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 433 records · Page 24Linked to original sources
PubMed1995

Discriminant analysis of biomechanical differences between novice, good and elite rowers.

Oar force and oar angle data resulting from a 6-min maximal rowing ergometer test undertaken by novice (n = 9), good (n = 23) and national (n = 9) level male rowers, were used to identify biomechanical performance variables which accurately discriminated between rowers of differing ability levels. The variables included two work capacity measures, mean propulsive power output per kilogram of body mass (W kg-1) and propulsive work consistency (%), and two skill variables, stroke-to-stroke consistency (%) and stroke smoothness (%). Discriminant function analysis indicated the presence of two functions, both of which clearly indicated the importance of mean propulsive power output per kilogram of body mass as a discriminating variable. Function 2 gave greater weight to stroke-to-stroke consistency and stroke smoothness than function 1; however, function 1 was the most powerful discriminator. Classification procedures were used to predict the ability level to which a rower most likely belonged and involved defining the 'distance' between each rower and each ability level centroid, with the rower being classified into the 'nearest' ability level. These procedures indicated that 100% of the elite, 73.9% of the good, 88.9% of the novice and 82.9% of all rowers were correctly classified into their respective skill levels. Stepwise discriminant analysis included the variables in the following order: mean propulsive power output per kilogram of body mass, stroke-to-stroke consistency, stroke smoothness and propulsive work consistency (P < 0.001). The results of this study indicate that biomechanical performance variables related to rowing capacity and skill may be identified and used to discriminate accurately between rowers of differing skill levels, and that, of these variables, propulsive work consistency is the least effective discriminator.

Adult↗
PubMed1982

Discriminant analysis and the selection of patients for controlled drinking programs: a methodological note.

The criterion group classification scheme commonly used in conjunction with discriminant function analysis places individuals in the group for which their membership probability is the highest. This optimizes the proportion of correctly classified cases. The clinical utility of a discriminant based scheme may, however, be underestimated if the proportion of correctly classified cases is the only concern. For clinical purposes, attention must also be paid to minimizing serious diagnostic errors and to improving predictions for individuals. Clinicians can address these concerns by considering membership probabilities for each criterion group of interest. The utility of this approach is illustrated using data from a study in which discriminant analysis was used to identify the characteristics of problem drinkers who abstained, controlled their drinking, or continued to drink heavily after treatment.

Alcohol Drinking↗
PubMed1986

Differential diagnosis of fever in systemic lupus erythematosus using discriminant analysis.

In an attempt to find a reliable method to assess fever in patients with systemic lupus erythematosus (SLE), a multifactorial analysis was applied to the routine laboratory examinations, including white blood cell count (WBC) and serum globulin fraction concentrations. During 74 febrile episodes, 49 SLE patients showed increased disease activity and the remaining 25 febrile episodes were due to intercurrent infection. The two different groups of fever episodes were clearly separated by a principal component analysis using five variables from the routine laboratory tests, including WBC, serum alpha-1, alpha-2, beta, and gamma globulins. Discriminant analysis showed that 95% of 74 febrile episodes could be correctly classified as to the cause of fever when a combination of WBC and alpha-2 globulin level was used as variables. A simple discriminant formula which we calculated was considered to be of practical use for the differentiation of the two clinical entities.

Alpha-Globulins↗
PubMed1988

[Discriminant analysis of methods for detecting the heterozygote carrier state for the Duchenne muscular dystrophy gene].

The authors used the procedure of a step-wise discriminant analysis for comparing the informative value of different methods for revealing heterozygotic carriers of the gene of Duchenne's myodystrophy by means of an analysis of the blood serum and physicochemical properties of erythrocytes in 11 mothers suffering from Duchenne's muscular dystrophy who were obligate (by the findings of a genealogical analysis) carriers of the gene of Duchenne's myodystrophy. Employment of a complex of four methods (determination of the constant of the rate of chloride-bicarbonate metabolism through the erythrocyte membrane, erythrocytic deformability, hemolytic stability of erythrocytes upon their heating at 55 degrees C, and analysis of the activity of serum creatine kinase) has increased 1.8-fold the rate of detecting heterozygotic carriers of the gene of Duchenne's myodystrophy as compared to the creatine kinase test.

Adult↗
PubMed1986

Accuracy of a discriminant analysis model for prediction of coliform mastitis in dairy cows and a comparison with clinical prediction.

We tested an equation, which had been developed previously using discriminant analysis, for predicting whether a cow has coliform mastitis. Variables indicating a high probability of coliform infection included history of previous mastitis in the affected quarter, weakness, clear or white color of milk, water consistency of the milk, swelling of the udder, lack of previous mastitis in other quarters, lack of palpable udder abscesses, and a high body temperature. Application of this predictive equation to 114 cows with mastitis to determine if they would have coliform organisms cultured from the affected quarters resulted in an accuracy of 71% (sensitivity = 0.42, specificity = 0.85), compared to an accuracy of 62% (sensitivity = .64, specificity = .61) for cowside prediction by the attending clinicians. Changing the cutoff score of the discriminant rule so that the sensitivity of the discriminant prediction was similar to that of the clinicians yielded an accuracy of 64% (sensitivity = .64, specificity = .64).

Animals↗
PubMed1986

Evaluating toxin-induced hepatic injury in rats by laboratory results and discriminant analysis.

The ability of 14 serum biochemical assays to predict the presence of hepatic necrosis induced by carbon tetrachloride (CCl4) (centrilobular necrosis), allyl alcohol (periportal necrosis), and 1-napththylisothiocyanate (ANIT) (biliary duct necrosis) was evaluated in rats. Results of these assays were analyzed using multivariate discriminant analysis to determine: which assays have the highest predictive value for discriminating between control and treated rats, and which assays would discriminate between rats in the three treatment groups. Individual assays with the highest predictive value for CCl4-induced lesions versus controls were glutamate dehydrogenase (GDH), sorbitol dehydrogenase (SDH), and alanine aminotransferase (ALT). Assays with the highest predictive value for ANIT-induced lesions were GDH, 5'-nucleotidase (5'NT), and ALT. Assays the highest predictive value for ANIT-induced lesions were GDH, 5'-nucleotidase (5'NT), and ALT. Assays with the highest predictive value for allyl alcohol-induced lesions were an ALT/isocitrate dehydrogenase (ICD) ratio, GDH, and ALT. Canonical correlation coefficients for each assay ranged from 0.98 to 0.91 with 95-100% correct group membership predictions (treated versus control) provided by each assay. Individual assays were not highly predictive for determining group membership among all three treatment groups. A two assay combination of 5'NT and an ALT/ICD ratio provided 100% correct group membership predictions and had high canonical correlations (f1 = 0.95, f2 = 0.83).

1-Naphthylisothiocyanate↗
PubMed1997

Identification of protein coding regions in the human genome by quadratic discriminant analysis.

A new method for predicting internal coding exons in genomic DNA sequences has been developed. This method is based on a prediction algorithm that uses the quadratic discriminant function for multivariate statistical pattern recognition. Substantial improvements have been made (with only 9 discriminant variables) when compared with existing methods: HEXON [Solovyev, V. V., Salamov, A. A. & Lawrence, C. B. (1994) Nucleic Acids Res. 22, 5156-5163] (based on linear discriminant analysis) and GRAIL2 [Uberbacher, E. C. & Mural, R. J. (1991) Proc. Natl. Acad. Sci. USA 88, 11261-11265] (based on neural networks). A computer program called MZEF is freely available to the genome community and allows users to adjust prior probability and to output alternative overlapping exons.

Base Sequence↗
PubMed1980

Quantification of the expanded role of the nurse practitioner: a discriminant analysis approach.

Graduates of a family nurse practitioner program and a sample of nonpractitioner nurses were compared in terms of their professional roles and concomitant attitudes. The stepwide discriminant analysis technique used in the study permitted adjustments for variables that affect nursing roles and provided a method for quantifying differences between the two groups of nurses. Role differences were characterized by the nurse practitioners' more frequent performance of functions relatively new to the nursing profession, such as physical assessment and prescription of medications, as well as functions more traditional to nursing. Among the latter were several dimensions of patient education and counseling. Attitudes of the nurses toward their own role also differed between the two groups and may reflect a commitment to professional growth on the part of the nurse practitioners which is not as prominent among their nonpractitioner counterparts.

Adult↗
PubMed1976

Application of step-wise discriminant analysis and Bayesian classification procedure in determining prognosis of acute myocardial infarction.

A retrospective study was carried out to assess the feasibility of computer-assisted prognostication by discriminant analysis and the Bayesian classification procedure based on clinical information collected on patients with acute myocardial infarction. The overall accuracy was 94.2% in predicting hospital death but the prediction of late death after discharge was less accurate. It was found that not all of the 44 variables used for analysis were necessary to reach the same level of predictive accuracy--16 to 20 variables would result in almost the identical prediction. The Bayesian classification procedure was applied to estimate probabilities of individual patients belonging to the different prognostic categories.

Bayes Theorem↗
PubMed1983

Improved detection of Duchenne muscular dystrophy heterozygotes using discriminant analysis of creatine kinase levels.

We have assessed the sensitivity and specificity of tests to detect carriers of Duchenne muscular dystrophy by use of three serum enzymes (creatine kinase, pyruvate kinase, and aldolase) and discriminant analysis in 21 obligate heterozygotes and 28 normal controls. We found no significant age effects on enzyme levels. Each enzyme level considered separately was significantly higher in heterozygotes. Use of logs improved discrimination, and log CK was sufficient by itself as a discriminant (that is, addition of other enzymes did not significantly improve discrimination). We present procedures to generate posteriori probabilities for genetic counselling that incorporate prior probabilities and enzyme levels. Our results show both improved sensitivity (90%) and specificity (86%).

Adult↗
PubMed1988

Urodynamics in prostatism. IV. Search for prognostic patterns as evaluated by linear discriminant analysis.

In order to examine the prognostic role of routine urodynamic testing in prostatism, a prospective study was undertaken. The patients were selected for prostatic surgery exclusively by means of non-urodynamic criteria, but in addition an extensive, blinded urodynamic work-up was performed, including uroflowmetry, pressure-flow study combined with stop-flow test and water cystometry. The study comprised 139 patients consecutively referred for prostatism. Six months postoperatively all patients were reexamined. Previously the preoperative urodynamic data from each modality were analysed separately. In an attempt to increase the prognostic information, all data were computed simultaneously using linear discriminant analysis. Several preoperative variables appeared valuable to discriminate between patients with favourable and unfavourable postoperative outcome, respectively. However, the results of classification employing even the best combinations of variables did not result in more than 88% of the patients being correctly classified. Furthermore, especially the patients with unfavourable outcome generally were misclassified. Several reasons for this lack of efficacy are briefly mentioned, including the great overlap in preoperative urodynamic data between patients with favourable and unfavourable postoperative outcome and the relatively low postoperative failure rate.

Adult↗
PubMed1983

Differential diagnostic value in hepatobiliary disease of serum conjugated bile acid concentrations and some routine liver tests assessed by discriminant analysis.

Serum concentrations of glycine and taurine conjugates of cholic, chenodeoxycholic, and deoxycholic acid were measured with a HPLC-enzymatic assay in 104 patients with hepatobiliary diseases. The capability of discriminating between four major diagnostic categories by the serum bile acid concentrations, alone and in conjunction with five commonly used biochemical liver tests, was evaluated by stepwise linear discriminant analysis. The serum bile acid pattern alone was inferior to the routine liver tests in separating the diagnostic groups. When the two sets of analytes were combined, the generalized group distance (Rao's V) was significantly increased, showing that the serum bile acid pattern contained discriminatory information in addition to the routine liver tests. The gain in correct reclassification of patients obtained by adding the serum bile acids, however, was only marginal.

Adolescent↗
PubMed1988

Diagnosis and subtyping of depressive disorders by quantitative electroencephalography: I. Discriminant analysis of selected variables in untreated depressives.

Of 88 inpatients admitted for assessment of affective illness, 70 met RDC criteria for major depressive disorder. All patients had a quantitative electroencephalogram (QEEG) after ten days drug-free. Several QEEG variables were examined by multivariate stepwise discriminant analysis of data from patients and controls. Measures of interhemispheric coherence, beta activity, and slow wave excess were potent discriminators. Depressives were discriminated from normals with an accuracy of eighty-six percent. Primary depressives were discriminated from alcoholics, primary dementias and normals with an overall accuracy of 76% (25% expected by chance). Primary and secondary major depressives were correctly classified with 77% accuracy. Unipolar depressives were discriminated from bipolar depressives with 88% accuracy. Differential diagnosis and treatment implications are discussed.

Adolescent↗
PubMed1985

Premarital contraceptive use: a discriminant analysis approach.

The ability of seven independent variables to predict accurately, from a sample of unmarried, sexually active students, which ones use reliable contraceptives and which ones use unreliable contraceptives, was investigated. Using discriminant analysis, the seven independent variables were age individuals started engaging in coitus, frequency of coitus, frequency of dating, length of time sex partners knew each other, number of sex partners, having anticipated coitus to occur, and the number of close friends who were thought to use birth control. The results indicated that these variables were accurate in predicting which students were users of contraceptives, with more than 80% of males and females being correctly classified. The number of close friends thought to use contraceptives was the most influential variable for both sexes, followed by length of time the partners knew each other.

Adult↗
PubMed1980

[Discriminant analysis in the quantitative evaluation of lung scintigrams (author's transl)].

Lung scintigrams made with 99mTc-MAA in a group of patients and a control group were compared and classified by a discriminant analysis based on two regional methods and several parameters for quantitative characterisation of the regions. Improved results are gained by a regional division of the lung orientated in the pulmonary lobes and segments and by combining several parameters.

Analysis of Variance↗
PubMed1987

Pedigree discriminant analysis of two French Canadian Tay-Sachs families.

Two French Canadian families among whom the Tay-Sachs allele is segregating are analyzed to investigate whether there is residual phenotypic familial covariation over and above that from major gene segregation. The traits analyzed are functions of hexosaminidase A (HEXA) and hexosaminidase B (HEXB) levels, and a combination of segregation and discriminant analysis is used to find a function of HEXA and HEXB levels to discriminate between carriers and noncarriers in this French Canadian population. We found that residual familial covariation is significant for the ratio HEXA/(HEXA + HEXB), the statistic generally used to determine if an individual is likely to be a carrier of the Tay-Sachs allele in Ashkenazi Jewish populations. This suggests that the ratio may not be appropriate for the French Canadian group and that the mutation may be different from that in Ashkenazi Jews. A linear function is calculated that gives improved discrimination between carriers and noncarriers for the two French Canadian pedigrees studied.

Female↗
PubMed1983

Separation of essential hypertensive patients based on blood pressure responses after the withdrawal of antihypertensive agents by step-wise discriminant analysis.

Thirty-five patients with uncomplicated hypertension were observed for blood pressure behaviour after prolonged antihypertensive medication withdrawal. Twenty-three patients (Group 1) remained normotensive (systolic less than 140 mmHg, diastolic less than 95 mmHg) for over 60 weeks compared to 12 patients (Group 2) who became hypertensive again during a 4-week placebo period. Discriminant analysis was performed on 31 clinical and laboratory variables measured before therapy to separate any discriminating factors for the two groups. Four variables maximized the separation of Group 1 from Group 2 patients. In descending order, these were serum sodium (p less than 0.001), mean corpuscular volume (p less than 0.01), serum albumin (p less than 0.01), and body weight (p less than 0.05). Using these four variables 73.9% of patients in Group 1 and 75% of patients in Group 2 were classified correctly into their respective groups. It is suggested that this observation may be useful in the development of new therapeutic regimens for patients with uncomplicated essential hypertension, for example by predicting those patients who may respond favourably to intermittent therapy or even to its withdrawal.

Adult↗
PubMed2002

Nonparametric discriminant analysis of phytoplankton species using data from analytical flow cytometry.

BACKGROUND: Analytical flow cytometry (AFC) provides rapid and accurate measurement of particles from heterogeneous populations. AFC has been used to classify and identify phytoplankton species, but most methods of discriminant analysis of resulting data have depended on normality assumptions and outcomes have been disappointing. METHODS AND RESULTS: In this study, we consider nonparametric methods based on density estimation. In addition to the familiar kernel method, methods based on wavelets are also implemented. Full five-dimensional wavelet estimation proves to be computationally prohibitive with current workstation power, so we employ projection pursuit for reduction of dimensionality. AFC typically produces very large samples, so we also investigate data simplification through binning. Further modifications to the discrimination strategy are suggested by specific features of phytoplankton data, namely, a hierarchical group structure, the possible presence of many groups, and the likelihood of encountering an aberrant group in a test sample. CONCLUSIONS: We apply all the resultant procedures to appropriate subsets of a very large data set, demonstrate their efficacy, and compare their error rates with those of more conventional methods. We further show that incorporation of the specific features of phytoplankton data into the analysis leads to improved results and provides a general framework for analysis of such data.

Animals↗