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 343 records · Page 19Linked to original sources
PubMed1990

Discriminant analysis for assessing the value of amniotic fluid microvillar enzymes in the prenatal diagnosis of cystic fibrosis.

We have analysed the sensitivity, specificity, and reliability of biochemical diagnosis based on microvillar membrane enzyme assay and using discriminant analysis in amniotic fluid samples obtained from 54 pregnancies at high risk for cystic fibrosis and 125 normal pregnancies. Our results show that amniotic fluid trehalase, alkaline phosphatase, alkaline phosphatase isoenzymes and gamma-glutamyltransferase enzyme activities measured during 16-20 gestational weeks, in spite of their non-specificity for cystic fibrosis, have a very good predictive value for fetal cystic fibrosis or exclude the possibility of the disease. Overall enzyme activity analysis provided over 90 per cent reliability of the method.

Alkaline Phosphatase↗
PubMed2005

Discriminant analysis to study trace elements in biomonitoring: an application on neurodegenerative diseases.

Quantification of 26 elements was performed in blood of patients affected by neurodegenerative pathologies, i.e., Alzheimer's disease (AD), Parkinson's disease (PD) and multiple sclerosis (MS), and of a control group to study the potential role of blood elements as markers for the different neurodegenerations. A multivariate discriminant analysis (stepwise method) was applied to determine the best set of variables to discriminate among subjects with different health status. Preliminary results show three classification functions of seven elements, namely Ca, Co, Cu, Fe, Ni, Pb and Zr.

Adult↗
PubMed2006

Classification of adolescent psychotic disorders using linear discriminant analysis.

BACKGROUND: The differential diagnosis between schizophrenia and bipolar disorder during adolescence presents a major clinical problem. Can these two diagnoses be differentiated objectively early in the courses of illness? METHODS: We used linear discrimination analysis (LDA) to classify 28 adolescent subjects into one of three diagnostic categories (healthy, N=8; schizophrenia, N=10; bipolar, N=10) using subsets from a pool of 45 variables as potential predictors (22 neuropsychological test scores and 23 quantitative structural brain measurements). The predictor variables were adjusted for age, gender, race, and psychotropic medication. All possible subsets composed of k=2-12 variables, from the set of 45 variables available, were evaluated using the robust leaving-one-subject-out method. RESULTS: The highest correct classification (96%) of the 3 diagnostic categories was yielded by 9 sets of k=12 predictors, comprising both neuropsychological and brain structural measures. Although each one of these sets misclassified one case, each set correctly classified (100%) at least one group, such that a fully correct diagnosis could be reached by a tree-type decision procedure. CONCLUSIONS: We conclude that LDA with 12 predictor variables can provide correct and robust classification of subjects into the three diagnostic categories above. This robust classification relies upon both neuropsychological and brain structural information. Our results demonstrate that, despite overlapping clinical symptoms, schizophrenia and bipolar disorder can be differentiated early in the course of disease. This finding has two important implications. Firstly, schizophrenia and bipolar disorder are different illnesses. If schizophrenia and bipolar are dissimilar clinical manifestations of the same disease, we would not be able to use non-clinical information to classify ('diagnose') schizophrenia and bipolar disorder. Secondly, if this study's findings are replicated, brain structure (MRI) and brain function (neuropsychological) used together may be useful in the diagnosis of new patients.

Adolescent↗
PubMed1990

Unsupervised learning and discriminant analysis applied to identification of high risk postoperative cardiac patients.

A set of 200 patients in the 6 hours immediately following cardiac surgery was analysed within a multidimensional space of 13 commonly monitored physiological variables in order to identify high risk patterns. The application of an unsupervised learning (clustering) method to these data clearly showed the existence of two well-separated classes of low and high risk patients. A stepwise discriminant analysis was then applied to patients representative of the two classes in order to find those variables which, over time, possessed the greatest separation power. The latter always included the oxygen delivery (DO2), an index related to the oxygen content in the blood (Pv(-)O2 or avO2D) and a myocardial contractility index (VF or LAP).

Algorithms↗
PubMed1991

Analytical morphies on mid-sagittal craniograms glabella-opisthocranion of Homo erectus and Homo sapiens neanderthalensis: Fourier parameters and multivariate discriminant analysis.

The analytical description of complicated morphologies offers the possibility to define patterns of parameters characterizing the investigated groups. These patterns must be considered as morphies useful in performing classification and comparison. Fourier parameters are extremely effective in describing and comparing complex irregular forms and since they are statistically independent we can use them in performing multivariate discriminant analysis. Two groups of mid-sagittal craniograms glabella-opisthocranion of asiatic samples of Homo erectus and of Homo sapiens neanderthalensis were described by means of Fourier harmonic analysis. The discriminatory power of all the obtained parameters (coefficients, amplitudes and phases) was tested. A discriminant function (error % = 0) was obtained using as parameters the first 4 sine/cosine coefficients, the 5th sine, the 6th and the 7th cosine components (11 parameters in all). When the information contained in the coefficient values is being subdivided into the two components of amplitude and phase, the amplitude component is not able to discriminate between the two groups (error % = 25), while the phase values of the first 7 harmonics are able to discriminate them (error % = 0 and distance between centroids = 47).

Animals↗
PubMed2005

Identification of candidate markers associated with agronomic traits in rice using discriminant analysis.

Plant genetic mapping strategies routinely utilize marker genotype frequencies obtained from progeny of controlled crosses to declare presence of a quantitative trait locus (QTL) on previously constructed linkage maps. We have evaluated the potential of discriminant analysis (DA), a multivariate statistical procedure, to detect candidate markers associated with agronomic traits among inbred lines of rice (Oryza sativa L.). A total of 218 lines originating from the US and Asia were planted in field plots near Alvin, Texas, in 1996 and 1997. Agronomic data were collected for 12 economically important traits, and DNA profiles of each inbred line were produced using 60 SSR and 114 RFLP markers. Model-based methods revealed population structure among the lines. Marker alleles associated with all traits were identified by DA at high levels of correct percent classification within subpopulations and across all lines. Associated marker alleles pointed to the same and different regions on the rice genetic map when compared to previous QTL mapping experiments. Results from this study suggest that candidate markers associated with agronomic traits can be readily detected among inbred lines of rice using DA combined with other methods described in this report.

Asia↗
PubMed1986

Evidence that the amino acid composition of the particle proteins of plant viruses is characteristic of the virus group. II. Discriminant analysis according to structural biological and classification properties of plant viruses.

The amino acid composition (AAC) of the coat proteins (CPs) of 126 plant viruses or strains were analyzed by stepwise discriminant analysis. The criteria chosen for discrimination were: the structure of virus particles (3 clusters); the mode of of transmission of the viruses (6 clusters); and the grouping of viruses according to the classification of the International Committee on Taxonomy of Viruses (23 groups). Statistically significant correlations were obtained with different groups of discriminant amino acids. The results confirm that the AAC of the CPs contains all the information needed for a quantitative classification of plant viruses. These results and possible explanations of these clustering patterns are discussed.

Amino Acids↗
PubMed1976

A discriminant analysis for qualitative data with interactions.

Two linkable computer programs have been developed for a discriminant analysis with qualitative variables, which permit taking into account 1st order interactions. The first program is used to estimate the parameters required in the second program. The second program allows a classification of new cases as well as an unbaised estimation of error rates.

Computers↗
PubMed2000

Computerized classification of corpus cavernosum electromyogram signals by the use of discriminant analysis and artificial neural networks to support diagnosis of erectile dysfunction.

Corpus cavernosum electromyogram (CC-EMG) provides diagnostic information on cavernous autonomic innervation and a measure of the degree to which the cavernous smooth muscle cells are intact. The complicated CC-EMG is evaluated and used in the diagnosis of patients suffering from erectile dysfunction. The evaluation procedure has been simplified by applying digital signal processing techniques. Since mathematically-based interpretations require quantitative data, spectral analysis was performed. The derived biosignals were analyzed by fast Fourier transform (FFT). Besides various other spectral parameters, specific frequency bands were determined in the power spectrum using factor analysis. The parameters were used for the computerized classification of normal and pathological CC-EMG data and the classification was performed using two independent methods: discriminant analysis (DA) and artificial neural networks (ANN). A medical expert analyzed a total of 200 CC-EMG recordings from patients with and without erectile dysfunction and separated these into normal (136) and pathological (64) cases. Although each independent method had already resulted in a relatively high number of correct classifications, the classification success rate could be slightly improved by using a combination of both classification methods. A total of 72.79% and 77.94% were successfully classified using DA and ANN, respectively. The combination of both methods increased the classification success to 80.15%. The results of this study enabled impartial evaluation of the CC-EMG signals for clinical diagnostic purposes of erectile dysfunction. This method provided an objective and easy way to analyze the CC-EMG. Furthermore, this results in patient diagnosis becoming an easier task for less experienced doctors, since little knowledge of the raw signal is needed.

Algorithms↗
PubMed1998

Prediction of common bile duct stones prior to cholecystectomy: a prospective validation of a discriminant analysis function.

BACKGROUND: Selection routines for preoperative endoscopic retrograde cholangiopancreatography (ERCP) in patients with symptomatic gallstone disease should give a low frequency of both false-negative ERCP results and residual common bile duct stones (CBDS). OBJECTIVE: To validate a discriminant function (DF) based on retrospectively collected data, for characterization of patients with symptomatic gallstone disease as regards presence of CBDS, and to compare clinical, ultrasonographic, and DF characterization. DESIGN: Prospective registration of CBDS criteria in consecutive patients with symptomatic gallstone disease. SETTING: A department of surgical gastroenterology in a Norwegian central hospital. PATIENTS: One hundred ninety-two patients with gallbladder stones. INTERVENTION: Laparoscopic cholecystectomy or ERCP with or without endoscopic sphincterotomy. MAIN OUTCOME MEASUREMENTS: Sensitivity and specificity of the clinical, ultrasonographic, and DF characterizations, and test of the validity of the DF. RESULTS: Thirty-two patients had CBDS. The clinical criteria of CBDS were present in 152 patients (79.2%): 21.1% of these patients had CBDS and there were no false-negative results (sensitivity, 100%; specificity, 25%). The risk of CBDS in patients with normal bile ducts at ultrasonographic examination was 8 of 124, and in patients with dilated ducts or suspected CBDS, 17 of 47 (sensitivity, 68%; specificity, 80%). The DF was positive in 50 patients (26%): 60% of these had CBDS, and there were 2 false-negative results (sensitivity, 94%; specificity, 88%). A discriminant analysis of the prospectively registered data selected the same set of CBDS criteria, and a new DF did not alter the characterization of any patient. CONCLUSIONS: Clinical characterization had a higher sensitivity for CBDS detection than ultrasonography alone, but a lower specificity. The DF analysis was both more sensitive and specific than ultrasonography, and seemed efficient in selecting symptomatic gallstone patients for ERCP. It was reproducible and simple to use.

Adult↗
PubMed1990

[Discriminant analysis of quantification theory on prognostic factors of chemotherapeutic effects on advanced testicular cancer. East Japan Testicular Tumor Study Group].

Prognostic factors of chemotherapy against advanced testicular cancer were analysed in 33 cases studied by East Japan Testicular Tumor Study Group. In this study a discriminant analysis of quantification theory (a multivariate analysis) was adapted, taking 7 factors as comparative variables. The significant factors for complete tumor response were clinical stage, histology, and tumor markers (HCG-beta, AFP). Prognostic score was calculated in each case by quantification theory, which correctly discriminated the group with CR from that without CR, at a probability of 90.1%. The results of our study indicate that the outcome of chemotherapy on advanced testicular cancer may be predicted with probability, by patients' status and adopted treatment. It may enable one to make an adequate treatment schedule for each patient.

Antineoplastic Combined Chemotherapy Protocols↗
PubMed1983

[Reaction time and eye movements in the recognition task of hand-written Katakana-letters: an experimental verification of the discriminant analysis of letter recognition by Hayashi's Quantification].

Hayashi's Quantification, model II, is a multivariate discriminant analysis for qualitative data. This method was applied to the quantitative indices about confusability of recognition of handwritten Japanese Katakana-letters. The experimental results of reaction time and eye movements in the recognition task corresponded well with indices computed by this statistical procedure. (a) The labels, given by the subjects to the letters, were in line with the prediction by the discriminant, (b) the reaction time and the number of fixations were bigger for highly confusable letters, and (c) those features, which were important according to the discriminant, were fixated more frequently. Thus, Hayashi's quantification procedure is valid for psychological experiments.

Adolescent↗
PubMed2004

Multiple-discriminant analysis for light-scattering spectroscopy and imaging of two-layered tissue phantoms.

We propose a new method for enhancing the sensitivity of the reflectance spectrum to the scattering feature of the superficial tissue layer. This method is based on multiple-discriminant analysis in the eigensubspace of the spectrum. Considering the application of scattering imaging, we evaluated this method by performing multispectral imaging of two-layered tissue phantoms. A color map converted from the spectral reflectance corresponds well to variations in the size of the scattering in the first layer.

Discriminant Analysis↗
PubMed1996

[Detection of treatment of chicken breast with ionized rays and gradation of radiation dosage with the help of headspace gas chromatography and discriminant analysis evaluation].

Chicken breast was irradiated with doses of 3, 5, and 7 kGy. Headspace gas chromatographical analysis demonstrated the tendency that the amounts of volatile compounds (mainly pentanal, hexanal and heptanal) are higher in irradiated samples in comparison with non irradiated. Statistical evaluation of the gas chromatograms by discriminant analysis enabled the detection of irradiation. Unknown samples could be classified in the groups "un-irradiated" or "irradiated" in most cases.

Aldehydes↗
PubMed1994

Reduction of false positives in computerized detection of lung nodules in chest radiographs using artificial neural networks, discriminant analysis, and a rule-based scheme.

A computer-aided diagnosis (CAD) scheme is being developed to identify image regions considered suspicious for lung nodules in chest radiographs to assist radiologists in making correct diagnoses. Automated classifiers--an artificial neural network, discriminant analysis, and a rule-based scheme--are used to reduce the number of false-positive detections of the CAD scheme. The CAD scheme first detects nodule candidates from chest radiographs based on a difference image technique. Nine image features characterizing nodules are extracted automatically for each of the nodule candidates. The extracted image features are then used as input data to the classifiers for distinguishing actual nodules from the false-positive detections. The performances of the classifiers are evaluated by receiver-operating characteristic analysis. On the basis of the database of 30 normal and 30 abnormal chest images, the neural network achieves an AZ value (area under the receiver-operating-characteristic curve) of 0.79 in detecting lung nodules, as tested by the round-robin method. The neural network, after being trained with a training database, is able to eliminate more than 83% of the false-positive detections reported by the CAD scheme. Moreover, the combination of the trained neural network and a rule-based scheme eliminates 96% of the false-positive detections of the CAD scheme.

Diagnosis, Computer-Assisted↗
PubMed2001

MRI characteristics in focal hepatic disease before and after administration of MnDPDP: discriminant analysis as a diagnostic tool.

The aim of this study was to determine if different types of focal hepatic lesions can be differentiated by specific quantitative and qualitative imaging characteristics pre- and post-Mangafodipir trisodium (MnDPDP) administration using a computerized multivariable, discriminant analysis (DA). In a multicenter trial, 151 patients with focal liver disease were studied at 1.5 and 1.0 T using gradient-recalled echo T1 and fast spin-echo T2-weighted images pre and post MnDPDP (0.005 mmol/kg b.w.) i.v. administration. Analysis could be performed in 141 of 151 of the patients. The variables used in both single variable analysis and DA included contrast-to-noise ratios pre and post MnDPDP, presence of rim enhancement, margin, and heterogeneity of a lesion pre and post MnDPDP. The classification of diagnoses using DA was compared with a standard of reference (HCC in 23%, metastases in 25%, cyst in 13%, FNH in 10%, hemangioma in 11%, and other or no lesion in 18% of the patients; histology in 49%, long-term follow-up in 51% of the cases). In the differentiation of the various hepatic lesions, CNR together with the presence of heterogeneity or rim enhancement as variables for DA gave the highest sensitivity, specificity, and accuracy which ranged between 65 and 93, 44 and 83, and 65 and 86%, respectively. The DA models based on post-MnDPDP variables showed better classification results than the models based on pre-MnDPDP variables. An improvement of accuracy was observed when differentiating HCC from FNH lesion groups (48.9-67.4%; p < or = 0.05), and when differentiating HCC from metastasis lesion groups (68.3-84.1%; p < or = 0.01). In all regards there was no difference for T2-weighted images pre and post MnDPDP. By combining quantitative and qualitative variables, DA proved to be a useful tool in lesion discrimination. Due to considerable heterogeneity within some of the lesion type groups, the definite diagnostic impact of MnDPDP cannot be completely established yet, and further investigation is still necessary.

Adolescent↗
PubMed1990

Discriminant analysis among septicemic melioidosis and other bacterial septicemia.

The clinical manifestations of septicemic melioidosis and other bacterial septicemia were studied at Srinagarind Hospital, Khon Kaen University. Forty-three cases of septicemic melioidosis and 68 non-melioidosis septicemia cases were analysed. By univariate analysis, the following clinical features are associated with septicemic melioidosis: male patients; age below 45 years; underlying diabetes mellitus or renal failure; pulmonary infection, impending respiratory failure and multiorgan involvement, while abdominal pain and urinary tract infection were more common in non-melioidosis septicemia. By using discriminant analysis and logistic regression, 3 features (diabetes mellitus, multiorgan involvement, and no abdominal pain or pulmonary infection) could discriminate the two groups with the accuracy of more than 85 per cent.

Adult↗
PubMed1985

Prediction of outcome in acute renal failure by discriminant analysis of clinical variables.

To define factors of prognostic importance in patients with acute renal failure, we studied 23 clinical variables (including preexisting conditions, the acute clinical setting, and complications) by univariate and multivariate analysis in 148 patients. Ten variables contributed to discrimination in the overall analysis. Using a function derived by stepwise discriminant analysis, death could be predicted with a positive predictive value of 100% and a sensitivity of 58%. The performance of this discriminant score was validated in a subsequent group of 113 patients with a positive predictive value of 100% and a sensitivity of 26%. Thus, a fatal outcome of acute renal failure can be accurately predicted in a considerable proportion of patients by a weighted evaluation of clinical variables. The discriminant score may be useful in comparing the severity of illness among series of patients with acute renal failure.

Acute Kidney Injury↗