Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Discriminant Analysis”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 919 records · Page 51Linked to original sources
PubMed2002

Characterizing the relationship between HIV-1 genotype and phenotype: prediction-based classification.

This paper establishes a framework for understanding the complex relationships between HIV-1 genotypic markers of resistance to antiretroviral drugs and clinical measures of disease progression. A new classification scheme based on the probabilities of how new patients will respond to antiretroviral therapy given the available data is proposed as a method for distinguishing among groups of viral sequences. This approach draws from existing cluster analysis, discriminant analysis, and recursive partitioning techniques and requires a model relating genotypic characteristics to phenotypic response. A data set of 2,746 sequences and the corresponding Indinavir 50% inhibitory concentrations are described and used for illustrative purposes.

Amino Acid Sequence↗
PubMed2004

Development of screening indicators for ranking areas at risk of vitamin A deficiency in Thailand.

The objective of this study was to develop community based screening indicators for identifying areas at risk of vitamin A deficiency. Three hundred children aged 24-71 months in 12 villages of 3 provinces who were previously identified to have various degrees of vitamin A deficiency were randomly selected to participate in the study. These villages were located in Songkhla, Yala and Narathiwat provinces. Data collection included anthropometric measurements, serum retinol analysis, data on dietary intake, illness, and socioeconomic status. Subsamples of 120 children were taken for Modified Relative Dose Response. Statistics used for data analysis were factor analysis, discriminant analysis and Receiver Operating Characteristic curves. Sensitivity and specificity of the screening indicators were calculated and compared with the rate of vitamin A deficiency at > or = 15 per cent of children with serum retinol < 0.70 micromol/l. Findings revealed that the screening indicators could identify areas at risk of vitamin A deficiency with 83.3 per cent efficiency. Data to be used for identifying areas at risk of vitamin A deficiency included home and land ownership for agriculture, dietary intake of vitamin A, access to social services (maternal education and antenatal care), vaccination, infectious diseases (diarrhoea and upper respiratory tract infection with fever) and nutritional status.

Age Distribution↗
PubMed2004

Evaluation of a simple carrier molecule to enhance drug penetration of dermal layers by utilizing multivariate methods, structure property correlations, and continuous system modeling.

Nicotinic acid is shown to be comparable to dihydropyridine in its capacity to facilitate penetration of an attached antibacterial drug through dermal layers. Antibacterial drugs examined with nicotinic acid or dihydropyridine carriers were beta-lactam antibiotics: methicillin, oxacillin, benzylpenicillin, penicillin F, penicillin dihydro F, propicillin, carbenicillin, penicillin K, penicillin X, and ampicillin. An oxymethyl (-O-CH2-) group is inserted as the linker between the antibiotic and the carrier group. Structure Property Correlations and multivariate methods such as regression analysis, cluster analysis, principal component analysis, discriminate analysis, self-organizing tree algorithm, and factor analysis clearly showed that nicotinic acid performs as an effective carrier drug and is comparable to dihydropyridine. The skin penetration constant Kp was calculated for all 10 antibiotics having either dihydropyridine or nicotinic acid as carrier, and was found to have a mean of 5.13E-05 cm/hour and 1.83E-05 cm/hour, respectively. The standard deviation for each group showed the numerical values overlap as did the 90% confidence interval for each group. A hierarchical tree organization of skin shows the overlapped dermal layers as they exist in normal skin and for the model utilized in this work. A Deming-Regression analysis also shows the nicotinic acid and dihydropyridine structures to have similar and correlated water solubility. Plotting Kp of the dihydropyridine structures as independent variable versus Kp of the nicotinic acid structures show good correlation (Pearson correlation r = 0.6606) and no significant departure from linearity. Connected box plots showed the majority of Kp values for each group of modified antibiotics to exist in a tight cluster. Polar graph of the Log Kow values showed the two groups of modified antibiotics to be correlated and numerically adjacent in trend. ChemSketch property calculations and modeling demonstrates the affects of structural oxygens, nitrogens, carbonyl groups, amide groups, and aromatic rings that are important in understanding the pervasiveness through dermal layers. Continuous model analysis by acslXtreme is utilized and demonstrates three models of the dispersion of drugs through dermal layers based on diffusivity constant (D), Log Kp from Log Kow and formula weight, and Kp as a function of time.

Administration, Topical↗
PubMed1987

[Psychometric detection of depressive mood conditions].

An investigation into the diagnostic value of psychometric methods for the diagnosis of depressive states involved five psychometric questionnaires, one concentration test procedure, and one problem-solving approach to register cognitive processes. The data obtained for 80 depressive patients of varied aetiology were compared with those of sample of 80 neurotics without depressive aberration. Even univariate comparisons revealed statistically significant differences between the two samples. Multivariate methods (factor analysis, discriminative analysis) yielded more differentiated information. The "Scale for depression depth measurements" was found to be of particular diagnostic relevance; it was standardized for the time being.

Adult↗
PubMed1980

Application of two multi-dimensional analytical methods to histological study of the aorta in dietary atherosclerosis of the rabbit.

Multivariate analysis (principal component analysis, discriminant analysis) have been applied to the histological data of arterial lesions in experimental atherosclerosis of the rabbit. We carried out a comparative study of: 1. the lesion observed at three levels of the aortas; origin of the aorta, thoracic aorta and abdominal aorta, and 2. the lesions according to the type of fat ingested during the experimental period. Five edible fats were studied: butter, olive oil, arachid oil, rapeseed oil rich in erucic acid, and rapeseed oil poor in erucic acid (Primor). This study re-affirms the possible importance of the above mentioned methods in evaluation by histology of lesions induced in the arteries by the different hyperlipidic regimens. Indeed these methods are complementary and enable the introduction of statistical methods in the quantitative evaluation of morphological lesions.

Animals↗
PubMedDate not supplied

QSAR in ecotoxicity: an overview of modern classification techniques.

This study deals with classification for toxicity prediction. Using a data set of 235 pesticides and 153 descriptors, we built several models using seven classification algorithms: nearest mean classifier, linear discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, soft independent modeling of class analogy, K nearest neighbors classification, classification, and regression tree. The performance of the models was then compared with the classifier, the end-points, the number of descriptor, and the diversity of the data set. Finally, we made a critical analysis of the models and descriptors.

Algorithms↗
PubMed1992

Statistical methods in diagnosis.

Motivations are presented for exploring formal statistical methods for use in medical diagnosis and the advantages and disadvantages are discussed. A brief review is presented of classical linear discriminant analysis, quadratic discriminant analysis, logistic regression, nearest neighbour and kernel methods, recursive partitioning methods, the independence model, regularized discriminant analysis, structured conditional probability distributions, methods for categorical data, and other methods. Criteria on which a choice might be made are presented and methods for assessing diagnostic performance are outlined. Particular applications of screening and chromosome analysis are used as illustrations and available software is described.

Bayes Theorem↗
PubMed2006

Statistical classification of black-capped (Poecile atricapillus) and mountain chickadee (Poecile gambeli) call notes.

Both black-capped (Poecile atricapillus) and mountain chickadees (Poecile gambeli) produce a chick-a-dee call that consists of several distinct note types. In some regions, these 2 species live sympatrically, and it has been shown that 1 species will respond weakly to songs of the other. This suggests that chickadee song, and potentially other of their vocalizations, contains species-specific information. We tested the possibility that call notes were acoustically sufficient for species identification. Black-capped and mountain non-D notes were summarized as a set of 9 features and then analyzed by linear discriminant analysis. Linear discriminant analysis was able to use these notes to identify species with 100% accuracy. We repeated this approach, but with black-capped and mountain D notes that were summarized as a set of 4 features. Linear discriminant analysis was able to use these notes to identify species with 94% accuracy. This demonstrates that any of the note types in these chickadee calls possesses sufficient information for species classification.

Acoustics↗
PubMed2005

Neural net applied to anthropological material: a methodical study on the human nasal skeleton.

A new information processing method, an artificial neural net, was applied to characterise the variability of anthropological features of the human nasal skeleton. The aim was to find different types of nasal skeletons. A neural net with 15*15 nodes was trained by 17 standard anthropological parameters taken from 184 skulls of the Aachen collection. The trained neural net delivers its classification in a two-dimensional map. Different types of noses were locally separated within the map. Rare and frequent types may be distinguished after one passage of the complete collection through the net. Statistical descriptive analysis, hierarchical cluster analysis, and discriminant analysis were applied to the same data set. These parallel applications allowed comparison of the new approach to the more traditional ones. In general the classification by the neural net is in correspondence with cluster analysis and discriminant analysis. However, it goes beyond these classifications because of the possibility of differentiating the types in multi-dimensional dependencies. Furthermore, places in the map are kept blank for intermediate forms, which may be theoretically expected, but were not included in the training set. In conclusion, the application of a neural network is a suitable method for investigating large collections of biological material. The gained classification may be helpful in anatomy and anthropology as well as in forensic medicine. It may be used to characterise the peculiarity of a whole set as well as to find particular cases within the set.

Adult↗
PubMed2006

Geographic classification of spanish and Australian tempranillo red wines by visible and near-infrared spectroscopy combined with multivariate analysis.

Visible (vis) and near-infrared (NIR) spectroscopy combined with multivariate analysis was used to classify the geographical origin of commercial Tempranillo wines from Australia and Spain. Wines (n = 63) were scanned in the vis and NIR regions (400-2500 nm) in a monochromator instrument in transmission. Principal component analysis (PCA), discriminant partial least-squares discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) based on PCA scores were used to classify Tempranillo wines according to their geographical origin. Full cross-validation (leave-one-out) was used as validation method when PCA and LDA classification models were developed. PLS-DA models correctly classified 100% and 84.7% of the Australian and Spanish Tempranillo wine samples, respectively. LDA calibration models correctly classified 72% of the Australian wines and 85% of the Spanish wines. These results demonstrate the potential use of vis and NIR spectroscopy, combined with chemometrics as a rapid method to classify Tempranillo wines accordingly to their geographical origin.

Analysis of Variance↗
PubMed2006

Activity optimization method in SPECT: a comparison with ROC analysis.

A discriminant method for optimizing activity in nuclear medicine studies is validated by comparison with ROC (received operating characteristic)-curves. The method is tested in 21 single photon emission computerized tomography (SPECT), performed with a cardiac phantom. Three different lesions (L(1), L(2) and L(3)) were placed in the myocardium-wall by pairs for each SPECT. Three activities (84, 37 or 18.5 MBq) of 99mTc were used as background. Linear discriminant analysis was used to select the parameters that characterize image quality among the measured variables in the images [(Background-to-Lesion (B/L(i)) and Signal-to-Noise (S(i)/N) ratios)]. Two clusters with different image quality (P=0.021) were obtained. The ratios B/L(1), B/L(2) and B/L(3) are the parameters used to construct the function with 100% of cases correctly classified into the clusters. The value of 37 MBq was the lowest tested activity for which good results for the B/L(i) ratios were obtained. The result coincides with the applied ROC-analysis (r=0.89).

Discriminant Analysis↗
PubMed2001

Drug use prevention for the high sensation seeker: the role of alternative activities.

Research demonstrating links between sensation-seeking and drug use, and sensation-seeking and participation in leisure activities suggests designing substance misuse prevention projects that encourage substituting alternative activities for drug use. The current study uses factor analysis and discriminant analysis to provide comprehensive information on the kinds of activities high-sensation seekers participate in. Factor analysis of activity participation indicates an eight factor solution. Discriminant analysis of factor scores indicates that high-sensation seekers can be discriminated from low-sensation seekers on the basis of two factors, active-adventure and conflict-combat. Implications for prevention program design are discussed.

Adolescent↗
PubMed2005

Proposal of a comprehensive clinical typology of alcohol withdrawal--a cluster analysis approach.

AIMS: To characterize the various courses of alcohol withdrawal. METHODS: The Alcohol Withdrawal Scale (AWS) was applied to 217 alcohol-dependent patients every 4 h till the symptoms of withdrawal had passed (until each of four consecutive scores were <3). Patients were medicated by a standardized treatment scheme according to AWS-scores. Hierarchical cluster analysis and discriminant analysis were applied. RESULTS: We found five clusters representing increasing severity of alcohol withdrawal. Each cluster is characterized by a combination of the two maximum subscores (vegetative and psychopathological subscore) and three additional psychopathological symptoms (anxiety, disorientation, and hallucination). In 18.4% of the patients, relevant symptoms were not observed (cluster 1), 18.9% developed mild or moderate vegetative symptoms only (cluster 2), and 40.6% additional anxiety (cluster 3). In cluster 4 (11.1%) the most frequent psychopathological symptoms were disorientation and anxiety but no hallucinations, which could be observed only in cluster 5 (11.1%). Discriminant analysis using the maximum subscores at the first day of treatment as independent variables correctly predicted 89.9% of the five clusters. CONCLUSIONS: Our findings support a model of alcohol withdrawal clustering along the two dimensions of vegetative and psychopathological severity. Furthermore, the AWS may be useful to predict the course of alcohol withdrawal already at the first day of treatment.

Adult↗
PubMed2003

New approach based on fuzzy logic and principal component analysis for the classification of two-dimensional maps in health and disease. Application to lymphomas.

Two-dimensional (2D) electrophoresis is the most wide spread technique for the separation of proteins in biological systems. This technique produces 2D maps of high complexity, which creates difficulties in the comparison of different samples. The method proposed in this paper for the comparison of different 2D maps can be summarised in four steps: (a) digitalisation of the image; (b) fuzzyfication of the digitalised map in order to consider the variability of the two-dimensional electrophoretic separation; (c) decoding by principal component analysis of the previously obtained fuzzy maps, in order to reduce the system dimensionality; (d) classification analysis (linear discriminant analysis), in order to separate the samples contained in the dataset according to the classes present in said dataset. This method was applied to a dataset constituted by eight samples: four belonging to healthy human lymph-nodes and four deriving from non-Hodgkin lymphomas. The amount of fuzzyfication of the original map is governed by the sigma parameter. The larger the value, the more fuzzy theresulting transformed map. The effect of the fuzzyfication parameter was investigated, the optimal results being obtained for sigma = 1.75 and 2.25. Principal component analysis and linear discriminant analysis allowed the separation of the two classes of samples without any misclassification.

Electrophoresis, Gel, Two-Dimensional↗
PubMed2000

Obstructive sleep apnea (OSA): a cephalometric analysis of severe and non-severe OSA patients. Part II: A predictive discriminant function analysis.

One hundred male obstructive sleep apnea (OSA) patients were classified into 2 groups on the basis of apnea-hypopnea index (AHI) as severe (AHI > or = 50) and non-severe (AHI < 50). A comprehensive cephalometric analysis of cervicocraniofacial skeletal and upper airway soft tissue morphology was performed in 51 non-severe and 49 severe OSA patients. In addition, a multivariate statistical method (principal component, analysis and predictive discriminant analysis) was performed to identify the components that could correctly differentiate the severe from the non-severe OSA patients. Eight principal components (PCs) of cervicocraniofacial skeletal morphology, 4 PCs of hyoid bone position and head posture, and 7 PCs of upper airway soft tissue morphology, together with the selected demographic variables, were deduced to formulate a linear canonical discriminant function. The equation of a 9-variable model was generated as follows: PDF score = 4.127 - 0.144 (Body Mass Index) - 0.376 (PC1.1) + 0.311 (PC1.4) + 0.214 (PC1.5) + 0.075 (PC 2.1) - 1.309 (PC2.3) + 0.708 (PC3.2) - 0.059 (PC3.3) + 0.609 (PC3.6). The cutoff score was -0.03899. The overall rate of correct classification was 83%. The results showed that Body Mass Index and 8 other PCs contributed significantly to the OSA severity. These analyses are proven to be a useful adjunctive diagnostic tool to select optimal treatment regimens for OSA patients with varying degrees of severity.

Aged↗
PubMed1996

Analysis of mandible of newly developing strain of Japanese white rabbit (Nib:JWNS).

In the present paper, we applied analysis of the mandible to a new strain of Japanese White rabbit being developed (Nib: JWNS), at 5th and 8th generations (F5 and F8), and evaluated the process of establishment, making comparison with the parent colonies (I, K and L), and other established JW colonies (A, E, O and R). The mandibles were measured at 12 sites and the data obtained were calculated by principal component analysis and discriminant analysis. As a result of principal component analysis, the parent colonies were found to be close to one another with intermediate size of the mandible and height of condyloid and angular processes, but in F5 and F8 the mandibles were slightly shorter in height and different from those in the parent colonies. On the other hand, results of discriminant analysis revealed that mandibles were discriminated correctly 100% in colonies A, O and R, and 90% in E and I. Colonies A, O, R, E and I were therefore regarded as established strains. In the developing colonies, the discriminant rate was 70% in F5 and 80% in F8. One mandible from F5 and two from F8 were wrongly classified to the parent colony L, which was the lowest discriminant rate among the colonies examined (61.5%). The results of both statistical analyses suggest that the JWNS are almost established at 8th generation as a new strain.

Animals↗
PubMed2001

Comparison of statistical methods for identification of Streptococcus thermophilus, Enterococcus faecalis, and Enterococcus faecium from randomly amplified polymorphic DNA patterns.

Thermophilic streptococci play an important role in the manufacture of many European cheeses, and a rapid and reliable method for their identification is needed. Randomly amplified polymorphic DNA (RAPD) PCR (RAPD-PCR) with two different primers coupled to hierarchical cluster analysis has proven to be a powerful tool for the classification and typing of Streptococcus thermophilus, Enterococcus faecium, and Enterococcus faecalis (G. Moschetti, G. Blaiotta, M. Aponte, P. Catzeddu, F. Villani, P. Deiana, and S. Coppola, J. Appl. Microbiol. 85:25-36, 1998). In order to develop a fast and inexpensive method for the identification of thermophilic streptococci, RAPD-PCR patterns were generated with a single primer (XD9), and the results were analyzed using artificial neural networks (Multilayer Perceptron, Radial Basis Function network, and Bayesian network) and multivariate statistical techniques (cluster analysis, linear discriminant analysis, and classification trees). Cluster analysis allowed the identification of S. thermophilus but not of enterococci. A Bayesian network proved to be more effective than a Multilayer Perceptron or a Radial Basis Function network for the identification of S. thermophilus, E. faecium, and E. faecalis using simplified RAPD-PCR patterns (obtained by summing the bands in selected areas of the patterns). The Bayesian network also significantly outperformed two multivariate statistical techniques (linear discriminant analysis and classification trees) and proved to be less sensitive to the size of the training set and more robust in the response to patterns belonging to unknown species.

Bayes Theorem↗
PubMed1991

Incidence and prediction of filled teeth from 12 to 18 years of age in a district in Norway.

The present study investigated whether the incidence or prevalence of filled teeth/approximal surfaces at one age could be predictive for the incidence in another period or for the prevalence at the age of 18. The study was conducted in 12-18-yr-olds in Norway. Regression analysis showed that the best prognosis for subsequent incidence of filled teeth/approximal surfaces could be made at the age of 15. By using regression analysis or discriminant analysis it was possible at the age of 15 to predict with high accuracy those who would acquire more fillings than the median at the age of 18. Discriminant analysis with one predictor variable is suggested for clinical use. The variable that discriminated best between above and below median number of new fillings in the period 15-18 yr was untreated lesions in the inner half of the enamel in the approximal surfaces of premolars and molars at the age of 15. From the use of simple prediction tools, it was concluded that individuals at the age of 15 with a low prevalence of filled teeth/filled approximal surfaces and without untreated approximal lesions would be subjected to a low incidence of new fillings until the age of 18.

Adolescent↗