PubMed Health⌕ Search

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 559 records · Page 31Linked to original sources

Ensemble of linear models for predicting drug properties.

We propose a new classification method for the prediction of drug properties, called random feature subset boosting for linear discriminant analysis (LDA). The main novelty of this method is the ability to overcome the problems with constructing ensembles of linear discriminant models based on generalized eigenvectors of covariance matrices. Such linear models are popular in building classification-based structure-activity relationships. The introduction of ensembles of LDA models allows for an analysis of more complex problems than by using single LDA, for example, those involving multiple mechanisms of action. Using four data sets, we show experimentally that the method is competitive with other recently studied chemoinformatic methods, including support vector machines and models based on decision trees. We present an easy scheme for interpreting the model despite its apparent sophistication. We also outline theoretical evidence as to why, contrary to the conventional AdaBoost ensemble algorithm, this method is able to increase the accuracy of LDA models.

ATP Binding Cassette Transporter, Subfamily B, Mem↗

Screening for asbestos-related pleural disease with digital storage phosphor radiography.

Digital storage phosphor radiography (SR) has a wide dynamic range and unique postprocessing capabilities that may improve the performance of screening studies for asbestos-related pleural disease compared with conventional film radiography (FR). In a group of 32 asbestos-exposed and nine control subjects with established pleural data, we compared the screening performance of FR and SR obtained with a single isoexposure, dual-energy technique (system resolution 0.2 mm, 10 bits). Performance was evaluated for 7320 observations by eight readers using a paired t test (P less than .02 with Bonferroni correction) of averaged receiver operating characteristic curve (ROC) areas (Az +/- standard error). We found that SR alone and SR supplemented by dual-energy soft-tissue and calcium images (SRde) were superior to FR in the overall detection of pleural abnormalities (Az = 0.90 +/- 0.01, 0.90 +/- 0.01, and 0.88 +/- 0.01, respectively). In the specific detection of pleural calcification, SRde was superior to FR (Az = 0.91 +/- 0.01 and 0.87 +/- 0.01, respectively; P less than 0.01). Analysis of variance indicated that SRde most closely reproduced an established pleural score based on the International Labor Organization (ILO) classification of the pneumoconioses (P less than 0.05, Scheffé's multiple comparison test). We conclude that isodose SR performs at least as well as FR in screening for asbestos-related pleural disease. SR supplemented by dual-energy images might improve the specific detection of pleural calcifications compared with FR.

Asbestosis↗

Variation in cervical cancer screening by region, socio-economic, migrant and indigenous status in women in New South Wales.

The purpose of this study was to estimate the extent of association of cervical screening in NSW women with socio-economic status (SES), rurality, and proportions of non-English speaking background (NESB) and Indigenous status. Data on women who had at least one Pap test over two years (January 1998-December 1999) were obtained from the NSW Pap test Register. Each local government area (LGA) was allocated to categories of population proportions of NESB and Indigenous status, a rurality classification based on population density and remoteness, and to an SES quintile. The odds ratios (OR) of having a Pap test were estimated and confounding adjusted by multiple logistic regression analysis. Implied Pap test rates in urban NESB and in rural Indigenous women were estimated from the modelled estimates. The adjusted OR for a Pap test in large rural centres (1.14) was significantly higher than those for metropolitan or capital city residents (0.9 and 1.0 respectively). Adjusted OR for a Pap test in other rural centres (0.73) and other remote areas (0.64) were significantly lower than those for metropolitan or capital city residents. In urban populations the lowest OR were in areas with both low SES and high proportion of NESB. The lowest OR for Pap screening in rural populations occurred in the most remote areas with the highest proportion of Indigenous women. For urban NESB women the biennial Pap test rate was estimated as 50%, and for rural Indigenous women 29%, compared with the NSW average of 59%.

Adult↗

Progress in toxinformatics: the challenge of predicting acute toxicity.

Historically, acute toxicity based on LC(50) and LD(50) tests has been analyzed using various quantitative structure-activity relationships (QSARs). The obtained QSAR equations cannot be related to the multiple health effects reflected in the experimental data of analyzed compounds. Therefore little predictive power for novel compounds can be achieved. New methods based on classification SAR (C-SAR) analysis offer new mechanistic knowledge that can be related to new health effects, resulting in better predictive power. To this end, a very careful interpretation of the obtained results is required, implying the use of the existing mechanistic information to the maximum possible extent. The current mini-review aims at determining ways of automated extraction of new mechanistic knowledge from existing data, as well as ways of relating this knowledge to various health effects. A comparison of "statistical induction" and "knowledge-based" approaches is provided. The existing and future developments in predictive acute toxicity are discussed.

Algorithms↗

Relationship of angiographic finding with neovascular structure detected by immunohistochemical staining of alpha-smooth muscle actin in small hepatocellular carcinoma.

To elucidate the relationship between angiographic features and histological findings, an immunohistological study of alpha-smooth muscle actin was performed in 106 patients with small hepatocellular carcinoma. Arterial dominance or portal blood paucity were found in 73 patients (68.9%) on digital subtraction angiography, 88 (83.0%) on computerized tomographic arterial portography and 87 (82.1%) on carbon dioxide-enhanced ultrasonography. Among 73 patients with hypervascularity on angiography, 57 (78.1%) had thick-walled, nuclei-rich and slender-shaped vessels (type II), eight (11.0%) had thin-walled, nuclei-poor and oval-shaped vessels (type I) and the remaining eight had a mixed type of II and I. Conversely, among 33 patients without hypervascularity, five (15.2%) had a type II, 21 (63.6%) had a type I, five had a mixed type and two had no positive vessel. Tumour size, histological classification and amount of non-triadal vessels were also associated with the angiographic appearance of the tumours. Among varied aspects of the cancer including tumour size, tumour multiplicity, microscopic portal invasion, histological classification, amount of alpha-smooth muscle actin-positive vessels and shape of alpha-smooth muscle actin-positive vessels, multivariate logistic regression analysis demonstrated that the shape of alpha-smooth muscle actin-positive vessels was solely associated with angiographic hypervascularity independently (P<0.0001). Although the existence of non-triadal vessels characterized hepatocellular carcinoma, angiographic hypervascularity was closely associated with the type II vessel. A morphological change of non-triadal vessel from type I to type II was considered to occur in an early stage of hepatocellular carcinoma.

Actins↗

Genomic analysis of mouse retinal development.

The vertebrate retina is comprised of seven major cell types that are generated in overlapping but well-defined intervals. To identify genes that might regulate retinal development, gene expression in the developing retina was profiled at multiple time points using serial analysis of gene expression (SAGE). The expression patterns of 1,051 genes that showed developmentally dynamic expression by SAGE were investigated using in situ hybridization. A molecular atlas of gene expression in the developing and mature retina was thereby constructed, along with a taxonomic classification of developmental gene expression patterns. Genes were identified that label both temporal and spatial subsets of mitotic progenitor cells. For each developing and mature major retinal cell type, genes selectively expressed in that cell type were identified. The gene expression profiles of retinal Müller glia and mitotic progenitor cells were found to be highly similar, suggesting that Müller glia might serve to produce multiple retinal cell types under the right conditions. In addition, multiple transcripts that were evolutionarily conserved that did not appear to encode open reading frames of more than 100 amino acids in length ("noncoding RNAs") were found to be dynamically and specifically expressed in developing and mature retinal cell types. Finally, many photoreceptor-enriched genes that mapped to chromosomal intervals containing retinal disease genes were identified. These data serve as a starting point for functional investigations of the roles of these genes in retinal development and physiology.

Animals↗

The role of expert system shell induction in the analysis of phase and amplitude images obtained from nuclear cardiology.

In an attempt to explain the results of a perception experiment, estimates of statistical parameters were obtained from phase and amplitude images of nuclear medicine multiple-gated cardiac studies. A commercially available induction system was used to create a rule-based decision tree using these estimates as a training set. In the classification of normal and abnormal studies two useful rules were found; one of these involved the standard deviation of the left ventricular phase histogram and the other concerned the correlation of adjacent pixels in the left ventricular region of the amplitude image. A discriminant analysis performed on five amplitude and five phase parameters produced no better discrimination than the use of the phase standard deviation alone. Although it was hoped that induction would find more than two useful rules, the results of the discriminant analysis confirm that induction has performed creditably on a difficult problem.

Algorithms↗

Gene amplification and proliferative kinetics in relation to prognosis of patients with gastric carcinoma.

BACKGROUND: The differences in survival of gastric carcinoma patients who have identical clinical or pathologic stages prompted the authors to investigate the prognostic significance of biologic features that are known to affect the clinical aggressiveness of other tumor types. METHODS: One hundred twenty-four tumor samples from patients who had received radical or palliative surgery were analyzed for c-myc, c-K-ras, hst, and c-erb B-2 gene amplification by means of the Southern blot technique. Of these tumors, 70 were also examined for cell kinetics by means of the thymidine labeling index (TLI). RESULTS: The analysis of associations between gene amplification and the anatomicopathologic variables (TNM classification, site of tumor, and histology) showed that amplification represents a late event in the natural history of gastric carcinoma. Gene amplification showed a slight, statistically insignificant, negative impact on overall survival (OS) (P = 0.09). Amplification of c-erb B-2 correlated in a statistically significant way with reduced OS (P = 0.03). Cox multiple regression analysis revealed that neither c-erb B-2 amplification nor TLI had prognostic significance in relation to OS. CONCLUSIONS: These data indicate that amplification of the examined oncogenes did not reveal a new independent prognostic factor for patients with gastric carcinoma. However, the authors' results did show a strong correlation between gene amplification and tumor progression, which warrants further study involving larger series of patients. At the same time, the TLI results underlined the need to identify the most suitable biologic material for use in the estimation of proliferative indexes in gastric carcinoma.

Adult↗

Association between complex coronary artery stenosis and unstable angina and the extent of plaque inflammation.

PURPOSE: Patients with unstable coronary syndromes often have complex morphology of coronary stenoses at angiography. We evaluated the association between qualitative assessment of coronary stenoses and plaque inflammation determined by immunohistochemistry. METHODS: A total of 79 patients with unstable (n = 46) or stable angina (n = 33) underwent directional coronary atherectomy for culprit lesions. Qualitative analysis of coronary angiograms was performed using a modified Ambrose classification. Coronary lesions were categorized as either simple (concentric and eccentric type I, n = 29) or complex (eccentric type II and multiple irregularities, n = 50). Cryostat sections of retrieved atherosclerotic specimens were stained immunohistochemically with monoclonal antibodies, alpha-actin (smooth muscle cells), CD68 (macrophages), and CD3 (T lymphocytes). The extent of atherosclerotic inflammation within each coronary lesion was determined by the percentage of immunopositive macrophages per total tissue area (including smooth muscle cells) and the number of T lymphocytes per mm(2). RESULTS: The mean (+/- SD) percentage of macrophages in atherectomy specimens from patients with unstable angina was greater than in specimens from patients with stable angina (21% +/- 14% vs. 13% +/- 10%, P = 0.01); similar results were seen when complex coronary lesions were compared with simple lesions (23% +/- 13% vs. 9% +/- 8%, P <0.001). In multivariate linear regression models, the combination of unstable angina and lesion complexity was strongly associated with the percentage of plaque macrophages. CONCLUSION: The extent of atherosclerotic plaque inflammation is associated with angiographic grading of coronary lesion complexity and unstable angina.

Aged↗

Multiclass cancer diagnosis using tumor gene expression signatures.

The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.

Biomarkers, Tumor↗

Fasting plasma glucose, uric acid, and triglycerides as predictors of the ratio of total cholesterol to HDL-C.

It was reported previously that a score composed of glucose, uric acid, and triglyceride was correlated closely with the total cholesterol:high density lipoprotein cholesterol (TC:HDL) ratio and could be used to predict those subjects for whom the more expensive HDL measurement would be useful. The authors tested this score using multiple regression and discriminant function analysis in a population sample of 209 men aged 40-79 years, Triglyceride was the only component of the score that contributed to the prediction or classification of the TC:HDL ratio. Although the correlations of the score with the TC:HDL ratio were relatively good (r = 0.72 or greater), the discriminant function analysis showed that subjects with high or low scores could have high or low TC:HDL ratios. The authors conclude that the score (essentially the triglyceride level) is inadequate to permit the classification of any individual as having a definite high or low TC:HDL ratio.

Adult↗

Prediction of scoliotic cobb angle with the use of the scoliometer.

STUDY DESIGN: A prospective study was conducted in a young homogenous adolescent population, with the use of the scoliometer. OBJECTIVES: To create a mathematic formula that provides the accurate Cobb angle of idiopathic scoliosis with the use of the scoliometer only. SUMMARY OF BACKGROUND DATA: The scoliometer is an accepted method for detection and evaluation of scoliosis during screening programs. To the author's knowledge, there are no previous methods and formulas to estimate the approximate Cobb angle using only the scoliometer. METHODS: Several clinical (scoliometer value, age, and sex) and radiographic (Cobb angle, Perdriolle of and apical vertebra, Risser iliac apophysis classification) parameters from 442 (4.37%) of 10,109 screened adolescents who had a scoliometer value of at least 7 degrees were taken and correlated using the simple and multiple linear regression analysis. RESULTS: Cobb angle and scoliometer value were statistically significantly correlated to each other. Two mathematic formulas were created to predict the Cobb angle of the thoracic and lumbar scoliosis, with similar sensitivity and accuracy. The thoracic and lumbar scoliometer values were statistic significantly correlated with the thoracic and lumbar Cobb angle (P = 0.0254 and P = 0.0015, respectively). The lumbar scoliometer value was significantly correlated with lumbar apical vertebra Perdriolle value. Also, the thoracic and lumbar Cobb angles were significantly correlated with thoracic and lumbar apical vertebra (P = 0.0001 and P = 0.0015, respectively). CONCLUSIONS: In the present study, the authors have constructed two mathematic formulas, which provide accurately the scoliotic Cobb angle in young adolescents using only the scoliometer with a deviation of 5.63 degrees thoracic curves and 5.79 degrees for lumbar curves. The authors recommended that all physicians engaged in scoliosis screening programs use the scoliometer based on the mathematic formulas that the authors developed. They believe that this method will reduce the cost of school screening programs, the overdiagnosis, and the unnecessary exposure to irradiation of this young population in the future.

Adolescent↗

Soft tissue differentiation using multiband signatures of high resolution ultrasonic transmission tomography.

In this paper, we are interested in soft tissue differentiation by multiband images obtained from the High-Resolution Ultrasonic Transmission Tomography (HUTT) system using a spectral target detection method based on constrained energy minimization (CEM). We have developed a new tissue differentiation method (called "CEM filter bank") consisting of multiple CEM filters specially designed for detecting multiple types of tissues. Statistical inference on the output of the CEM filter bank is used to make a decision based on the maximum statistical significance rather than the magnitude of each CEM filter output. We test and validate this method through three-dimensional interphantom/intraphantom soft tissue classification where target profiles obtained from an arbitrary single slice are used for differentiation over multiple other tomographic slices. The performance of the proposed classifier is assessed using receiver operating characteristic analysis. We also apply our method to classify tiny structures inside a bovine kidney and sheep kidneys. Using the proposed method we can detect physical objects and biological tissues such as styrofoam balls, chicken tissue, calyces, and vessel-duct successfully.

Algorithms↗

Government statistics of certified causes of perinatal mortality in Moscow and certain problems with its improvement.

While preparing the Ninth Revision of the International Classification of Diseases, Injuries and Causes of Death (1970-1975), the World Health Organisation sought ways of improving the accuracy of statistics of perinatal mortality. A new Certificate of Cause of Perinatal Death, developed for use in all regions of the USSR and introduced there in 1974, was recommended for introduction in other countries. This was based on the reorganised and more clear-cut coding outlined in Chapter XV of ICD-9. Comparison of the perinatal death rates in 1975 with those in 1986 showed a fall from 25 to 20 per 1000 births, with changes in causes related to changes on classification. Cross-tabulation of multiple-cause perinatal death was made possible by coding maternal conditions affecting the fetus or newborn separately from fetal conditions originating in the perinatal period. Analysis of the results of tabulation of multiple-cause perinatal death in Moscow in 1986 proceeded to a proposed structure for a Basic Tabulation List allowing comparisons of the statistics of perinatal mortality.

Cause of Death↗

Spectral Doppler characterization of endoleaks following endoluminal abdominal aortic aneurysm repair.

BACKGROUND: Colour Doppler ultrasound of endoluminal abdominal aortic aneurysm repair is becoming an established imaging technique in identifying endoleak. Management and treatment of endoleak is determined in part by the exact nature of the endoleak, namely its type and whether it has single or multiple vessel inflow and outflow. To date, spectral Doppler waveform analysis has provided some information about the propensity for spontaneous seal of isolated type II endoleaks, rather than assisting in their classification. METHODS: We present a collection of three case reports outlining the directionality/phasicity of the Doppler waveform profile associated with endoleaks whose type and subtype (uni- /or multi-conduital) were angiographically determined. RESULTS: In all three cases uniconduital type II endoleak demonstrated a to-and-fro waveform on Doppler ultrasound imaging. CONCLUSIONS: To-and-fro Doppler waveforms may be associated with uniconduital type II endoleaks. If upon investigation of further cases this is found to be the case, this waveform classification may facilitate determination of the subtype (uni- or multi-conduital) of endoleak, thus identifying those cases which may be more amenable to percutaneous repair.

Angioplasty↗

The combination of radiotherapy and surgery in the treatment of carcinoma of the uterine cervix.

In the Department of Radiotherapy and Oncology at Oxford, 1303 patients were registered between 1950 and 1975 with a diagnosis of carcinoma of the uterus; from these, 883 cases of carcinoma of the uterine cervix could be identified with certainty. Each patient's full clinical record was established from multiple hospital notes, operating theatre records, histopathological report files and so on. A uniform classification, based on the TNM system, was used for all patients. A data file, suitable for computer analysis, was established which contained all the available data. Analysis revealed that all patients could be divided into two distinct groups that had been prospectively determined and that the allocation achieved was random. The results, by various methods of analysis, show consistently that a policy of radical radiotherapy combined with radical surgery gave an increased survival rate, and a decreased mortality rate from cancer when compared with a treatment policy of only radical radiotherapy. During the 25 years being reviewed there was a progressive increase in the number of young patients with cancer of the uterine cervix in the early stages of disease at presentation and in the survival of patients with the early stages of invasive cancer.

Adult↗

Plasma atrial and brain natriuretic peptide levels in dogs with congestive heart failure.

Plasma concentrations of atrial natriuretic peptide (ANP) and brain natriuretic peptide (BNP) were measured in 6 dogs with experimental mitral regurgitation (MR) and 19 canine patients with asymptomatic and symptomatic congestive heart failure (CHF). In dogs with experimental MR, ANP and BNP concentrations were significantly correlated with pulmonary capillary wedge pressure (PCWP) (ANP; r=0.852, P=0.0004, BNP; r=0.832, P=0.0008). ANP level was shown to have a predominant effect on PCWP in comparison with BNP using multiple regression analysis. In canine patients with asymptomatic and symptomatic CHF, ANP and BNP concentrations were significantly different among the heart failure classes according to the New York Heart Association functional classification (ANP; P=0.0165, BNP; P=0.0005). In addition, ANP and BNP levels in dogs with decompensated heart failure (n=10) significantly increased in comparison with those in dogs with compensated heart failure (n=9). There was however no correlation between ANP and BNP levels in each heart failure class. In conclusion, plasma ANP and BNP levels may become predictors of PCWP and the severity of heart failure in dogs with MR, although further investigations on ANP and BNP levels in more clinical cases are required.

Animals↗

Childhood femur fractures, associated injuries, and sociodemographic risk factors: a population-based study.

OBJECTIVE: The objectives of this study were to determine the incidence of femur fractures in Colorado children, to assess underlying causes, to determine the prevalence and predictors of associated injuries, and to identify potentially modifiable risk factors. METHODS: The study population included all Colorado residents who were aged 0 to 17 years at the time of injury between January 1, 1998, and December 31, 2001. Cases of femur fracture were ascertained using the population-based Colorado Trauma Registry and International Classification of Diseases, Ninth Revision, Clinical Modification codes 820.0 to 821.39. Associated injuries with an Abbreviated Injury Scale of 2 or higher were classified into 5 categories. Poisson regression, small area analysis, and multivariate logistic regression were used to identify predictors of femur fractures and associated injuries, respectively. RESULTS: During the study period, 1139 Colorado children (795 boys, 344 girls) sustained femur fractures, resulting in the incidence of 26.0 per 100000 person-years. Rates were higher in boys than in girls in all age groups (overall risk ratio: 2.19; 95% confidence interval: 1.92-2.47) but did not differ by race/ethnicity. Femur fractures that were caused by nonaccidental trauma showed more distal and combined shaft + distal pattern; their incidence did not differ by gender or race but was higher in census tracts with more single mothers and less crowded households. Associated injuries were present in 28.6% of the cases, more often in older children. Fatalities occurred only among children with associated injuries. Children who were involved in nonaccidental trauma, motor vehicle crashes, or auto-pedestrian accidents were 16 to 20 times more likely to have associated injuries than those with femur fractures as a result of a fall. In small-area analysis, the incidence of femur fractures in infants and toddlers was higher in census tracts characterized by higher proportion of Hispanics, single mothers, and more crowded households. Among children 4 to 12 years of age, the incidence was higher in census tracts with fewer single-family houses and more crowded households. Finally, the incidence of femur fractures among teenagers was higher in rural tracts and those with a higher proportion of Hispanics. CONCLUSIONS: Femur fractures and associated injuries remain a major cause of morbidity in children. Predictors of femur fractures change with age; however, the risk is generally higher among children who live in the areas with lower socioeconomic indicators.

Abbreviated Injury Scale↗