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 1,027 records · Page 57Linked to original sources
PubMed2003

[Antithrombin III in burned children].

We studied haemostatic parameter and Antithrombin III (ATIII) level in 50 consecutive admissions for severe burns between 1990 to1994 to the Centro Grandi Ustionati Ospedale S. Eugenio, Rome. The criteria for inclusion in the study were age <16 years and the presence of major burns (extent of the burns >30 and second and third degree burns). Treatment consisted of initial fluid resuscitation and early excision and grafting of burn wounds and critical care support by a multidisciplinary team. Burn-related variables haemostatic values and the conditions of microcirculation were proposed and analysed with the help of Fisher exact test, chi square test, logistic regression and discriminant analysis. By the discriminant analysis, the coefficients of the standardized functions and the percentage of correctly classified individuals were calculated. The analysis showed total burned surface turned out to be the best predictor of survival. High discrimination efficiency was observed for age, weight, burn type (flame, scald contact chemical electrical). By the logistic regression, the total burned surface confirmed to be the best predictor of survival and between the haemostatic variables ATIII give a significant value (p=0.0244). Moreover, it is noteworthy that ATIII level at the onset of the disease gives a significant correlation with mortality (p=0.0005). The Fisher test showed a significant association between ATIII level and death (p=0.0005). This was confirmed by the chi square test (p=0.00027). Considering the AT deficiency in patients with thermal injuries, we conducted a pilot study to assess AT concentrate infusions for safety and efficacy in thermal injury. The patients received AT concentrate infusions every 8 hours to raise the plasma level to 100 % in the first 72 hours after injury and were compared with control patients with burns. Day4 levels were 105%+/-20% in patients treated with AT patients versus 50%+/-14% in the control patients (P < 0.001). In the group treated with AT the time to microcirculation recovery was shorter (P<0.02).

Adolescent↗
PubMed2001

Occupational factors contributing to low self-esteem in registered nurses and licensed practical nurses: a multivariate analysis.

The present study examines job-related factors leading to low self-esteem in nurses. The lowering of self-esteem suggests that such nurses had difficulty in fully accepting themselves and their circumstances. Subjects were registered nurses (RN) and licensed practical nurses (LPN) at hospitals, and unemployed registered nurses (UEN) seeking employment. Questionnaires were provided at 53 hospitals and a Nurse Bank in Kanagawa Prefecture. The responses of 552 RN, 146 LPN and 433 UEN were analyzed. Questions were asked about personal life, past or present nursing experience, working conditions, nursing skills, satisfaction with work performance and self-esteem. Factors giving rise to low self-esteem were determined using logistic regression analysis and logistic discriminant analysis. Employment status and qualifications were determined to be the most important factors determining the self-esteem of nurses. The next most important factors were 'a limited number of years of experience (less than five years)' and 'dissatisfaction with discretion and responsibility as a nurse' (P < 0.01). Adjusted odds ratio for a reduction in self-esteem for LPN was 4.07 times higher than for UEN, and 2.2 times higher than for RN by logistic regression analysis. LPN are treated as unskilled workers, and thus significant differences were apparent in their performance of certain job tasks. These differences were analyzed using discriminant analysis, and were referred to as follows, 1: Advanced assessment skills, 2: Advanced technical skills, 3: Advanced communication skills, and 4: Nursing plan and documentation (positive discrimination rate was 70.8%). Job dissatisfaction is closely associated with the level of professional training. Continuous education and a feedback system for various levels of nurses are needed.

Adult↗
PubMed2006

Chemometric classification of traditional Chinese medicines by their geographical origins using near-infrared reflectance spectra.

Some raw materials that have different places of production for the plant sources of the drugs Astragalus membranaceus and ginseng have been studied, based on their near-infrared reflectance spectra. The experimentally recorded spectra represent heavily ill-posed and highly correlative data sets. Three related methods, i.e. the Fisher linear discriminant analysis (FLDA), the ridge-type linear discriminant analysis (RLDA) and a newly proposed penalized ridge-type linear discriminant analysis (PRLDA), have been investigated. FLDA over-fits for the training objects of the two data sets to a high extent and is unstable for the predictive objects of the two data sets. RLDA shows obvious improvement in terms of over-fitting and unstability, but the stability for the predictive objects of the two data sets is too sensitive to their ridge-type penalized weights, tending to produce erroneous discrimination results. The proposed PRLDA can circumvent the two aforementioned problems with a large domain of penalized weights for correct discriminant analysis of the two data sets studied. The combination of the PRLDA method and near infrared reflectance spectroscopy can be adapted for the discrimination of the production places of plant sources of these drugs.

Algorithms↗
PubMedDate not supplied

From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods.

This article reviews the wealth of different pattern recognition methods that have been used for magnetic resonance spectroscopy (MRS) based tumor classification. The methods have in common that the entire MR spectra is used to develop linear and non-linear classifiers. The following issues are addressed: (i) pre-processing, such as normalization and digitization, (ii) extraction of relevant spectral features by multivariate methods, such as principal component analysis, linear discriminant analysis (LDA), and optimal discriminant vector, and (iii) classification by LDA, cluster analysis and artificial neural networks. Different approaches are compared and discussed in view of practical and theoretical considerations.

Humans↗
PubMed1989

A comparison of dummy variable versus traditional multiple discriminant function analysis.

The authors compare the use of dummy variable and traditional multiple discriminant function analysis when dealing with research questions where ratio or nominal scale independent variables can be used. A healthcare-related example of using dv MDF is given and the authors conclude that it is superior to traditional MDF for determining variable importance and developing market segment profiles.

Analysis of Variance↗
PubMed1999

Diet and chronic constipation in children: the role of fiber.

BACKGROUND: Chronic constipation is one of the most common disorders in Western countries and despite numerous clinical, pathophysiologic, and epidemiologic studies its cause is still unclear. Several hypotheses have been proposed and according to experimental studies and clinical observation, fiber intake could play a role in its pathogenesis. The purpose of this case-control study was to examine the possible correlation of idiopathic chronic constipation in children and dietary intake, particularly fiber intake. METHODS: A randomized sample of children (291 children with constipation and 1602 controls) aged 2 to 14 years was taken from three of the 52 counties of Greece. Stratification was performed on the basis of urban, rural, or suburban location and socioeconomic status. The nutritional data were obtained from a 3-day dietary record and a dietary history. Statistical analysis was performed with multivariate tests, multivariate analysis of variance, discriminant analysis, and chi-square analysis according to the characteristics of the correlated variables. RESULTS: Constipated children had a lower caloric and nutrient intake (p < 0.001), lower body weight/height (p < 0.001), and higher prevalence of reported anorexia (p < 0.001). Discriminant analysis indicated that dietary fiber alone was independently negatively correlated with chronic constipation, despite the age and the age of onset of constipation. Relative risk also had a negative correlation with fiber intake (p < 0.001). Of the main fiber fractions only cellulose and pentose were independently correlated with chronic constipation. CONCLUSIONS: Lack of fiber may play an important role in the etiology of chronic idiopathic constipation in children.

Adolescent↗
PubMed2000

[An epidemiological study on acute diarrhea during a filed exercise in PLA unit in an area in southern China].

OBJECTIVE: To explore the epidemiological characteristics and risk factors of acute diarrheal disease during a filed exercise. METHODS: Epidemiological study of a certain artillery acute diarrheal disease during a filed exercise and multiple linear stepwise regression analysis, multiple stepwise discriminate analysis were used. RESULTS: Result showed that the incidence rate of training troops was significantly higher than that of the local troops at the corresponding period (7.32% vs 0.98% P<0.05). The incidence rate among officers was significantly lower than that of the soldiers (0.99% vs 8.20% P<0.05). The incidence rate was significantly higher at the beginning of assemble for training but smooth and steady afterwards with several outbreaks. There was highly significant difference in the incidence rate of 39 companies. Regression and discrimination analysis suggested that the incidence rate was correlated with the density of flies and average boiled water volume provided everyday. The correct classifying rate of the discrimination was 91.9% in total. CONCLUSION: These results provided a basis for prevention of acute diarrheal disease during filed exercise of military action.

Acute Disease↗
PubMed2003

Native fluorescence spectroscopy of blood plasma in the characterization of oral malignancy.

Native fluorescence characteristics of blood plasma were studied in the visible spectral region, at two different excitation wavelengths, 405 and 420 nm, to discriminate patients with different stages of oral malignancy from healthy subjects. The fluorescence spectra of blood plasma of oral malignant subjects exhibit characteristic spectral differences with respect to normal subjects. Different ratios were calculated using the fluorescence intensity values at those emission wavelengths that give characteristic spectral features of each group of experimental subjects studied. These fluorescence intensity ratios were used as input variables for a multiple linear discriminant analysis across different groups. Leave-one out cross-validation was used to check the reliability of each discriminant analysis performed. The discriminant analysis performed across normal and oral cancerous subjects classified 94.7% of the original grouped cases and 93.7% of the cross-validated grouped cases. A classification algorithm was developed on the basis of the score of the discriminant functions (discriminant score) resulted in the analyses. The diagnostic potentiality of the present technique was also estimated in the discrimination of malignant subjects from normal and nonmalignant diseased subjects such as liver diseases. In the discriminant analysis performed across the three groups, normal, oral malignancy (including early and advanced stages) and liver diseases, 99% of the original grouped cases and 95.9% of the cross-validated grouped cases were correctly classified. Similar analysis performed across normal, early stage of oral malignancy, advanced oral malignancy and liver diseases correctly classified 94.9% of the original grouped cases and 91.8% of the cross-validated grouped cases.

Blood Chemical Analysis↗
PubMed2000

Fiber intake and childhood appendicitis.

In order to investigate the possible role of fiber in the etiology of acute appendicitis, 203 consecutive appendectomized children with histologically proved appendicitis and 1922 controls were studied by the diet history method. Statistics were performed by multivariate analysis of variance, discriminant analysis and chi 2. Appendectomized children had statistically significant lower mean daily intake of fiber (17.4 g versus 20.4 g, P < 0.001) including all fiber fractions: cellulose, uronic acid, pentose, exose and lignin. No statistical difference was found for energy, protein, carbohydrate and fat intake. Discriminant analysis proved that only cellulose and exose are independently correlated to appendicitis and lower fiber intake is thought to be the cause in 70% of the cases. Recurrent abdominal pain, chronic constipation and positive family history of appendectomy were more frequent in appendectomized children (P < 0.001). This study gives evidence that low fiber intake could play an important role in the pathogenesis of appendicitis.

Abdominal Pain↗
PubMedDate not supplied

Bipolar II depressive mixed state: finding a useful definition.

Recent studies showed that depressive mixed state (DMX) (major depressive episode [MDE] with few hypomanic symptoms) was common among depressed outpatients. The aim of the present study was to find a clinicallly useful definition of DMX. A useful definition could be one increasing the probability of making the correct diagnosis of bipolar II. Different definitions of DMX were tested by comparing the sensitivity, specificity, and predictive power for the diagnosis of bipolar II. Three hundred thirty-six consecutive bipolar II (n = 206) and unipolar (n = 130) MDE outpatients were interviewed with the DSM-IV Structured Clinical Interview-Clinician Version (SCID-CV). Different DMX definitions were tested, based on factor analysis, multivariate regression, discriminant analysis, and logistic regression analysis results. The sensitivity, specificity, correctly classified, and receiver operating characteristic (ROC) area for bipolar II diagnosis were compared. Two factors (factor 1, including irritability, psychomotor agitation, and more talkativeness, and factor 2, including racing thoughts, irritability, and distractibility) were significantly associated with bipolar II diagnosis. Of the hypomanic symptoms most common in bipolar II DMX, only irritability and racing thoughts were significantly associated with bipolar II diagnosis on discriminant analysis. DMX with three or more concurrent hypomanic symptoms (DMX3) was strongly associated with bipolar II diagnosis. Comparisons of sensitivity, specificity, correctly classified, and ROC area of the different DMX definitions (factor 1, factor 2, DMX3, irritability during MDE, racing thoughts during MDE) for the diagnosis of bipolar II, showed that factor 1 had the best combination of sensitivity and specificity, high correctly classified and ROC, but DMX3 has the highest specificity, and slightly lower correctly classified and ROC than factor 1. A DMX definition having the highest specificity (DMX3) for bipolar II diagnosis may be more useful to clinicians, leading to few false positives. Bipolar II diagnosis has important treatment and clinical implications, but misdiagnosis is common because diagnosis is often based on history of hypomania (dependent on memory and clinical skills). A cross-sectional marker like DMX3 may increase the probability of making the correct diagnosis of bipolar II, and therefore may be a useful definition of DMX.

Adult↗
PubMed1992

Sex determination by discriminant function analysis of lateral cranial form.

To sex the cranium, morphological features of cranial specimens were quantified with a personal computer that automatically measures distance and gradient for 39 craniometric points in the lateral contour line of the skull, which were digitized by a tablet digitizer connected to the computer. Specimens used for discriminant analysis were 50 male and 50 female adult Japanese skulls. The lateral contour showed sex differences in the nasal bone, supraorbital ridge, forehead and vertex. The nasal bone and supraorbital ridge were more developed in male contour line, and the forehead was more rounded in female contour line. But compared with the supraorbital ridge and forehead, the vertex had a wide variety of contour lines in both sexes. The vertex seemed to be less reliable as the indicator of sex. The sex differences were better reflected by gradient than distance. From variables of the gradient and distance showing significant sex differences, the discriminant function was derived and tested in 21 other specimens (13 male and 8 female skulls). The mean ratio of correct sexing of the human skull by the discriminant function was 86%.

Adult↗
PubMed1996

Towards a texture naming system: identifying relevant dimensions of texture.

Recently, researchers have started using texture for data visualization. The rationale behind this is to exploit the sensitivity of the human visual system to texture in order to overcome the limitations inherent in the display of multidimensional data. A fundamental issue that must be addressed is what textural features are important in texture perception, and how they are used. We designed an experiment to help identify the relevant higher order features of texture perceived by humans. We used twenty subjects, who were asked to rate 56 pictures from Brodatz's album on 12 nine-point Likert scales. Each subject was also asked to group these pictures into as many classes as desired. We applied the techniques of hierarchical cluster analysis and non-parametric multidimensional scaling (MDS) to the pooled similarity matrix generated from the subjects' groupings. We used Classification and Regression Tree Analysis (CART), discriminant analysis, and principal component analysis on the data from the scale ratings. The clusters generated from hierarchical cluster analysis remained intact in the MDS plots. We found that the MDS solutions fit the data well. The stress in the three-dimensional case is 0.12. The CART and discriminant analyses provided further justification for our interpretation. The three orthogonal dimensions we identified for texture are repetitive vs non-repetitive; high-contrast and non-directional vs low-contrast and directional; granular, coarse and low-complexity vs non-granular, fine and high-complexity.

Adult↗
PubMed2001

Predicting mastery level on a large-scale standardized patient test: a comparison of case and instrument score-based models using discriminant function analysis.

Clinical skills assessments have traditionally been scored via experts' ratings of examinee performance. However, this approach to scoring may be impractical in a large-scale context due to logistical and cost considerations as well as the increased probability of rater error. The purpose of this investigation was therefore to identify, using discriminant analysis, weighted score-based models that maximize the accuracy with which mastery level can be estimated for examinees taking a nationally administered standardized patient test. Additionally, the accuracy with which the resulting classification functions can be applied to predict mastery level for a cross-validation sample of examinees was also examined. Results suggest that it might be feasible to implement an automated scoring procedure in a cost-effective manner while still retaining the important facets of the decision-making process of expert raters. Cost-benefit, test development and psychometric implications of these results are important and discussed in the full paper.

Clinical Competence↗
PubMedDate not supplied

A study on the antipicornavirus activity of flavonoid compounds (flavones) by using quantum chemical and chemometric methods.

The AM1 semiempirical method is employed to calculate a set of molecular properties (variables) of 45 flavone compounds with antipicornavirus activity, and 9 new flavone molecules are used for an activity prediction study. Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA), Stepwise Discriminant Analysis (SDA), and K-Nearest Neighbor (KNN) are employed in order to reduce dimensionality and investigate which subset of variables should be more effective for classifying the flavone compounds according to their degree of antipicornavirus activity. The PCA, HCA, SDA, and KNN methods showed that the variables MR (molar refractivity), B(9) (bond order between C(9) and C(10) atoms), and B(25) (bond order between C(11) and R(7) atoms) are important properties for the separation between active and inactive flavone compounds, and this fact reveals that electronic and steric effects are relevant when one is trying to understand the interaction between flavone compounds with antipicornavirus activity and the biological receptor. In the activity prediction study, using the PCA, HCA, SDA, and KNN methodologies, three of the 9 new flavone compounds studied were classified as potentially active against picornaviruses.

Antiviral Agents↗
PubMed1985

Utilizing the health belief model to predict dieting and exercising behavior of obese and nonobese adolescents.

This study was undertaken to explain dieting and exercising behavior of obese and nonobese adolescents as measured by the elements of the Health Belief Model (HBM). An elicitation questionnaire was used to determine salient beliefs about dieting, exercising, and obesity for each of the major components of the HBM. The Health Belief Model questionnaire, developed from the elicited salient beliefs, contained items employed to measure attitudes towards obesity and exercise, knowledge of obesity and exercise, weight locus of control, and beliefs and evaluations about obesity and exercise. Discriminant analysis and stepwise discriminant analysis were employed in the data analysis of the 69 obese and 100 nonobese HBM respondents to determine the relative importance of the investigated factors in predicting obesity. It was found that benefits of dieting was the most powerful predictor of dieting behavior for the obese adolescents, whereas susceptibility to the causes of obesity best explained present dieting behavior of nonobese adolescents. Exercising behavior of obese teenagers was best explained by cues to exercising. No HBM variables were significant in predicting exercising behavior of nonobese adolescents.

Adolescent↗
PubMed1996

Using tissue texture surrounding calcification clusters to predict benign vs malignant outcomes.

The positive predictive value of mammography is between 20% and 25% for clustered microcalcifications. For very early cancers there is often a lack of concordance between mammographic signs and pathology. This study examines the usefulness of computer texture analysis to improve the accuracy of malignant diagnosis. Texture analysis of the breast tissue surrounding microcalcifications on digitally acquired images during stereotactic biopsy is used in this study to predict malignant vs benign outcomes. 54 biopsy proven cases (36 benign, 18 malignant) are used. The texture analysis calculates statistical features from gray level co-occurrence matrices and fractal geometry for equal probability and linear quantizations of the image data. Discriminant models are generated using linear discriminant analysis and logistic discriminant analysis. Results do not differ significantly by method of quantization or discriminant analysis. Jackknife results misclassify 2 of 18 malignant cases (sensitivity 89%) and 6 of 36 benign cases (specificity 83%) for logistic discriminant analysis. From this preliminary study, texture analysis appears to show significant discriminatory power between benign and malignant tissue, which may be useful in resolving problems of discordance between pathological and mammographic findings, and may ultimately reduce the number of benign biopsies.

Biophysical Phenomena↗
PubMed1984

Differentiating violent and nonviolent opiate-addicted reformatory inmates with the MMPI.

Used multivariate profile analysis and stepwise discriminant analysis in an effort to discriminate among four groups of male opiate-addicted reformatory inmates (N = 193) classified according to degree of criminal violence: (1) Bodily Violent (N = 19); (2) Potentially Bodily Violent (N = 25); (3) Materially Violent (N = 113); and (4) Nonviolent (N = 36). Profile analysis indicated that the four groups were very similar; a stepwise discriminant analysis significantly distinguished the Bodily Violent group from each of the other groups, but failed to differentiate successfully among the remaining three groups. A second stepwise discriminant analysis, in which Groups 2, 3 and 4 were combined, produced a significant discriminant function and correctly classified 68.4% of the Bodily Violent group and 75.9% of the combined Nonbodily Violent groups. The MMPI scales that contributed most to the latter prediction of group membership, in relative order of discriminating power, were: F, MA, D, PD, HS, PA and SI.

Adolescent↗
PubMed2005

Typification of cider brandy on the basis of cider used in its manufacture.

A study of typification of cider brandies on the basis of the origin of the raw material used in their manufacture was conducted using chemometric techniques (principal component analysis, linear discriminant analysis, and Bayesian analysis) together with their composition in volatile compounds, as analyzed by gas chromatography with flame ionization to detect the major volatiles and by mass spectrometric to detect the minor ones. Significant principal components computed by a double cross-validation procedure allowed the structure of the database to be visualized as a function of the raw material, that is, cider made from fresh apple juice versus cider made from apple juice concentrate. Feasible and robust discriminant rules were computed and validated by a cross-validation procedure that allowed the authors to classify fresh and concentrate cider brandies, obtaining classification hits of >92%. The most discriminating variables for typifying cider brandies according to their raw material were 1-butanol and ethyl hexanoate.

Alcoholic Beverages↗