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 613 records · Page 34Linked to original sources
PubMed1991

Potential of descriptive linear discriminant analysis for studying clinical chemical and haematological data from persons with heterozygous sickle cell disease.

To study the potential of multivariate classification methods in order to obtain more insight into abnormal laboratory data from patients with sickle cell disease, we investigated standard haematological and clinical chemical variables of 18 controls and 37 apparently healthy persons with heterozygous sickle cell disease (Hb AS), all women, using both univariate and multivariate classification methods. In the univariate method, those with Hb AS showed decreased serum log aspartate aminotransferase (log AST) activity, mean corpuscular volume and mean corpuscular haemoglobin (MCH) and increased sodium concentration. The multivariate method identified sodium, potassium, urea, uric acid, log AST, alanine aminotransferase and MCH as the variables that produced maximal separation between persons with Hb As and controls. It increased the 'non-error rate' for classification of persons with Hb AS by 16.4% compared with classification based on the variable, MCH, that produced maximal separation by the univariate method. The frequency distribution of percentage Hb S in the Hb AS group proved bimodal with maximal separation at 37.0% Hb S. The subgroup with 37.0% or less (n = 16) was considered to have concomitant heterozygous alpha-thalassaemia-2. In the univariate method the subgroup characterized by greater than 37.0% Hb S (n = 21) had increased serum sodium and uric acid concentrations, perhaps related to sickle cell nephropathy, whereas the subgroup with less than or equal to 37% Hb S did not. The multivariate method added information to the univariate method by additionally identifying abnormalities in serum potassium and urea concentrations in the former subgroup.(ABSTRACT TRUNCATED AT 250 WORDS)

Adult↗
PubMed2005

Possible contribution of artificial neural networks and linear discriminant analysis in recognition of patients with suspected atrophic body gastritis.

AIM: To investigate whether ANNs and LDA could recognize patients with ABG in a database, containing only clinical and biochemical variables, of a pool of patients with and without ABG, by selecting the most predictive variables and by reducing input data to the minimum. METHODS: Data was collected from 350 consecutive outpatients (263 with ABG, 87 with non-atrophic gastritis and/or celiac disease [controls]). Structured questionnaires with 22 items (anagraphic, anamnestic, clinical, and biochemical data) were filled out for each patient. All patients underwent gastroscopy with biopsies. ANNs and LDA were applied to recognize patients with ABG. Experiment 1: random selection on 37 variables, experiment 2: optimization process on 30 variables, experiment 3: input data reduction on 8 variables, experiment 4: use of only clinical input data on 5 variables, and experiment 5: use of only serological variables. RESULTS: In experiment 1, overall accuracies of ANNs and LDA were 96.6% and 94.6%, respectively, for predicting patients with ABG. In experiment 2, ANNs and LDA reached an overall accuracy of 98.8% and 96.8%, respectively. In experiment 3, overall accuracy of ANNs was 98.4%. In experiment 4, overall accuracies of ANNs and LDA were, respectively, 91.3% and 88.6%. In experiment 5, overall accuracies of ANNs and LDA were, respectively, 97.7% and 94.5%. CONCLUSION: This preliminary study suggests that advanced statistical methods, not only ANNs, but also LDA, may contribute to better address bioptic sampling during gastroscopy in a subset of patients in whom ABG may be suspected on the basis of aspecific gastrointestinal symptoms or non-digestive disorders.

Adult↗
PubMedDate not supplied

Virtual screening using binary kernel discrimination: analysis of pesticide data.

This paper discusses the use of binary kernel discrimination (BKD) for identifying potential active compounds in lead-discovery programs. BKD was compared with established virtual screening methods in a series of experiments using pesticide data from the Syngenta corporate database. It was found to be superior to methods based on similarity searching and substructural analysis but inferior to a support vector machine. Similar conclusions resulted from application of the methods to a pesticide data set for which categorical activity data were available.

Algorithms↗
PubMed1988

On the sensitivity of linear discriminant analysis to sampling variation and analytical errors.

The influence of analytical inaccuracy and imprecision on the linear discriminant function is considered. Analytical shifts occurring between the analysis of samples from each of two groups give spuriously low error rates if the function is evaluated on the training set, notably at high dimensions. Inaccuracy arising after the establishment of a discriminant function may change considerably the individual group error rates whereas the overall error rate is moderately affected. Imprecision decreases the group separation by an amount comparable to that in the univariate situation. In conclusion, evaluation of the error rates of a discriminant function on an independent test set is important to obtain realistic estimates of the performance and is preferable to using unbiased statistical methods or the split-sample principle based solely upon the training set.

Biometry↗
PubMed1994

Discriminant analysis of macrocytic red cells.

Laboratory classification of red cell disorders uses the red cell indices (MCV, MCH, MCHC, RDW) and information gleaned from microscopic evaluation of a blood film. Additional red cell information is now available using the H series of automated blood cell analysers (Ames Technicon Division of Bayer Diagnostics). This study involved the development of a discriminant rule which would differentiate between three causes of macrocytosis (vitamin B12/folate deficiency, alcohol excess/liver disease and a reticulocytosis) using the information available on Research Screen 1 and Report Screen 3 of the H*1 instrument (Report Screen 3 is a graphical display of the trimmed scattergram of red cell volume and red cell haemoglobin concentration and Research Screen 1 displays the associated numerical data). Three methods of analysis were assessed to define a suitable discriminant rule. The percentages of patients correctly classified by the three methods were: 92.1%, 82.0% and 89.2% for Methods 1, 2 and 3 respectively. Method 1 involved the application of quadratic discrimination to transformed variables and produced the best results. Although complex, it could easily be applied using the microprocessor capability of the average multiparameter haematology analyser.

Alcoholism↗
PubMed1983

Separation of subtypes of depression using discriminant analysis. Separation of bipolar endogenous depression from nonendogenous ("Neurotic") depression.

We derived a discriminant function separating patients with bipolar endogenous depression ("melancholia") from patients with nonendogenous ("neurotic") depression, and showed that the difference between the groups was not one of overall severity of illness alone. The discriminant function (DF) included 5 clinical items. We reduced the DF to a discriminant index (DI) with integral item weights, and trichotomized the DI scores into two definite classifications and an intermediate, uncertain classification. We cross-validated this DI in a separate group of patients, and found no decrease in the accuracy of classification on cross-validation. Thirty-three of 41 (80%) of the patients in the cross-validation group were classified by the DI; 26 of 33 (79%) correctly. We also validated the DI classification against an external, biological marker, the dexamethasone suppression test (DST). The DI predicted the DST result with the same accuracy as the clinical diagnoses did, supporting the validity of the DI.

Adult↗
PubMed1999

A discrimination analysis of training-structure effects on stimulus equivalence outcomes.

Experiments designed to establish stimulus equivalence classes frequently produce differential outcomes that may be attributable to training structure, defined as the order and arrangement of baseline conditional discrimination training trials. Several possible explanations for these differences have been suggested. Here we develop a hypothesis based on an analysis of the simple simultaneous and successive discriminations embedded in conditional discrimination training and testing within each of the training structures that are typically used in stimulus equivalence experiments. Our analysis shows that only the comparison-as-node (many-to-one) structure presents all the simple discriminations in training that are subsequently required for consistently positive outcomes on all tests for the properties of equivalence. The sample-as-node (one-to-many) training structure does not present all the simple discriminations required for positive outcomes on either the symmetry or combined transitivity and symmetry (equivalence) tests. The linear-series training structure presents all the simple discriminations required for consistently positive outcomes on tests for symmetry, but not for symmetry and transitivity combined (equivalence) or transitivity alone. Further, the difference in the number of simple discriminations presented in comparison-as-node training versus the other training structures is larger when the intended class size is greater than three or the number of classes is larger than two. We discuss the relevance of this analysis to interpretations of stimulus equivalence research, as well as some methodological and theoretical implications.

Discrimination Learning↗
PubMed1983

Pedigree discriminant analysis: a method to identify monogenic segregation.

We describe a method for obtaining a linear discriminant function to identify monogenic segregation in multivariate pedigree data. It differs from Fisher's linear discriminant function in that it does not assume that the genotype of each individual in the pedigree already known. The method consists of finding that linear function of the variables that maximizes the likelihood of a set of pedigree data, under the hypothesis of single gene segregation, subject to the constraint that the total sample variance of the function remains constant. To simplify the computation the variables are first transformed to their standardized principal components. Reanalysis of a set of pedigree data suggests that age and powers of age should be considered as extra variables from which the principal components are obtained, and virtually all of the variance should be accounted for by the principal components used to obtain the discriminant function.

Age Factors↗
PubMed1982

Separation of subtypes of depression using discriminant analysis. I. Separation of unipolar endogenous depression from non-endogenous depression.

We derived a discriminant function based on clinical features to classify patients with endogenous depression ('melancholia') and non-endogenous ('neurotic') depression. The difference between the groups was not one of overall severity of illness alone. Bipolar melancholic patients were classified less well than were unipolars, supporting previous findings of clinical differences between these groups. The discriminant function (DF) was reduced to a discriminant index (DI) which classified a separate group of unipolar melancholic and non-endogenous patients with comparable accuracy. Approximately 80 per cent of all cases received a definite classification by the DI. The agreement between the 105 definite DI classifications and the clinical diagnoses was 90 per cent when results from the derivation and validation groups were combined. The DI classification was then validated against an objective biological marker, the dexamethasone suppression test (DST). The diagnostic discriminant index predicted the DST result with the same accuracy as the clinical diagnoses. The discriminant index can serve as an operational definition of the patients diagnosed as endogenous or nonendogenous unipolar depression in future studies by ourselves and other groups of investigators.

Adult↗
PubMed1988

Quantitative grading of exercise stress test for patients with coronary artery disease using multivariate discriminant analysis.

A group of 111 male patients who had undergone maximal or symptom-limited maximal exercise stress testing for evaluation of coronary artery disease (CAD) were subjected to coronary angiography. Group I comprised 33 patients with normal or single-vessel disease (SVD), while 78 patients with double-vessel disease (DVD) or triple-vessel disease (TVD) formed Group II. On univariate analysis of the exercise test, the following variables were found to be of significance in discriminating between the two groups: age, exercise duration, double product (heart rate X systolic blood pressure) at peak exercise, duration of ST-segment depression, number of leads showing ST depression, ST depression of 1 mm or more, configuration of the depressed ST segment, and diastolic blood pressure response to exercise. Multivariate analysis however revealed that only the following five variables had significant discriminant power: number of leads showing ST depression, exercise duration, double product, diastolic pressure response, and ST-segment configuration. On the basis of their relative importance, a regression equation was developed to give a quantitative score to individual patients. A score of less than zero detected multivessel disease (MVD) with high specificity (94%) and sensitivity (70%), while a score of 15 or more almost excluded MVD (sensitivity 87%). The scoring system as reported here improved the exercise stress test interpretation when compared with the conventional reporting system.

Adult↗
PubMedDate not supplied

Discriminant analysis based on multivariate response curves: a descriptive approach to dynamic allocation.

We examine the problem of discriminating between two groups in the context of multivariate response curves observed over a specified time interval. We propose a descriptive solution for the case where one can determine the response curves by linear interpolation between successive observations. Unlike most previously reported methods that use only the current multivariate observation, our approach accounts for the history of the process. Moreover the method has the potential advantage of being applicable dynamically, as one observes the multivariate response curve. Finally, the method demonstrates simplicity and flexibility, two important features for successful, routine, clinical application.

Humans↗
PubMed1993

Drug discrimination analysis of endogenous neuroactive steroids in rats.

Rats were trained in a two-lever procedure to discriminate either pentobarbital (10 mg/kg), ethanol (1.5 g/kg), diazepam (1 mg/kg), or lorazepam (1 mg/kg) from the no-drug condition. Consistent with previous reports, rats in the pentobarbital, ethanol, and diazepam training conditions all showed complete dose-dependent generalization to pentobarbital under test conditions, but rats trained to discriminate lorazepam did not. Administration of the neuroactive steroids 3 alpha,21-dihydroxy-5 alpha-pregnan-20-one (3 alpha,5 alpha-THDOC) and 3 alpha-hydroxy-5 alpha-pregnan-20-one (3 alpha,5 alpha-P) also produced complete generalization in rats trained to discriminate pentobarbital, ethanol, and diazepam, but not in rats trained to discriminate lorazepam. These results further indicate the specificity of the lorazepam training condition and are consistent with neurochemical data indicating that these neuroactive steroids are similar to barbiturates in modulating gamma-aminobutyric acid (GABA)A receptors. In the context of previous data, the results from the four training groups suggest that the discriminative-stimulus effects of the neuroactive steroids are sedative/anxiolytic in nature and probably mediated through a non-benzodiazepine GABAA site.

Animals↗
PubMedDate not supplied

A drug discrimination analysis of ethanol-induced behavioral excitation and sedation: the role of endogenous opiate pathways.

The drug discrimination technique was used to characterize the biphasic behavioral effects of ethanol (ETOH) and examine the role of opiate pathways in mediating ETOH's excitatory (EX) and sedative (SED) phase effects. Forty Sprague-Dawley rats were trained to perform ETOH vs. saline discriminations during either ETOH's EX (6 min post-dose) or SED (30 min post-dose) phase of action in a double-lever food reinforced operant paradigm. After animals had achieved the required performance criterion, dose-response and phase-generalization tests were conducted in each group. In addition, preliminary studies were conducted to examine the effect of naloxone (NLX) pretreatment on discrimination of ETOH's EX and SED phase stimulus effects. Results of generalization testing demonstrate that discrimination of ETOH was dose-dependent and there was no generalization between phases regardless of the initial training condition. NLX pretreatment significantly attenuated discrimination of ETOH's EX phase effects but was ineffective in antagonizing ETOH's SED effects. These data demonstrate that the stimulus properties of ETOH are phase-dependent and suggest that opiate pathways are critical for the expression of ETOH's EX phase behavioral effects.

Animals↗
PubMed1986

Epidemiology of polyps in the rectum and sigmoid colon. Discriminant analysis for identification of individuals at risk of developing colorectal neoplasia.

In an endoscopic population screening examination for detection of colorectal polyps among 324 men and women aged 50-59 years, adenomas greater than or equal to 5 mm in diameter were found in 38 individuals, and 212 were polyp-free. Dietary registration was performed by 155 individuals on a case/control basis. At 2 years' follow-up study polyps less than 5 mm in diameter were also removed. This rendered a total of 39 adenoma patients and 59 polyp-free individuals available for a combined analysis of both case history and dietary information. Application of a linear discriminant model on the combined clinical and dietary information enabled us to select a possible set of variables to characterize 88 out of 98 individuals (90%) correctly as adenoma patients or polyp-free individuals. However, when only case history information was used for the total material of 38 adenoma patients and 212 polyp-free individuals, only 189 out of 250 individuals (76%) were correctly classified. Although age, smoking habits, and a family history of colorectal cancer appeared as useful variables in the discriminant function, this study demonstrated the importance of nutritional factors in characterization of adenoma patients in the present age group of 50-59 years. In the present study we could not find any set of case history information which could indicate the usefulness of a questionnaire-based 'pre-screening' to guide recommendations for endoscopic screening examination.

Colonic Polyps↗
PubMed1983

Differentiating regular from irregular dental attenders of either sex by linear discriminant analysis.

The present article describes an attempt to improve the prediction of dental attendance, results by using an additional number of variables and performing discriminant analyses, done separately for men and women. It appears that regular and irregular dental attenders might be discriminated on the basis of mathematically combined variables and interactions. The (number of) variables selected by the analysis to differentiate regular from irregular male attenders differ(s) from those selected for female attenders. About 80% of all respondents can be classified correctly, but this is largely due to the assignment of actual regulars to classified regulars. The use of differing sets of prior probabilities affects the classification results, namely, either the classification of the regulars or that of the irregulars improves. In the discussion attention is given to the seemingly contradictory results of the Mann-Whitney tests per variable on the one hand and the discriminant analyses on the other. In this connection, the finding that 'education' plays a different role for men than for women is discussed. The validity of the variable 'last visit' is dubious. It is concluded that when differentiating regulars from irregulars, a division of the respondents according to sex makes sense because of the (number of) variables associated with their regular dental attendance. Furthermore, it seems warranted to say that the classification of the irregulars fails because the reversed scores on the variables with which the regulars are classified don't contain all information needed for the prediction of irregular dental attendance. Lastly, notwithstanding the use of more variables in the present study, the results are not better than those in the previous one, in which just three factors were used.

Adolescent↗
PubMed1987

Discriminant analysis of the Self-Administered Alcoholism Screening Test.

For a sample of 1156 patients (520 alcoholics and 636 nonalcoholics), discriminant function analyses were performed on the total score, a nine-item version, and a two-item version of the Self-Administered Alcoholism Screening Test (SAAST). With sensitivities set at 90 and 95%, specificities for the total score and nine-item versions ranged from 96.4 to 99.4%. Cross-validation of the nine-item version with the "jackknife" procedure resulted in only one additional misclassification of the 1156 subjects. Separate analyses of the male and female samples revealed that more items entered the discriminant function for women than for men and resulted in a higher, although clinically nonsignificant, percentage of correct classification for women. The results strongly support the use of either the total score or the nine-item version of the SAAST in large-scale screening for alcoholism in a medical patient population.

Adult↗
PubMed1979

Two kinds of radicals: a discriminant analysis of a projective test.

Rorschach tests were administered to 36 subjects grouped according to ethnicity and political ideology. Pairwise discriminant analyses of scores significantly differentiated both Jewish and non-Jewish radicals from nonradicals in a manner consistent with previous survey findings.

Journal Article↗