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 469 records · Page 26Linked to original sources
PubMed1978

Evaluation of the discriminative power of lipidophoresis by discriminant analysis using a simple quantitative method of agarose lipidophoresis.

A simple, reproducible and quantitative method for separation of lipoproteins in agarose is presented. The validity of the results is shown by comparison with gravimetric analysis of fractions separated by ultracentrifugation in a discontinuous NaCl-KBr gradient. Results for a large group of normals and of patients with various lipid disorders are presented, and discriminant analysis is used to evaluate objectively the potential of lipidophoresis in the classification of hyperlipoproteinemias. It is shown that quantitative lipidophoresis gives as much information as the determination of cholesterol and triglycerides, for classification purposes.

Adult↗
PubMed1981

Antenatal prediction of women at increased risk for infants with low birth weight. A discriminant analysis of maternal characteristics known at 24 weeks.

Prenatal factors known to be associated with delivery of an infant with low birth weight (LBW) were studied in 165 women who were delivered of infants of 25,000 gm or less, as well as 154 women who were delivered of term infants with normal birth weights (greater than 2,500 gm). Data included information related to th clinical course of the pregnancy through 24 weeks' gestation. Of 25 characteristics measured prenatally, 10 variables were identified with indicated differences between the LBW and normal birth weight groups sufficient to make them suitable for a discriminant analysis. Following further analysis and attribute reduction, eight variables were selected as the final set of discriminating attributes. These are: maternal age, height, and weight, the patients's perception of her own parental treatment as a child, presence of uterine anomalies, bleeding during pregnancy, suspected multiple gestation, and number of previous pregnancies ending with a gestational age of 13 through 36 weeks. On the basis of coefficients derived for each of these variables, an equation was developed to derive a discriminant score for each patient. With the use of such equations, 73.5% of the known cases were correctly classified into groups with low and high birth weight. A similar high correct classification of cases was made when suspected multiple gestation was excluded as a variable.

Adolescent↗
PubMed1985

[Discriminant analysis of the mandible for sex determination].

Seventeen measuring parameters were used to characterize 197 mandibles (109 males, 88 females) taken from the corpses of people 20-80 years of age from the Rhine-Main-Neckar area. The representative measuring parameters and discriminating functions of intact lower jaws and lower jaw fragments of most frequent fracture types were determined in this practice group by means of discriminating analysis. In the present research material it was possible to determine sex accurately from an intact lower jaw bone in 82.6% (m) and 79.5% (f) of the cases. Furthermore, our results show clearly that sex may even be determined from lower jaw fragments. The classification was correct, depending on the type of fragment, in 72.5%-81.7% (m) and 71.6%-79.5% (f) of the cases.

Adult↗
PubMed1992

In vivo spectrophotometric evaluation of neoplastic and non-neoplastic skin pigmented lesions. II: Discriminant analysis between nevus and melanoma.

Reflectance spectrophotometry from 420 to 780 nm on 31 primary melanoma and 31 benign nevi has been performed by using an external integrating sphere coupled to a spectrophotometer. Measurements show that reflectance spectra of melanoma and nevi manifest dissimilar patterns. From these spectra four variables, whose physical and/or physiological meanings remain to be investigated, have been derived. All of them are significantly different when compared between melanoma and nevi. A discriminant function between the two groups of lesions has been determined by using a stepwise discriminant analysis, resulting in a test with a sensitivity of 90.3% and a specificity of 77.4%. This method of discrimination between melanoma and nevi seems to have a discriminating power almost equal to that of a clinical judgement from a specialized medical doctor, thus suggesting a new method for screening skin pigmented lesions.

Diagnosis, Differential↗
PubMed1977

Use of discriminant analysis in relating maternal anti-D levels to the severity of haemolytic disease of the Newborn.

The automated assay of maternal anit-D levels has been compared with manual methods and correlated with the severity of haemolytic disease of the newborn using discriminant analysis. The automated assay of anti-D proved to be marginally better than manual techniques in predicting the need for amniocentesis. The level at which amniocentesis should be considered has been calculated to be 4IU/ml of maternal serum.

Animals↗
PubMed1979

Application of discriminant analysis to level of performance of alcoholics and nonalcoholics on Wechsler-Bellevue and Halstead-Reitan subtests.

Investigated the utility of subtests from the Wechsler-Bellevue Intelligence Scale and the Halstead-Reitan Neuropsychological Test Battery to differentiate between alcoholics and nonalcoholics (N = 76). Analyses of variance indicated that the alcoholics were more impaired than nonalcoholics. It was found that the Wechsler-Bellevue Performance subtests were more discriminative than were Verbal subtests, with performance on the Halstead-Reitan variables being intermediate. The nine measures that differentiated most significantly between groups were subjected to a stepwise multivariate discriminant analysis. The resulting function correctly classified Ss with an overall accuracy of 74.7%. It was found that the Block Design subtest was the best single discriminator. The findings were discussed in relationship to previous findings and with respect to general issues of clinical neuropsychological assessment.

Alcoholism↗
PubMed1985

[Multivariate discriminant analysis--a current method for evaluating the enzyme spectrum in cancer patients].

The study was concerned with the procedure and results of evaluation of the clinical course versus enzymatic activity in blood serum of patients with breast, uterine and bladder tumors. Mathematical and statistical methods used in multivariate discriminant analysis offer more advantage as compared with the standard procedures for evaluation of enzymatic activity in blood serum of cancer patients.

Breast Neoplasms↗
PubMed1979

Discriminant analysis: a method of identifying foci of vector-borne diseases.

Identification of foci of vector-borne diseases does not require knowledge of exact abundances of vectors and pathogens; rather, a focus is defined by the presence, or some minimal level of abundance, of a vector and pathogen. Stepwise discriminant analysis (DA) was applied to data on free-ranging adult wood ticks (the vector) and to data on isolations of Colorado tick fever virus from small mammals. Trap stations were grouped on the basis of relative abundance of wood ticks for one set of analyses and on the presence or absence of virus for another set of analyses. Additional data consisted of easily measured environmental variables. It is concluded that DA provides a useful tool for analysis of ecosystem structure and an effective means of identifying foci of infection.

Animals↗
PubMed1984

Discriminant analysis of Hodgkin's disease and non-Hodgkin's lymphomas by age and serum proteins.

Immunonephelometric evaluations of 13 serum proteins were made in 71 patients with two types of lymphoproliferative diseases: Hodgkin's disease (32 patients) and non-Hodgkin's lymphomas (39 patients). The subjects were differentiated by discriminant analysis by means of age and three selected proteins: properdin factor B, IgM and ceruloplasmin. The results obtained permitted classification of 90% of the cases reported.

Adolescent↗
PubMed1984

Appointment compliance behavior of community mental health patients: a discriminant analysis.

This study evaluated various demographic and psychiatric signs and symptoms of community mental health clients in an attempt to identify those variables which influence appointment compliance behavior. A sample of 172 non-psychotic clients with a primary diagnosis of neurosis, personality disorder, or transient-situational disturbance were studied utilizing discriminant analysis. The results indicate that approximately 85 percent of the clients were properly classified as either compliant or non-compliant in their appointment behavior. The implications for mental health care are discussed.

Adult↗
PubMed2005

Biochemical measures in the diagnosis of alcohol dependence using discriminant analysis.

BACKGROUND: Alcohol dependence often cannot be diagnosed based on self-report alone. Various biochemical and haematological parameters have been used to screen alcohol use disorders. AIM: To develop discriminant equations based on lipid and liver measures independently for identifying alcohol dependent and non-dependent subjects. SETTINGS AND DESIGN: Case control study in a tertiary care hospital. METHODS AND MATERIALS: One hundred subjects fulfilling the criteria of alcohol dependence and seventy healthy controls were included. The socio-demographic details, caloric intake, height, weight and blood pressure were recorded. Samples were analysed for various lipid measures as well as liver function. STATISTICAL ANALYSIS USED: Diagnostic values such as sensitivity, specificity, positive predictive value (PV+), negative predictive value (PV-) and discriminant analysis. RESULTS: Using discriminant analysis, two equations were constructed based on liver and lipid measures independently. 84.7% of the subjects on the basis of total cholesterol (TC), apolipoprotein B (ApoB) and low density lipoprotein/high density lipoprotein-cholesterol (LDL/HDL-c and 89.1% on the basis of aspartate amino transferase (AST) and gamma glutamyl transferase (GGT) were correctly classified into their respective groups. CONCLUSIONS: This study demonstrates the ability of TC, ApoB and LDL/HDL-c (among lipid measures) and AST and GGT (among liver measures) in discriminating alcohol dependents from non-dependent subjects.

Adolescent↗
PubMed1991

Distinguishing between conduct problem and emotionally disturbed students in secondary school: a five-instrument discriminant analysis.

Five instruments, the Differential Test of Conduct and Emotional Problems, Louisville Behavior Checklist, Personality Inventory for Children, 16 PF Test, and Tennessee Self-concept Scale, were given to differentiate between 50 conduct problem and 48 emotionally disturbed students assigned in public school to secondary level classes for the severely emotionally handicapped. Discriminant analysis of each test's rate of classification germane to both a pre-assessment categorization as conduct problem vs emotionally disturbed and a post-assessment classification as no problem vs conduct problem vs emotionally disturbed vs combined problem is presented. The analysis indicated that the Differential Test of Conduct and Emotional Problems, Louisville Behavior Checklist, and Personality Inventory for Children can, with variable effectiveness, significantly classify adolescents into groups using such pre- and post-assessment information.

Adolescent↗
PubMed2007

Features of metabolic syndrome in non-diabetic Italians and Brazilians: a discriminant analysis.

This aim of this study was to compare the characteristics of metabolic syndrome (MetS) in a Brazilian and an Italian population. The subjects were non-diabetic men and women aged 40-74 years from population-based surveys: 1242 from Brazil and 1198 from Italy. Logistic regression models were used to compare adjusted prevalence rates and make a discrimination analysis to distinguish the subjects with a diagnosis of MetS in the two groups. Dyslipidemia [low high-density lipoprotein (HDL)-cholesterol] and impaired fasting glucose were more prevalent among the Brazilians, and increased blood pressure and abdominal obesity (in men) among the Italians. Generally, the Italians showed higher prevalence of overall obesity and high pulse-pressure, and the Brazilians had higher prevalence of metabolic markers of insulin resistance. Among the subjects with the syndrome, HDL-cholesterol was the most discriminant factor, followed by plasma uric acid levels (which were higher in the Brazilians). The Italian men had a larger waist circumference and the Italian women higher body mass index values than the Brazilians. Italians had higher systolic and lower diastolic pressure values. The patterns of the metabolic alterations seemed to be more linked to insulin resistance among Brazilian subjects, whereas obesity seemed to play a more important role among the Italians. Although they are not sufficient to support the hypothesis of differences in the underlying pathophysiological processes between these groups, our results illustrate the difficulty of using a single unifying definition of MetS, and suggest that different benefits may be obtained from treatments targeting obesity, blood pressure or insulin resistance.

Adult↗
PubMed1983

Discriminant analysis of the localization of aggression-inducing electrode placements in the hypothalamus of male rats.

Over 400 sites in the hypothalami of 270 male CPB/WE-zob rats were electrically stimulated in order to induce fights between males. The localization of electrodes inducing fights seems to differ from the localization of electrodes in which no fights can be induced. The differences in localization were detected and tested by a non-parametric discriminant analysis. The results were plotted by computer in a stereotaxic atlas of the hypothalamus of the CPB/WE strain. The method delimits areas within the hypothalamus where the probability to induce aggression is high, intermediate or low. Moreover, the procedure allows discrimination between areas where the thresholds for attack behaviour are generally lower than elsewhere and where the fiercest forms of attack are induced. None of the areas delimited coincide with a classical subdivision of the hypothalamus. Parts of the perifornical, anterior, lateral and ventromedial hypothalamus seem to be involved. The methods developed here may help to relate stimulation-induced aggression to other characteristics of the 'aggressive' area which cannot be obtained directly from fighting rats such as cytological, endocrinological, biochemical or physiological data. In addition, the procedure may help to settle disputes on the specificity of the localization of neural substrates of other stimulation-induced behaviours. The methods to discriminate between overlapping 3-dimensional reconstructions validated here for aggressive responses, can also be applied to other types of stereotaxic data and other types of effects, such as electrical, hormonal or other physiological responses. They may be especially useful if the localization of the neural population involved is not yet known, and unknown current-spread or diffusion of substances complicates the interpretation of stereotaxic data.

Aggression↗
PubMed2005

A linear discrimination analysis based virtual screening of trichomonacidal lead-like compounds: outcomes of in silico studies supported by experimental results.

A computational (virtual) screening test to identify potential trichomonacidals has been developed. Molecular structures of trichomonacidal and non-trichomonacidal drugs were represented using stochastic and non-stochastic atom-based quadratic indices and a linear discrimination analysis (LDA) was trained to classify molecules regarding their antiprotozoan activity. Validation tests revealed that our LDA-QSAR models recognize at least 88.24% of trichomonacidal lead-like compounds and suggest using this methodology in virtual screening protocols. These classification functions were then applied to find new lead antitrichomonal compounds. In this connection, the biological assays of eight compounds, selected by computational screening using the present models, give good results (87.50% of good classification). In general, most of the compounds showed high activity against Trichomonas vaginalis at the concentration of 100 microg/ml and low cytotoxicity to this concentration. In particular, two heterocyclic derivatives (VA7-67 and VA7-69) maintained their efficacy at 10 microg/ml with an important trichomonacidal activity (100.00% of reduction), but it is remarkable that the compound VA7-67 did not show cytotoxic effects in macrophage cultivations. This result opens a door to a virtual study considering a higher variability of the structural core already evaluated, as well as of other chemicals not included in this study.

Animals↗
PubMed1997

Study of major volatiles in wines and discriminant analysis applied to classification according to region.

The major volatiles of eighty eight wines (white, rosè and red) from Madrid were studied. The samples came from the three districts forming the "Vinos de Madrid" DO (Denominación de Origen) region: Arganda, Navalcarnero and San Martín, and were analyzed by gas chromatography. The resulting data were treated by Stepwise Discriminant Analysis (SDA) in order to ascertain the efficacity of these compounds in classifying the wines according to their geographical origin. The results confirm that the above components were of little use in classifying the red and white wines and, although a correct classification percentage of 90.91% was obtained for the rosés when all the variables were used, this too was considered unsatisfactory.

Chromatography, Gas↗
PubMed1994

Differential diagnosis of Parkinson's disease, multiple system atrophy, and Steele-Richardson-Olszewski syndrome: discriminant analysis of striatal 18F-dopa PET data.

Clinicopathological series indicate that the clinical diagnosis of Parkinson's disease is correct in only 80% of cases. Multiple system atrophy (MSA) and Steele-Richardson-Olszewski syndrome (SRO) comprise most of the misdiagnoses. By means of 18F-dopa PET the pattern of nigrostriatal dopaminergic dysfunction in 28 patients with clinically probable Parkinson's disease, 25 with MSA, and 10 patients with SRO, was assessed and compared with the pattern in 27 normal subjects. Discriminant function analysis was used to assess the ability of 18F-dopa PET to categorize individual parkinsonian patients on the basis of their caudate and putamen tracer uptake. Discriminant function analysis assigned all control subjects a normal category. One Parkinsonian patient out of 63 was classified as "normal" on the basis of PET findings, although this patient had significantly reduced putamen 18F-dopa uptake. Discriminant function analysis was less effective at distinguishing different categories of akinetic-rigid syndrome on the basis of their striatal 18F-dopa uptake, as judged against clinical criteria. Patients clinically labelled as having typical or atypical Parkinsonian syndromes were assigned the same category on PET criteria 64% and 69% of the time, respectively. When all three categories of Parkinson's disease, MSA, and SRO were considered together, clinical and 18F-dopa PET findings correlated in 64% of patients assigned a diagnosis of Parkinson's disease and 70% of those given a diagnosis of SRO; MSA was less readily discriminated, patients with MSA being assigned to MSA, Parkinson's disease, and SRO groups with equal frequency. The correlation between clinical and discriminant function analysis assignment improved when separate comparisons were made between Parkinson's disease and MSA, or Parkinson's disease and SRO groups. In these analyses, clinical and PET categorisation of MSA and Parkinson's disease agreed in 60% of cases, and of SRO and Parkinson's disease in 90% of cases. In summary, (18)F-dopa PET successfully discriminates normal subjects from parkinsonian patients, and patients with Parkinson's disease from patients with SRO, but is less reliable in distinguishing Parkinson's disease from MSA. The concomitant assessment of striatal neuronal function with additional PET tracers may be necessary to reliably differentiate typical and atypical parkinsonian syndromes.

Adult↗