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 199 records · Page 11Linked to original sources
PubMed2003

[The use of discrete characters in discriminant analysis for diagnosis of pulmonary tuberculosis and for classification of patients differing in treatment efficiency based on polymorphisms at nine codominant loci-HP, GC, TF, PI, PGM1, GLO1, C3, ACP1 and ESD].

Discriminant analysis was used to differentiate patients with pulmonary tuberculosis (N = 106) from healthy individuals (N = 328) and patients whose treatment was efficient (N = 71) from those whose treatment was inefficient (N = 35). The analysis involved the data on nine polymorphic codominant loci: HP, GC, TF, PI, PGM1, GLO1, C3, ACP1, and ESD. The loci were selected by significance of differences in genotype frequencies between tuberculosis patients and healthy controls (GC, TF, PI, C3, ACP1) or between the two groups of patients differing in treatment efficiency (HP, GC, PI, PGM1, C3, ESD). Discrimination was based on a graphic method of Bayes classification procedure with a single-variate nomograph allowing easy estimation of the a posteriori probabilities for an individual to be classified. The two groups of patients proved to be discriminated sufficiently well (probability of misclassification Perr = 0.24), whereas discrimination between tuberculosis patients and healthy individuals was less efficient (Perr = 0.33). The method was proposed as a means of predicting the efficiency of treatment in pulmonary tuberculosis. Along with clinical, roentgenological, and laboratory examination, discriminant analysis may be employed as an accessory test in diagnostics of pulmonary tuberculosis, especially when the diagnosis is questionable.

Adult↗
PubMed1999

Immunological diagnosis of human cystic echinococcosis: utility of discriminant analysis applied to the enzyme-linked immunoelectrotransfer blot.

An enzyme-linked immunoelectrotransfer blot for the diagnosis of human hydatid disease was performed, and the different antibody responses were analyzed by a discriminant analysis. This multivariate technique gave us, first, a selection of the most important responses against Echinococcus granulosus infection and, second, a procedure for the classification of patients into two groups: patients with hydatid disease and patients without a history of hydatid disease. This method was applied to 67 patients, 25 with active hydatid cysts (24 hepatic and 1 pulmonary) and 42 without a history of hydatid disease and was compared with the results obtained by conventional serology: indirect hemagglutination, latex particle agglutination, and basophil degranulation. An immunoelectrotransfer blot coupled to a discriminant analysis was more sensitive than conventional serological diagnosis and detected 100% of patients with an active hepatic hydatid cyst with a specificity of 100%. This method, however, failed to detect an uncomplicated hyaline pulmonary hydatid cyst.

Discriminant Analysis↗
PubMed1991

[Quantitative EEG analysis and the value for differential diagnosis on depression: II. Multivariate regression and discriminate analysis].

Multivariate regression and discriminate analyses were carried out based on the EEG power variables and some related clinical materials from 47 depressed patients and 43 normal controls. The results of regression analysis showed that the severity and duration of depression were associated with EEG slow activity, while the age of first episode and age of the patients were associated with EEG fast activity. Discriminate analysis clearly demonstrates the possible utility of EEG data in the differential diagnosis of depression.

Adolescent↗
PubMed1997

Optimal discriminant analysis for ordinal responses.

Optimal classification formulation is adapted to the context of discrimination when the response is ordinal. The resulting method, optimal discriminant analysis for ordinal responses (ODAO), is presented and compared with two reference discrimination techniques used in this context (proportional-odds ordinal logistic regression and normal discrimination) using a study of prognosis following burn injuries and simulated data. The ODAO method clearly outperforms both reference methods in terms of classification accuracy (in training and validation samples), robustness to outliers, simplicity of use and applicability in clinical settings. ODAO is a promising method for improving classification performance in discrimination with ordinal responses and merits further investigation.

Adult↗
PubMed1987

Is it possible to characterize recurrent urinary stone formers who benefit from thiazide prophylaxis? Application of discrimination analysis.

Twenty-three patients with recurrent urinary stones have been treated for 12-54 months with hydrochlorthiazide and 25 with placebo. Discrimination analysis was performed in order to distinguish patients with new stone formation (non-responders) from those without stone recurrence (responders) during the treatment. The discriminant function classified 16 out of 18 responders as such and 5 non-responders as such by using a combination of the three initial variables urinary pH, 24-h urine volume and serum phosphate. Eighteen other analysed variables and patient factors did not contribute to this discrimination. By using "leaving-one-out-technique", the probability for erroneously classifying a patient increased from 9 to 17%. Applying the discriminant function on the group receiving placebo, 92% of these patients were classified as responders to thiazide. It is concluded that discrimination analysis may give valuable information in characterizing patients who will benefit from a special therapy.

Clinical Trials as Topic↗
PubMed2003

Discrimination analysis of discontinuous breath sounds using higher-order crossings.

The paper evaluates the performance of an automatic discrimination analysis (DA) method used to discriminate efficiently the types of discontinuous breath sound (DBS), i.e. fine crackles (FCs), coarse crackles (CCs) and squawks (SQs); this may lead to more accurate characterisation of the pulmonary acoustical changes due to the related pathology. Based on higher-order crossings (HOCs), the proposed method, HOC-DA, captured the differences in the oscillatory patterns of FCs, CCs and SQs, which are only exposed when higher (> 1) crossings are employed. Prior to HOC-DA, wavelet-based de-noising of DBSs was employed to eliminate the effects of the vesicular sound (background noise) from their oscillatory pattern. The HOC-DA was applied to 157 discontinuous breath sounds corresponding to 16 cases included in three lung sound databases. Results showed that the HOC-DA efficiently separated FCs from CCs, SQs from CCs (both with an accuracy of 100%), and SQs from FCs (accuracy of 80%), with the optimum order ranging from 9 to 11. When compared with other classification tools, the HOC-DA resulted in high discrimination accuracy without involving high computational complexity. Owing to its simplicity, it could be implemented in a real-time context and be used in clinical medicine as a module of an integrated intelligent patient evaluation system.

Auscultation↗
PubMed1995

Evaluation of the response to chemotherapy in patients affected with small cell lung cancer using discriminant analysis: a preliminary report.

This report represents an attempt to combine the serum levels of more tumor markers together to evaluate the response to chemotherapy in 26 patients affected with small cell lung cancer (SCLC), by means of discriminant analysis. A pilot prospective study was performed on 26 subjects affected with inoperable SCLC (18 extensive diseases, and 8 limited diseases) and treated with chemotherapy (etoposide plus cisplatin regimen). Serum levels of a panel of tumor markers: Carcinoembryonic antigen (CEA), Tissue Polypeptide Antigen (TPA), Neuron Specific Enolase (NSE) and CYFRA -21.1 were determined before starting chemotherapy and at the restaging time (after 3 months). To optimize the classification power of these markers, a discriminant analysis was done, which permitted generating two classification functions, based on Tissue Polypeptide Antigen and Neuron Specific Enolase levels able to correctly classify 25 out of 26 subjects (8 progressions and 18 non progressions). The results obtained, furtherly confirm that tumor markers are useful to evaluate the chemotherapy response and indicate a possible approach to obtain the maximum usefulness of the serum marker levels.

Adult↗
PubMed2003

Discriminant analysis in allergic rhinitis and asthma: methacholine dose-response slope allows a good differentiation between mild asthma and rhinitis.

Asthma and rhinitis frequently coexist in allergic patients, but nasal symptoms may predominate, leading to asthma underdiagnosis and undertreatment. Discriminant analysis obtains the best differentiation between groups using one or one set of variables. Our aim was to identify the laboratory test [allergen exposure, total and specific serum IgE, lung function, blood eosinophils and, bronchial response and sensitivity to methacholine (Mth) and allergen] or combination of them that allowed the best differentiation between mild asthma and allergic rhinitis. A cross-sectional analysis was performed in 86 Dermatophogoides pteronyssinus allergic rhinitis patients, who were classified according to clinical data as rhinitis plus mild asthma (n = 62) or "pure" rhinitis (n = 24). Bronchial symptoms had been exhaustively evaluated during a 2-years pre-inclusion period. Patients underwent skin tests and bronchial challenge with Mth and allergen. The exposure to D. pteronyssinus allergen (Der pl) was quantified in dust samples. Dose-response curves with Mth [until the FEV1 fell by 40% or the maximal dose (200 mg/ml) was inhaled] were attained. We developed multiple models of discriminant analysis in order to evaluate the capacity of the above variables to differentiate groups. Asthma patients had higher total and specific IgE levels and a greater sensitivity (PD20 values) and response [dose-response slope (DRS)] to both Mth and allergen. The model entering these variables was the one that correctly classified more patients (79.2%). The discriminative power of the model that only included Mth-DRS values was similar to the above (78.8%). Bronchial response to Mth is quantitatively different in allergic rhinitis patients who display mild asthma symptoms when compared to those that only report rhinitis, suggesting a distinct bronchial intrinsic behavior. The utilization of complete dose-response curves with Mth allows a good separation between mild asthma and "pure" rhinitis patients and might be useful in the diagnosis of mild asthma. Whether the early detection and treatment of these patients prevents the development of symptomatic asthma needs further evaluation.

Adult↗
PubMed2002

Symbolic discriminant analysis of microarray data in autoimmune disease.

New laboratory technologies such as DNA microarrays have made it possible to measure the expression levels of thousands of genes simultaneously in a particular cell or tissue. The challenge for genetic epidemiologists will be to develop statistical and computational methods that are able to identify subsets of gene expression variables that classify and predict clinical endpoints. Linear discriminant analysis is a popular multivariate statistical approach for classification of observations into groups. This is because the theory is well described and the method is easy to implement and interpret. However, an important limitation is that linear discriminant functions need to be prespecified. To address this limitation and the limitation of linearity, we have developed symbolic discriminant analysis (SDA) for the automatic selection of gene expression variables and discriminant functions that can take any form. In the present study, we demonstrate that SDA is capable of identifying combinations of gene expression variables that are able to classify and predict autoimmune diseases.

Autoimmune Diseases↗
PubMed1998

The sensory profile: a discriminant analysis of children with and without disabilities.

OBJECTIVES: The purpose of this study was to determine which factors on the Sensory Profile, a measure of children's responses to commonly occurring sensory experiences, best discriminate among children with autism or pervasive developmental disorder (PDD), children with attention deficit hyperactivity disorder (ADHD), and children without disabilities. METHOD: Data for three groups of children 3 to 15 years of age were used: 38 children with autism or PDD, 61 with ADHD, and 1,075 without disabilities. The researchers conducted a discriminate analysis on the three groups, using group membership as the dependent variable and the nine factors of the Sensory Profile as independent variables. RESULTS: The analysis yielded two discriminant functions: one that differentiated children with disabilities from children without disabilities and another that differentiated the two groups of children with disabilities from each other. Nearly 90% of the cases were correctly classified with these two functions. CONCLUSION: The Sensory Profile is useful for discriminating certain groups of children with disabilities. Children with disabilities are accurately classified into disability categories with the factors described by previous authors. This suggests that patterns of behavior associated with certain developmental disorders are reflected in populations of children without disabilities. It may be the frequency or intensity of certain behaviors that differentiate the groups.

Adolescent↗
PubMed1976

[Use of discrimination analysis in perinatology].

From 50 normal births blood of mother and child was examined simultaneously at three different times, meant for determination of 13 biochemical parameters. Evaluation of the measured values was done by the multivariate method of discriminance analysis. Basing on the observed data problems of discriminance analysis are dealt with in an introductive way. The perinatal example is used to demonstrate how in the case of a complex problem connections may be better visible by this method, though detailed informations are lost.

Adenosine Triphosphate↗
PubMed1999

Use of SHIRPA and discriminant analysis to characterise marked differences in the behavioural phenotype of six inbred mouse strains.

Detailed characterisation of six inbred strains of mice commonly used in transgenic and knockout research was carried out using a battery of behavioural tests (SHIRPA) followed by discriminant analysis of the data. In the primary observation screen, DBA/2 mice were relatively irritable and vocalised during handling. C57BL/6 were hyperactive as measured by transfer arousal, arena activity and touch-escape tests. By contrast, C3H were markedly hypoactive, had significantly enhanced grip strength and were also significantly impaired on the visual placing task. In the elevated plus-maze, BALB/c mice showed the highest level of open arm entries and time spent in the open arms, indicating the lowest level of anxiety. There was a clear dissociation of strains on exploratory activity, as measured in the holeboard test and spontaneous locomotor activity (LMA). DBA/2 mice were hyperactive in LMA but demonstrated relatively low levels of holeboard exploration. None of the six strains learnt the water maze spatial learning task particularly well. C57BL/6 and 129/Sv demonstrated most ability and C3H showed no evidence of having acquired the task. The SHIRPA screening battery and discriminant analysis of the data have enabled us to determine the relevant contribution of a number of behavioural measurements to the marked differences in phenotype of mouse strains. These data confirm the importance of carrying out a comprehensive profile in order to accurately characterise the phenotype of gene-targeted and transgenic mice.

Animals↗
PubMed1987

A simple randomisation procedure for validating discriminant analysis: a methodological note.

Because the goal of discriminant analysis (DA) is to optimise classification, it designedly exaggerates between-group differences. This bias complicates validation of DA. Jack-knifing has been used for validation but is inappropriate when stepwise selection (SWDA) is employed. A simple randomisation test is presented which is shown to give correct decisions for SWDA. The general superiority of randomisation tests over orthodox significance tests is discussed. Current work on non-parametric methods of estimating the error rates of prediction rules is briefly reviewed.

Random Allocation↗
PubMed1978

Discriminant analysis in the differential diagnosis of hypercalcaemia.

Linear discriminant analysis, a multivariate statistical procedure, applied to serum calcium, phosphate, alkaline phosphatase, bicarbonate, chloride, creatinine and tubular reabsorption of phosphate, proved to be effective in distinguishing patients with Primary Hyperparathyroidism from other hypercalcaemic patients in eithy-four retrospective cases. The application of the model to thirty-four prospective cases enabled us to separate correctly, hyperparathyroid patients from non-parathyroid hypercalcaemic patients.

Diagnosis, Differential↗
PubMed1983

Discriminant analysis of acquired esotropia surgery. Predictor variables for short- and long-term outcomes.

In a retrospective study, a computer-based stepwise discriminant analysis was used to create a biostatistical model of the results of surgery in acquired esotropia. One hundred seventy-two patients who had bilateral medial rectus muscle recession as an initial operative procedure with at least 6 months postoperative follow-up were studied. The outcome groups for the discriminant analysis were based on the ocular deviation 6 weeks after the first surgery and at the patient's last visit, or the presence or absence of stereopsis at the last visit. With respect to the two predominant ocular deviation groups (Esotropia or Success) 6 weeks after surgery, 11 independent variables were analyzed; those determined to be prognostic of the outcome grouping were refractive error of the left eye and preoperative deviation, in that order. With respect to ocular deviation at last visit, 146 patients were followed for over 2 years and were last examined when over 5 years of age; of the 12 independent variables analyzed, postoperative deviation at 6 weeks, refractive error of the right eye, and age of onset were predictive. With respect to stereopsis, 126 patients had similar follow-up; of the 11 independent variables analyzed, only postoperative deviation at 6 weeks was prognostic. The results indicate that in patients with acquired esotropia the postoperative deviation is the most important prognostic factor for both the maintenance of ocular alignment and the status of stereopsis; refractive error and the age of onset of the esotropia influence the ocular alignment at the last visit.

Age Factors↗
PubMed1983

Discriminant analysis of congenital esotropia surgery. Predictor variables for short- and long-term outcomes.

In a retrospective study, a computer-based stepwise discriminant analysis was used to create a biostatistical model of the results of surgery in congenital esotropia. One hundred fifty-seven patients who had bilateral medial rectus muscle recession as an initial operative procedure with at least 6 months postoperative follow-up were studied. The outcome groups for the discriminant analysis were based on the ocular deviation 6 weeks after the first surgery and at the patient's last visit, or the presence or absence of stereopsis at the last visit. With respect to the two predominant ocular deviation groups (Esotropia or Success) 6 weeks after surgery, 11 independent variables were analyzed; those determined to be prognostic of the outcome grouping were preoperative deviation, millimeters of medial rectus muscle recession, and interval between the onset of strabismus and surgery. With respect to ocular deviation at last visit, 105 patients were followed for over 2 years and were last examined when over 5 years of age; of the 12 independent variables analyzed, only postoperative deviation at 6 weeks was predictive. With respect to stereopsis, 94 patients had similar follow-up; of the 12 independent variables analyzed, preoperative deviation and age at surgery were prognostic. The results indicate that a smaller preoperative deviation and earlier surgical intervention increase the probability of achieving some degree of stereopsis in patients with congenital esotropia.

Age Factors↗
PubMed2004

Evaluation of HIV-1 kinetic models using quantitative discrimination analysis.

MOTIVATION: Since the identification of human immunodeficiency virus (HIV) over twenty years ago, many mathematical models of HIV dynamics have been proposed. The purpose of this study was to evaluate intracellular and intercellular scale HIV models that best described the dynamics of viral and cell titers of a person, where parameters were determined using typically available patient data. In this case, 'best' was defined as the model most capable of describing experimental patient data and was determined by Bayesian-based model discrimination analysis and the ability to provide realistic results. RESULTS: Twenty models of HIV-1 viral dynamics were initially evaluated to determine whether parameters could be obtained from readily available clinical data from established HIV-1 patients with stable disease. Based on this analysis, three models were chosen for further examination and comparison. Parameters were estimated using experimental data from a cohort of 338 people monitored for up to 2484 days. The models were evaluated using a Bayesian technique to determine which model was most probable. The model ultimately selected as most probable was overwhelmingly favored relative to the remaining two models, and it accounted for uninfected cells, infected cells and cytotoxic T lymphocyte dynamics. The authors developed a fourth model for comparison purposes by combining the features of the original three models. Parameters were estimated for the new model and the statistical analysis was repeated for all four models. The model that was initially favored was selected again upon model discrimination analysis. CONTACT: srivasta@engr.uconn.edu.

Cohort Studies↗
PubMed1993

Discriminant analysis of clinical tests in histologic diagnosis of renal disease.

We have used discriminant analysis of the results of clinical examination to study whether or not it is possible to presume the histological findings of the kidney within the limits of the screening tests (urinalysis and blood tests) presently conducted at the outpatient clinic. A retrospective analysis was made of the data for 42 children who were found in school urine tests to have urinary abnormalities. Two discriminant functional equations were made and the overall rates of correct discrimination were > or = 90%. Proteinuria, IgA and complement titer were selected. These results were considered useful in determining the indication for renal biopsy.

Adolescent↗