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 667 records · Page 37Linked to original sources

PubMed2005

Bladder cancer outcome and subtype classification by gene expression.

Models of bladder tumor progression have suggested that genetic alterations may determine both phenotype and clinical course. We have applied expression microarray analysis to a divergent set of bladder tumors to further elucidate the course of disease progression and to classify tumors into more homogeneous and clinically relevant subgroups. cDNA microarrays containing 10,368 human gene elements were used to characterize the global gene expression patterns in 80 bladder tumors, 9 bladder cancer cell lines, and 3 normal bladder samples. Robust statistical approaches accounting for the multiple testing problem were used to identify differentially expressed genes. Unsupervised hierarchical clustering successfully separated the samples into two subgroups containing superficial (pT(a) and pT(1)) versus muscle-invasive (pT(2)-pT(4)) tumors. Supervised classification had a 90.5% success rate separating superficial from muscle-invasive tumors based on a limited subset of genes. Tumors could also be classified into transitional versus squamous subtypes (89% success rate) and good versus bad prognosis (78% success rate). The performance of our stage classifiers was confirmed in silico using data from an independent tumor set. Validation of differential expression was done using immunohistochemistry on tissue microarrays for cathepsin E, cyclin A2, and parathyroid hormone-related protein. Genes driving the separation between tumor subsets may prove to be important biomarkers for bladder cancer development and progression and eventually candidates for therapeutic targeting.

Aged↗

PubMedDate not supplied

Typing of field rabies virus strains in FR Yugoslavia by limited sequence analysis and monoclonal antibodies.

A total of 32 rabies virus isolates (15 of fox, 14 of cat and 3 of dog origin) from the territory of FR Yugoslavia were collected from December 1996 till February 1998 and analyzed by limited sequencing of N gene and by indirect immunofluorescence and a panel of 20 antinucleocapsid monoclonal antibodies (MAbs). All examined strains were characterized as sylvatic fox strains. Two main genetic variants were detected, 15 isolates belonging to Group I, 14 belonging to Group II, while the remaining 3 could not be classified into any group. This classification was confirmed by MAbs. The obtained results indicate at least two independent cycles of rabies transmission, probably resulting from multiple modes of transmission to the territories now belonging to FR Yugoslavia.

Animals↗

PubMed2005

Texture for script identification.

The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.

Algorithms↗

PubMedDate not supplied

Multi-variant analysis of otoacoustic emissions and estimation of hearing thresholds: transient evoked otoacoustic emissions.

Evaluation of cochlear hearing loss by means of transiently evoked otoacoustic emissions is already established in clinical practice. However, accurate prediction of pure-tone thresholds is still questioned and is still regarded as troublesome. Both click- and tone-burst-evoked otoacoustic emissions at several intensity levels were measured and analysed in 157 ears from normally hearing and 432 ears from patients with different degrees of pure sensory hearing loss using the ILO88/92 equipment. Results of otoacoustic emissions (OAE), elicited by clicks and tone-bursts at centre frequencies from 1 to 5 kHz, were analysed using two different statistical methods. Both multivariate discriminant analysis and forward multiple regression analysis were used to determine which OAE variables were most discriminating and best at predicting hearing thresholds. We found that a limited set of variables obtained from both tone-burst and click measurements can accurately predict and categorize hearing loss levels up to a limit of 60 dB HL. We found correct classification scores of pure-tone thresholds between 500 and 4000 Hz up to 100 per cent when using combined click and tone-burst otoacoustic measurements. Prediction of pure-tone thresholds was correct with a maximum estimation error of 10 dB for audiometric octave frequencies between 500 and 4000 Hz. Measurements of multiple tone-bursts OAEs have a significant clinical advantage over the use of clicks alone for clinical applications, and a good classification and prediction of pure-tone thresholds with otoacoustic emissions is possible.

Acoustic Stimulation↗

PubMed2006

Principal component and linear discriminant analysis of T1 histograms of white and grey matter in multiple sclerosis.

Twenty-three relapsing remitting multiple sclerosis (RRMS) patients and 14 controls were imaged to produce normal-appearing white and grey matter T1 histograms. These were used to assess whether histogram measures from principal component analysis (PCA) and linear discriminant analysis (LDA) out-perform traditional histogram metrics in classification of T1 histograms into control and RRMS subject groups and in correlation with the expanded disability status score (EDSS). The histograms were classified into one of two groups using a leave-one-out analysis. In addition, the patients were scanned serially, and the calculated parameters correlated with the EDSS. The classification results showed that the more complex techniques were at least as good at classifying the subjects as histogram mean, peak height and peak location, with PCA/LDA having success rates of 76% for white matter and 68%/65% for grey matter. No significant correlations were found with EDSS for any histogram parameter. These results indicate that there is much information contained within the grey matter as well as the white matter histograms. Although in these histograms PCA and LDA did not add greatly to the discriminatory power of traditional histogram parameters, they provide marginally better performance, while relying only on data-driven feature selection.

Brain↗

PubMed2004

Gene mining: a novel and powerful ensemble decision approach to hunting for disease genes using microarray expression profiling.

Current applications of microarrays focus on precise classification or discovery of biological types, for example tumor versus normal phenotypes in cancer research. Several challenging scientific tasks in the post-genomic epoch, like hunting for the genes underlying complex diseases from genome-wide gene expression profiles and thereby building the corresponding gene networks, are largely overlooked because of the lack of an efficient analysis approach. We have thus developed an innovative ensemble decision approach, which can efficiently perform multiple gene mining tasks. An application of this approach to analyze two publicly available data sets (colon data and leukemia data) identified 20 highly significant colon cancer genes and 23 highly significant molecular signatures for refining the acute leukemia phenotype, most of which have been verified either by biological experiments or by alternative analysis approaches. Furthermore, the globally optimal gene subsets identified by the novel approach have so far achieved the highest accuracy for classification of colon cancer tissue types. Establishment of this analysis strategy has offered the promise of advancing microarray technology as a means of deciphering the involved genetic complexities of complex diseases.

Acute Disease↗

PubMed2000

[Evaluation of diagnostic scores via intercategorial kappa coefficients].

A study design for the evaluation and confirmed modification of diagnostic rules is described. Based on the assessment of intercategorial rater agreement, those categories, which cause confusion in multiple ratings, can be combined and the gain in rater agreement can be assessed by the computation of appropriately modified kappa measures. The proposal is illustrated by the analysis of an evaluation trial related to SPECT based classification of patients with Graves' ophthalmopathy.

Diagnostic Imaging↗

PubMed2005

Erectile dysfunction in patients with chronic viral liver disease: its relevance to protein malnutrition.

BACKGROUND: In patients with chronic liver disease (CLD), quality of life is generally accepted as poor, especially for physical function. However, sufficient data regarding erectile function has not been shown in patients with CLD. The international index of erectile function (IIEF) is widely used to assess erectile function, and a short form of the IIEF was recently developed (IIEF-5). Using this questionnaire, we evaluated erectile dysfunction (ED) in patients with CLD. METHODS: A total of 117 Japanese patients (64 with chronic hepatitis [CH] and 53 with liver cirrhosis [LC]) were analyzed. The etiologies were hepatitis B virus (HBV) in 21, HCV in 94, and non-B non-C in 2. The IIEF-5 and Medical Outcomes Study Short Form 36 (SF-36) were administered to the patients, and biochemical analyses for items serum albumin, prothrombin time, bilirubin, and ammonia were also performed. RESULTS: The incidence of ED was 85% in the total cohort with CLD, 78% in those with CH, and 92% in those with LC (P < 0.05 between CH and LC). ED was found in 50% of CLD patients under age 50 years, in 79% aged 50-59, and in 100% aged over 60 (P, overall <0.001). The scores for ED severity correlated with increasing grades of a modified Child-Pugh classification (P < 0.05). Simple regression analysis showed age (P < 0.01), physical function (P < 0.001), role physical (P < 0.001), and social functioning (P < 0.05) on the SF-36, and serum albumin (P < 0.001) as significant determinants of ED. Multiple regression analysis identified age (P < 0.001) and serum albumin (P < 0.001) as independent significant factors that determined ED. CONCLUSIONS: These data clearly demonstrate that liver disease is the cause of ED in patients with CLD, and serum protein status could be relevant to this condition in these patients.

Adult↗

PubMed1990

Interactive morphometry of normal and hyperplastic peritoneal mesothelial cells and dysplastic and malignant ovarian cells.

This study used computerized interactive morphometry to evaluate the differential characteristics of mesothelial normal cells, mesothelial hyperplastic cells, and carcinomatous cells, and also compared hyperplastic mesothelial cells with ovarian dysplastic cells from a previous study. The procedure included extraction of multiple descriptors of the nuclear profile: perimeter length, area, longest chord, circularity factors, standard deviations of these characteristics, and a 10-bin size distribution table of the nuclear area. The final classification is achieved by stepwise discriminant analysis of these variables. The analysis classified all cases correctly with high posterior probabilities.

Cystadenocarcinoma↗

PubMed2005

A prognostic approach to defining chronic pain.

This paper develops a prognostic approach to defining chronic back pain. Possible and probable chronic back pain were defined, respectively, by a 50% and an 80% (or greater) probability of future clinically significant back pain. We assessed whether an empirically derived chronic pain classification satisfied these validating criteria among 1213 primary care back pain patients assessed at baseline and at 1, 2 and 5 year follow-ups. From multiple measures of back pain intensity and dysfunction, Latent Transition Regression Analysis empirically identified four pain severity latent classes: no pain; mild pain; moderate pain and limitation; and severe, limiting pain. From one observation point to the next, patients were most likely to remain in the same pain severity class, but chronic pain was better characterized as a dynamic state than a static trait. Among persons with severe, limiting pain, prognostic variables (depression, diffuse pain, pain persistence) improved prediction of future severe, limiting pain. A risk score developed from pain severity and prognostic measures identified risk levels corresponding to 50 and 80% probability thresholds for predicting future clinically significant back pain. At baseline and 1 year, 6.1 and 4.4% of study patients met or exceeded the 80% risk threshold for probable chronic back pain. An additional 20.3% at baseline and 12.5% at 1 year met or exceeded the 50% risk threshold for possible chronic back pain. Defining chronic pain prospectively, by risk thresholds for future clinically significant pain, provides an empirically grounded approach to chronic pain assessment.

Adolescent↗

PubMed1994

Visual agnosia and optic aphasia: are they anatomically distinct?

A patient with left infero-medial occipital-temporal infarct suffered a visual agnosia that, by a minor change of the task, could be manipulated to optic aphasia. Tools in actual use and pantomimes of tool use were better named than stationary tools, a dissociation that suggests differences in the ability of stimuli to evoke associations over multiple modalities. Based on this case and analysis of previous reports we suggest that optic aphasia differs from visual agnosia primarily in the degree of callosal disconnection and that the preserved demonstration of tools use and semantic classification of optic aphasia reflect right hemisphere contribution to visual processing.

Aged↗

PubMed2006

Proliferative diabetic retinopathy is associated with microalbuminuria in patients with type 2 diabetes.

Diabetic retinopathy is one of the leading causes of blindness in working-age individuals. Diabetic patients with proteinuria or those on dialysis usually present severe forms of diabetic retinopathy, but the association of diabetic retinopathy with early stages of diabetic nephropathy has not been entirely established. A cross-sectional study was conducted on 1214 type 2 diabetic patients to determine whether microalbuminuria is associated with proliferative diabetic retinopathy in these patients. Patients were evaluated by direct and indirect ophthalmoscopy and grouped according to the presence or absence of proliferative diabetic retinopathy. The agreement of diabetic retinopathy classification performed by ophthalmoscopy and by stereoscopic color fundus photographs was 95.1% (kappa = 0.735; P < 0.001). Demographic information, smoking history, anthropometric and blood pressure measurements, glycemic and lipid profile, and urinary albumin were evaluated. On multiple regression analysis, diabetic nephropathy (OR = 5.18, 95% CI = 2.91-9.22, P < 0.001), insulin use (OR = 2.52, 95% CI = 1.47-4.31, P = 0.001) and diabetes duration (OR = 1.04, 95% CI = 1.01-1.07, P = 0.011) were positively associated with proliferative diabetic retinopathy, and body mass index (OR = 0.90, 95% CI = 0.86-0.96, P < 0.001) was negatively associated with it. When patients with macroalbuminuria and on dialysis were excluded, microalbuminuria (OR = 3.3, 95% CI = 1.56-6.98, P = 0.002) remained associated with proliferative diabetic retinopathy. Therefore, type 2 diabetic patients with proliferative diabetic retinopathy more often presented renal involvement, including urinary albumin excretion within the microalbuminuria range. Therefore, all patients with proliferative diabetic retinopathy should undergo an evaluation of renal function including urinary albumin measurements.

Albuminuria↗

PubMedDate not supplied

[An algorithm for synthesis of small-size autonomous devices for detection of medico-biological parameters].

Problems of synthesis of devices for detection of medico-biological parameters are considered. A classification of the devices and their functional units is proposed. An algorithm for synthesis of detectors of medico-biological parameters on the basis of multiple-use functional units is suggested. The algorithm is based on analysis of functional unit modifications providing optimization of the device characteristics.

Algorithms↗

PubMed1977

[Re-operations on patients with ball valve prostheses].

Out of 989 cases with a ball-valve prosthesis, 66 have been reoperated (6.7%). 2.9% of the cases reviewed annually have thus been reoperated. The main indications for reoperation were displacement (75.5%), malfunction (10.5%) which was related to a failure of the material of the prosthesis or to the deposition of fibrinous plaques, and associated lesions (14%) which were valvular, coronary or myocardial. There were multiple complications in 36 patients. The operative mortality was 31.8% (21.7% over the last two years). On statistical analysis, the significant risk factors were a previous history of bacterial endocarditis, grouping in Class IV of the NYHA classification, enlargement of the QRS complex (0.12 s), urgency of reoperation, and prolonged extracorporeal circulation (2 hours). The rapid fall in survival time was due in part to late deaths (16 patients). By way of contrast, the clinical result was satisfactory in 71% of the survivors. Analysis of the causes of failures has lead to a search for ways of preventing the necessity for reoperation.

Adult↗

PubMed2006

Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals.

Knee joint disorders are common in the elderly population, athletes, and outdoor sports enthusiasts. These disorders are often painful and incapacitating. Vibration signals [vibroarthrographic (VAG)] are emitted at the knee joint during the swinging movement of the knee. These VAG signals contain information that can be used to characterize certain pathological aspects of the knee joint. In this paper, we present a noninvasive method for screening knee joint disorders using the VAG signals. The proposed approach uses wavelet packet decompositions and a modified local discriminant bases algorithm to analyze the VAG signals and to identify the highly discriminatory basis functions. We demonstrate the effectiveness of using a combination of multiple dissimilarity measures to arrive at the optimal set of discriminatory basis functions, thereby maximizing the classification accuracy. A database of 89 VAG signals containing 51 normal and 38 abnormal samples were used in this study. The features extracted from the coefficients of the selected basis functions were analyzed and classified using a linear-discriminant-analysis-based classifier. A classification accuracy as high as 80% was achieved using this true nonstationary signal analysis approach.

Algorithms↗

PubMed2004

Analysis of missense variation in human BRCA1 in the context of interspecific sequence variation.

INTRODUCTION: Interpretation of results from mutation screening of tumour suppressor genes known to harbour high risk susceptibility mutations, such as APC, BRCA1, BRCA2, MLH1, MSH2, TP53, and PTEN, is becoming an increasingly important part of clinical practice. Interpretation of truncating mutations, gene rearrangements, and obvious splice junction mutations, is generally straightforward. However, classification of missense variants often presents a difficult problem. From a series of 20,000 full sequence tests of BRCA1 carried out at Myriad Genetic Laboratories, a total of 314 different missense changes and eight in-frame deletions were observed. Before this study, only 21 of these missense changes were classified as deleterious or suspected deleterious and 14 as neutral or of little clinical significance. METHODS: We have used a combination of a multiple sequence alignment of orthologous BRCA1 sequences and a measure of the chemical difference between the amino acids present at individual residues in the sequence alignment to classify missense variants and in-frame deletions detected during mutation screening of BRCA1. RESULTS: In the present analysis we were able to classify an additional 50 missense variants and two in-frame deletions as probably deleterious and 92 missense variants as probably neutral. Thus we have tentatively classified about 50% of the unclassified missense variants observed during clinical testing of BRCA1. DISCUSSION: An internal test of the analysis is consistent with our classification of the variants designated probably deleterious; however, we must stress that this classification is tentative and does not have sufficient independent confirmation to serve as a clinically applicable stand alone method.

Amino Acid Sequence↗

PubMedDate not supplied

Comparison of linear and nonlinear classification algorithms for the prediction of drug and chemical metabolism by human UDP-glucuronosyltransferase isoforms.

Partial least squares discriminant analysis (PLSDA), Bayesian regularized artificial neural network (BRANN), and support vector machine (SVM) methodologies were compared by their ability to classify substrates and nonsubstrates of 12 isoforms of human UDP-glucuronosyltransferase (UGT), an enzyme "superfamily" involved in the metabolism of drugs, nondrug xenobiotics, and endogenous compounds. Simple two-dimensional descriptors were used to capture chemical information. For each data set, 70% of the data were used for training, and the remainder were used to assess the generalization performance. In general, the SVM methodology was able to produce models with the best predictive performance, followed by BRANN and then PLSDA. However, a small number of data sets showed either equivalent or better predictability using PLSDA, which may indicate relatively linear relationships in these data sets. All SVM models showed predictive ability (>60% of test set predicted correctly) and five out of the 12 test sets showed excellent prediction (>80% prediction accuracy). These models represent the first use of pattern recognition methods to discriminate between substrates and nonsubstrates of human drug metabolizing enzymes and the first thorough assessment of three classification algorithms using multiple metabolic data sets.

Algorithms↗

PubMed2004

Long-term prognosis for childhood and juvenile absence epilepsy.

PURPOSE: To analyse prognostic factors for long term seizure remission in patients with childhood (CAE) and juvenile absence epilepsy (JAE). STUDY DESIGN: A retrospective analysis of a hospital based prevalence cohort. METHODS: The cohort consisted of 163 patients (104 females, 59 males) treated at the Universitatsklinik fur Neurologie, Innsbruck between 1970 and 1997. All had absences according to the ILAE classification. Follow up was in 1999 to 2000. We assessed multiple clinical and EEG factors as predictors of outcome and compared a classification according to the predominant pattern of seizure recurrence (pyknoleptic, PA or non pyknoleptic absence, NPA) with the ILAE classification with respect to prognosis. RESULTS: The mean age at seizure onset was 10.9 years (range, 3 to 27); age at follow up was 36.7 years (range, 13 to 81); duration of follow up was 25.8 years (range, 3 to 69). Sixty four patients (39 %) had CAE and 64 (39 %) JAE, while 35 (22%) had typical absences but could not be clearly defined as either CAE or JAE, and were therefore called "the overlap group". Patients with JAE or patients in the overlap group developed more often generalized tonic clonic seizures (GTCS) (p<0.001) and myoclonic attacks (p<0.05) during the course of the disease. At follow up 36 (56 %) of patients with CAE, 40 (62%) with JAE and 19 (54 %) of the overlap group were seizure free for at least two years (p=ns). When classified according to the predominant absence pattern at seizure onset 42 (51%) patients with PA and 53 (65%) with NPA were in remission (p=ns). In a stepwise binary logistic regression analysis the pattern of absence (PA or NPA) together with the later development of additional seizure types (myoclonias or GTCS), but not the CAE/JAE classification was predictive for long term lack of remission with a correct prediction of 66% of all patients. CONCLUSION: Only 58% of patients with absences were in remission after a long term follow up. CAE and JAE are closely related syndromes with large overlap of the age of onset. A classification according to the predominant seizure pattern at onset, together with later development of myoclonic attacks or GTCS is useful in predicting seizure remission in absence epilepsies.

Adolescent↗