm(3); 24 multiple; 136 with edema; 117 with calcification. The MIB-1 staining index in 56 of 296 grade I meningiomas in WHO classification was >or= 3.0; in 27 of 28 grade II; and in 17 of 18 grade III, respectively. Logistic regression analysis demonstrated that male (odds ratio [OR], 2.374, p=0.003), recurrence (OR, 7.574, p=0.0001), skull base (OR, 0.540, p=0.035), calcification (OR, 0.498, p=0.019) were independent risk factors for a high MIB-1 staining index (>or=3.0); age, symptomatic, volume, multiple, edema were not. Male, recurrence, non-skull base, absence of calcification are independent risk factors for a high proliferative potential. These should be taken into consideration when managing meningiomas.

Adult↗

PubMed2002

Classification and phylogenetic analysis of the cAMP-dependent protein kinase regulatory subunit family.

The members of the PKA regulatory subunit family (PKA-R family) were analyzed by multiple sequence alignment and clustering based on phylogenetic tree construction. According to the phylogenetic trees generated from multiple sequence alignment of the complete sequences, the PKA-R family was divided into four subfamilies (types I to IV). Members of each subfamily were exclusively from animals (types I and II), fungi (type III), and alveolates (type IV). Application of the same methodology to the cAMP-binding domains, and subsequently to the region delimited by beta-strands 6 and 7 of the crystal structures of bovine RIalpha and rat RIIbeta (the phosphate-binding cassette; PBC), proved that this highly conserved region was enough to classify unequivocally the members of the PKA-R family. A single signature sequence, F-G-E-[LIV]-A-L-[LIMV]-x(3)-[PV]-R-[ANQV]-A, corresponding to the PBC was identified which is characteristic of the PKA-R family and is sufficient to distinguish it from other members of the cyclic nucleotide-binding protein superfamily. Specific determinants for the A and B domains of each R-subunit type were also identified. Conserved residues defining the signature motif are important for interaction with cAMP or for positioning the residues that directly interact with cAMP. Conversely, residues that define subfamilies or domain types are not conserved and are mostly located on the loop that connects alpha-helix B' and beta strand 7.

Amino Acid Sequence↗

PubMed2005

Molecular mechanisms of the neural melanocortin receptor dysfunction in severe early onset obesity.

The neural melanocortin receptors, melanocortin-3 and -4 receptors (MC3R and MC4R), have been shown to regulate different aspects of energy homeostasis in rodents. Human genetic studies showed that mutations in the MC4R gene are the most common monogenic form of obesity. Functional analyses of the mutant receptors revealed multiple defects. A classification scheme is presented for cataloguing the ever-increasing array of MC4R mutations. Functional analysis of the only inactivating MC3R mutation is also summarized. Insights from the analyses of the naturally occurring mutations in the MC3R and MC4R on the structure and function of these receptors are highlighted.

Animals↗

PubMed1995

Altered endogenous growth hormone secretory kinetics and diurnal GH-binding protein profiles in adults with chronic liver disease.

OBJECTIVE: Increased serum GH concentrations and GH responses to a variety of stimuli have been reported in patients with chronic liver disease (CLD). We investigated the pulsatile pattern of endogenous GH release and GH-binding protein (GHBP) and insulin-like growth factor-I (IGF-I) diurnal profiles in adults with cirrhosis, in comparison with healthy, matched control subjects. DESIGN: Case-control, cross-sectional. PATIENTS: Seven patients with biopsy proven cirrhosis, and sex, age, height, weight and oestrogen status matched controls. MEASUREMENTS: Serum immunoreactive GH concentrations in samples collected at 20-minute intervals for 24 hours were analysed using a multi-parameter deconvolution method to simultaneously resolve endogenous GH secretory and disappearance rates. Diurnal patterns of GHBP (specific immunoprecipitation method) and serum IGF-I (RIA after acid-ethanol extraction) were assessed. RESULTS: The mean daily GH secretion rate in patients with CLD was increased (210 +/- 93 vs 100 +/- 55 mU/I/day; P = 0.025), and GH disappearance half-time was prolonged (43 +/- 10 vs 24 +/- 9 min; P = 0.006) compared to controls. Detectable GH secretory bursts were more frequent in patients with CLD (10 +/- 1 vs 6 +/- 3/day; P = 0.038), but of similar mean mass (21 +/- 10 vs 17 +/- 8 mU/I) compared to controls. In patients with CLD, mean serum GHBP was slightly lower (63 +/- 36 vs 71 +/- 14% pooled control; P > 0.1). Fasting serum IGF-I concentrations (after size-exclusion HPLC) were lower in the patients with CLD (13 +/- 5 vs 21 +/- 2 nmol/l; P < 0.0001). Multiple regression analysis showed that GH secretion rate was increased in patients with CLD with higher Child's classifications (R2 = 0.86; P = 0.002) and with lower serum IGF-I concentrations measured after HPLC (R2 = 0.11; P = 0.044). CONCLUSIONS: Adults with chronic liver disease have (1) increased total daily GH secretion rates, which appear to be influenced by disease severity and diminished serum IGF-I-mediated negative feedback; (2) markedly impaired endogenous GH clearance, possibly reflecting changes in hepatic GH-receptor status; and (3) GHBP levels which do not correlate with GH kinetics or serum IGF-I concentrations.

Adult↗

PubMed1991

Prediction of resumption of drinking in posttreatment alcoholics.

The ability of five factors (depressive symptomatology, neuropsychological performance, psychosocial maladjustment, previous treatment history, and childhood attention deficit disorder symptomatology) to predict relapse was examined in a follow-up experimental design. Fifty-eight male and 45 female alcoholics were interviewed immediately following release from inpatient treatment units. Fourteen months later, 41 subjects (41%) were classified as resumers; 62 (59%) were abstainers. Resumers showed significantly poorer scores than abstainers on all five of the predictor variables. Discriminant function analysis resulted in 75% correct classification of resumers and abstainers (chi 2 = 22.1, p less than .001). Stepwise multiple regression resulted in isolation of depressive symptomatology as the best single predictor of relapse.

Adult↗

PubMedDate not supplied

Personality and performance: attributes of effective residential child care workers.

Better than age, experience, or education, this research found that personality characteristics differentiated child care workers from the general population. Ten of the 16 primary 16PF scores were significantly different and generally described an altruistic but assertive and venturesome propensity to manage others. The linear specification equation that summarized these personality differences also differentiated most from least effective child care workers: Low scores were associated with dependence and "job/person mismatch"; high-scores were associated with independence and assertiveness and, sometimes, unmanageability and "incompatible attitudes." Five 16PF factors differentiated most from least effective child care workers: Warmth (A+), intelligence (B+), assertiveness (E+), social reservation (H-), and conservatism (Q1-). Although child care workers were significantly bolder (H+) than the general population, especially effective child care workers were less bold and radical than their less effective colleagues. Both analyses identified traits similar to those that Mufson found and suggested that personality characteristics were significantly related to performance. The liner specification equation predicted correctly 63% of the time; the discriminant analysis, 70%. These equaled the classification criteria reported by supervisors from at least two agencies. Since the adjusted multiple r2 was about .25, one must wonder about the influence of other, unknown factors. Interrater reliability and varying agency performance standards may have been among those. The authors have used the 16PF for several years at the United Methodist Children's Home with very encouraging results. Although not used to select or screen applicants, the 16PF has been very helpful in reconsidering applicants who interviewed poorly or confirming those who interviewed well.(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗

PubMed1984

The role of surgical reperfusion in myocardial infarction.

The role of coronary artery bypass graft surgery during myocardial infarction is unclear. This article reviews worldwide results with this form of therapy. Included in the analysis are the effects of surgical reperfusion on left ventricular function, anginal classification following reperfusion, the effects of early versus late reperfusion, and an in-depth mortality analysis from multiple medical centers. It is concluded that surgery can be performed with a very low mortality in most patients with acute myocardial infarction, but the most appropriate form of therapy of acute myocardial infarction that will result in low mortality and morbidity remains a challenge for future investigation.

Adult↗

PubMed1994

A retrospective analysis of bone scan abnormalities in mastocytosis: correlation with disease category and prognosis.

UNLABELLED: To investigate the usefulness of bone scintigraphy in systemic mastocytosis (SM), the scans of 73 patients were retrospectively reviewed and correlated with disease category. METHODS: A modification of a previously described method for bone scan classification in this disease was used. In addition to the group as a whole, two subsets of patients with multiple bone scans were identified for closer analysis: those with (n = 13) and without (n = 12) scintigraphic evidence of progression of disease. RESULTS: Overall, patients with more aggressive SM tended to have increasingly abnormal initial bone scans (p2 = 0.0003), although there was a considerable degree of overlap. Of patients undergoing serial studies, those with scintigraphic progression also tended to have more aggressive disease (p2 = 0.006) and a poorer prognosis than those with stable bone scans. CONCLUSIONS: Both the degree of abnormality on initial bone scan and progression of scintigraphic abnormalities with serial scanning appear to correlate with the presence of more aggressive systemic mastocytosis. Based on the patterns seen, in many cases this may be a reflection of bone marrow expansion, which in turn probably reflects increased marrow disease.

Adolescent↗

PubMed2000

Nonhistological diagnosis of human cerebral tumors by 1H magnetic resonance spectroscopy and amino acid analysis.

We describe a multivariate analysis procedure to classify human cerebral tumors nonhistologically in vitro, combining the use of 1H magnetic resonance spectroscopy (MRS) with automatic amino acid analysis of biopsy extracts. Eighty-one biopsies were obtained surgically and classified histologically in eight classes: high-grade astrocytomas (class 1, n = 19), low-grade astrocytomas (class 2, n = 10), normal brain (class 3, n = 9), medulloblastomas (class 4, n = 4), meningiomas (class 5, n = 18), metastases (class 6, n = 8), neurinomas (class 7, n = 9), and oligodendrogliomas (class 8, n = 4). Perchloric acid extracts were prepared from every biopsy and analyzed by high resolution 1H MRS and automatic amino acid analysis by ionic exchange chromatography. Intensities of 27 resonances and ratios of resonances were measured in the 1H MRS spectra, and 17 amino acid concentrations were determined in the chromatograms. Linear discriminant analysis provided the most adequate combination of these variables for binary classifications of a biopsy between any two possible classes and in multiple choice comparisons, involving the eight possible classes considered. Correct diagnosis was obtained when the class selected by the computer matched the histological diagnosis. In binary comparisons, consideration of the amino acid profile increased the percentage of correct classifications, being always higher than 75% and reaching 100% in many cases. In multilateral comparisons, scores were: high-grade astrocytomas, 80%; low-grade astrocytomas, 74%; normal brain, 100%; medulloblastomas, 100%; meningiomas, 94.5%; metastases, 86%; neurinomas, 100%; and oligodendrogliomas, 75%. These results indicate that statistical multivariate procedures, combining 1H MRS and amino acid analysis of tissue extracts, provide a valuable classifier for the nonhistological diagnosis of biopsies from brain tumors in vitro.

Algorithms↗