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 307 records · Page 17Linked to original sources
PubMed1988

Discriminant analysis of microcalorimetric data of bacterial growth.

In this work a bacterial classification method based on the discriminant analysis of the microcalorimetric data provided by the growth power-time (p-t) curves is developed. This method is applied to classify several species of Enterobacteria of different origins, and the results are compared with those obtained by conventional techniques. The proposed analysis allows us to classify bacteria into species and discriminate among strains of the same species. The classification is carried out using one run of each isolate after standardization of inocula and growth conditions. The discrimination power of available microcalorimetric data is also discussed, and the most discriminant set of data is proposed as the input variables of the analysis. Finally, the advantages of microcalorimetry as a taxonomical technique are discussed.

Calorimetry↗
PubMed1996

An optimization model for constrained discriminant analysis and numerical experiments with iris, thyroid, and heart disease datasets.

A nonlinear 0/1 mixed integer programming model is presented for a constrained discriminant analysis problem. The model enables controlling misclassification probabilities by placing restrictions on the numbers of misclassifications allowed among the training entities and incorporating a "reserved-judgment" region to which entities whose classifications are difficult to determine may be allocated. A linearization of the model is given, and preliminary numerical results for two medical and one non medical domain are presented.

Databases, Factual↗
PubMed1998

Spectrophotometric imaging of cutaneous pigmented lesions: discriminant analysis, optical properties and histological characteristics.

Reflectance imaging spectroscopy at 17 selected wavelengths in the range 420-1040 nm has been applied as a method to discriminate melanoma from other pigmented cutaneous lesions. Reflectance images are acquired for 18 primary melanomas and 33 benign naevi in 44 patients. From each spectral image, four parameters related to lesion reflectance (mean value of reflectance, variegation, area and roundness of lesion) are derived at the corresponding wavelength. A discriminant function between the two groups of lesions is determined by using a stepwise discriminant analysis, resulting in a test with a sensitivity of 89% and a specificity of 88%. Since analyses are carried out on the same data set used to obtain the discriminant function, our results should be interpreted with caution. Moreover, in an attempt to assign a physical and/or physiological meaning to the lesion image descriptors, some histological features (i.e., lesion thickness, degree and uniformity of pigmentation) have also been analysed, and their correlations with the image descriptors investigated. Neither degree nor uniformity of pigmentation can fully explain the variations observed in the lesion image descriptors. It is hypothesized that the presence of pathologically related biological components such as lymphocytes and highly aggregated cells may play an important role. The actual performance of the spectrophotometric imaging system should be proven in an additional, unselected number of cases before being used as a diagnostic adjunct for physicians in the clinical detection of melanoma.

Diagnosis, Differential↗
PubMed1984

Applying descriptive discriminant analysis as a visual aid for physicians interpreting biochemical test results.

Descriptive discriminant analysis displays for classes of common hepatic and biliary disorders and other mimicking conditions using 11 biochemical measurements, were demonstrated to physicians as an aid to interpretation. Displayed on a video, biochemical distinctions among disorders were made apparent to viewers. Physician users could easily see where their patient's results fell in relation to other results from patients with relevant diseases. Users had difficulty specifying which diseases they wanted included in displays. This technique would be useful for verifying experts' test result interpretations, when the differential diagnosis can be explicitly stated.

Biliary Tract Diseases↗
PubMedDate not supplied

Nonlinear discriminant analysis and prognostic factor classification in node-negative primary breast cancer using probabilistic neural networks.

BACKGROUND: We used non-linear kernel discriminant analysis (KDA) to predict the outcome of 134 axillary node-negative primary breast cancer patients not treated with adjuvant therapy in a non censored database. MATERIAL: Posterior probabilities of relapse at 5 years were estimated using probabilistic neural networks (PNN) and a cross-validation (leave-one-out) technique to avoid overfitting the data. A stepwise method was used to construct the models to define the best combination of risk factors among eleven prognostic factors: age, menopausal status, Scarff-Bloom-Richardson grade, clinical tumor size, pathological tumor size, estrogen and progesterone receptor status, urokinase-type plasminogen activator, p53 protein level, c-erbB-2 protein and epidermal growth factor receptor. The different variables were tested individually and in combination to determine their prognostic power using a ROC indicator, which measures the separation between the probability distributions of the output neuron activations under the null hypothesis (no recurrence at 5 years) and under the alternative hypothesis (recurrence at 5 years). RESULTS: The best predictive one-dimensional model was obtained with uPA (ROC indicator = 0.75). A two-factor model including uPA and clinical tumor size (T) gave the best discrimination between recurrence and non recurrence at 5 years (ROC indicator = 0.84). Additional variables did not improve the accuracy of the prediction. The uPA-T model generated a map useful in predicting the posterior probability of cancer recurrence in a given patient. This representation allows the entire database to be easily visualized and each patient can be compared with the entire database. CONCLUSION: This is a powerful approach to analyze the impact of prognostic factors and it could find clinical applications in breast cancer.

Age Factors↗
PubMed2006

Identification of primary tumors of brain metastases by infrared spectroscopic imaging and linear discriminant analysis.

This study applies infrared (IR) spectroscopy to distinguish normal brain tissue from brain metastases and to determine the primary tumor of four frequent brain metastases such as lung cancer, colorectal cancer, breast cancer, and renal cell carcinoma. Standard methods sometimes fail to identify the origin of brain metastases. As metastatic cells contain the molecular information of the primary tissue cells and IR spectroscopy probes the molecular fingerprint of cells, IR spectroscopy based methods constitute a new approach to determine the primary tumor of a brain metastasis. IR spectroscopic images were recorded by a FTIR spectrometer equipped with a macro sample chamber and coupled to a focal plane array detector. Unsupervised cluster analysis of IR images revealed variances within each sample and between samples of the same tissue type. Cluster averaged IR spectra of tissue classes with known diagnoses were selected to develop a metric with eight variables. These data trained a supervised classification model based on linear discriminant analysis that was used to identify the origin of 20 cryosections including one brain metastasis with an unknown primary tumor.

Brain Neoplasms↗
PubMed1996

Correspondence discriminant analysis: a multivariate method for comparing classes of protein and nucleic acid sequences.

This report describes two applications of a multivariate method for studying classes of nucleotide or protein sequences: correspondence discriminant analysis (CDA). The first example is the discrimination between Escherichia coli proteins according to their subcellular location (membrane, cytoplasm and periplasm). The high resolution of the method made it possible to predict the subcellular location of E.coli proteins for whom this information is not known. The second example is discrimination between the coding sequences of leading and lagging strands in four bacteria: Mycoplasma genitalium, Haemophilus influenzae, E.coli and Bacillus subtilis. The programs used for computing the analysis are integrated in a publicly available package that runs on MacOS 7.x or Windows 95 operating systems (http:/(/)biomserv.univ-lyonl.fr/ADE-4.html). These programs are also accessible through our World Wide Web server (http:/(/)biomserv.univ-lyonl.fr/Net Mul.html).

Amino Acid Sequence↗
PubMed2004

Linear discriminant analysis of dermoscopic parameters for the differentiation of early melanomas from Clark naevi.

As a first step to develop a screening system for pigmented skin lesions, we performed digital discriminant analyses between early melanomas and Clark naevi. A total of 59 cases of melanoma, including 23 melanoma in situ and 36 thin invasive melanomas (Breslow thickness < or =0.75 mm), and 188 clinically equivocal, histopathologically diagnosed Clark naevi were used in our study. After calculating 62 mathematical variables related to the colour, texture, asymmetry and circularity based on the dermoscopic findings of the pigmented skin lesions, we performed multivariate stepwise discriminant analysis using these variables to differentiate melanomas from naevi. The sensitivities and specificities of our model were 94.4 and 98.4%, respectively, for discriminating between melanomas (Breslow thickness < or =0.75 mm) and Clark naevi, and 73.9 and 85.6%, respectively, for discriminating between melanoma in situ and Clark naevi. Our algorithm accurately discriminated invasive melanomas from Clark naevi, but not melanomas in situ from Clark naevi.

Dermatology↗
PubMed1994

Evaluation of obstructed kidneys by discriminant analysis of 99mTc-MAG3 renograms.

This study sought to develop a method of improving the differential diagnostic between healthy and obstructed kidneys using only parameters derived from the 99mTc-MAG3 renogram. The analysis included data from 46 healthy and 36 obstructed kidney units. The parameters calculated were: mean transit time (MTT), time at 20% of the initial height of the renal retention function (T20) and time to peak of the renogram (TP). A discriminant analysis was carried out to obtain a discriminant function in order to differentiate between the two groups. The best results were obtained using the function: (2.5629 InT20) + (2.1280 In TP) -27.1224 which correctly classified 97.56% of the cases, giving a sensitivity of 94.44% and a specificity of 99.99%.

Adult↗
PubMed2006

Identification of new antimalarial drugs by linear discriminant analysis and topological virtual screening.

OBJECTIVES: A quantitative structure-activity relationship study using a database of 395 compounds previously tested against chloroquine-susceptible strains of the blood stages of Plasmodium falciparum to predict new in vitro antimalarial drugs has been developed. METHODS: Topological indices were used as structural descriptors and were related to antimalarial activity by using linear discriminant analysis (LDA) and multilinear regression (MLR). Two discriminant equations were obtained (FD1 and FD2), which allowed us to carry out successful classification of 90% and 80% of compounds, respectively. The IC50 values of the compounds were introduced to get an MLR equation model suitable to predict their in vitro activities. RESULTS: Using this model, a set of 27 drugs against a chloroquine-susceptible clone (3D7) of P. falciparum have been selected and evaluated in vitro. Among these drugs are monensin, nigericin, vincristine, vindesine, ethylhydrocupreine and salinomycin with in vitro IC50s at nanomolar concentrations (0.3, 0.4, 2, 6, 26 and 188 nM, respectively). Other compounds such as hycanthone, amsacrine, aphidicolin, bepridil, amiodarone, ranolazine and triclocarban showed in vitro IC50 values below 5 microM in the mathematical model. CONCLUSIONS: These results demonstrate the usefulness of the approach for the selection and design of new lead drugs active against P. falciparum.

Animals↗
PubMed1981

Discriminant analysis to predict graduation--nongraduation in a master's degree program in nursing.

Discriminant analysis was used to predict graduation and two categories of nongraduation from readily available admissions data at the University of Kansas nursing master's degree program. The traditional admissions indices, baccalaureate grade point average (GPA) and Graduate Record Examination (GRE)-verbal and -quantitative scores, were used as predictors. Criterion categories were composed of 102 graduates, 103 individuals who dropped out of the program, and 65 individuals who were not accepted. The first discriminant function was, chi 2 (6) = 87.567, p less than .0001, and extracted 98% of the variance of the discriminant space. Follow-up procedures using one-way ANOVA's and Scheffé multiple comparisons indicated that the baccalaureate GPA and GRE-verbal and -quantitative scores independently differentiated the graduate and dropout groups from the not-accepted group at a statistically significant level (p less than .05). Practical significance of the independent contribution of these variables to group differentiation, as measured by omega 2 was 22% for the baccalaureate GPA, 13% for the GRE-verbal scores, and 10% for the GRE-quantitative scores. Implications for future research are discussed.

Analysis of Variance↗
PubMed2002

Discriminant analysis of anthropometric and biomotor variables among elite adolescent female athletes in four sports.

The aim of this study was to identify anthropometric and biomotor variables that discriminated among groups of elite adolescent female athletes aged 14.3 +/- 1.3 years (mean +/- s) from four different sports (tennis, n = 15; swimming, n = 23; figure skating, n = 46; volleyball, n = 16). The anthropometric variables included body mass, height, bi-epicondylar breadth of the distal extremity of the humerus and femur, maximal girth of the calf and biceps and the sum of five adipose skinfolds. The biomotor variables were maximal aerobic power, muscular endurance and flexibility of the trunk. Discriminant analysis revealed three significant functions (P < 0. 05). The first discriminant function primarily represented differences between figure skaters and all other groups of athletes. The other two underlined anthropometric and biomotor differences between swimmers and volleyball players and between tennis players and swimmers, respectively. After validation, the analysis showed that 88% of the athletes were correctly classified in their respective sports. Our model confirms that elite adolescent female athletes show physical and biomotor differences that clearly distinguish them according to their particular sport.

Adolescent↗
PubMed1987

Linear discriminant analysis of regional ejection fractions in the diagnosis of coronary artery disease.

We studied the application of linear discriminant analysis to the computer assisted interpretation of rest and exercise gated blood pool studies. Data were obtained in 45 patients in whom the presence or absence of coronary artery disease was determined by coronary angiography. Automated analysis of regional ejection fractions using a linear discriminant function (LDF) was compared to the fully automated calculation of global ejection fraction and to the subjective evaluation of wall motion. A LDF constructed from the data for the first 31 consecutive patients correctly classified 25/31 (81%). The change in global ejection fraction correctly classified 24/31 (77%) and wall motion analysis 25/31 (81%). In a distinct group of 14 patients the same LDF correctly classified 12/14 (86%), global ejection fraction 9/14 (64%) and wall motion analysis 10/14 (71%).

Coronary Disease↗
PubMed1993

Selective cervical cytology screening: discriminant analysis approach.

Cervical cancer is one of the leading malignancies seen in Indian women. It has been well established that organized cervical cytology screening program is the mainstay for control of cervical cancer. It is not possible to carry out cervical cytology screening for masses in India due to paucity of human and financial resources. Hence there is a need for development of an alternate strategy to concentrate on women with high risk. In the present communication attempt was made to define a high risk group based on sociodemographic factors, viz. age, parity, education and clinical features. A total of 67,000 women were screened of which in 250 malignancy was detected. The rate of malignancy was observed to be high in women above 40 years (10.5/1000) with more than two children (6.1/1000) and in illiterate group (4.9/1000) as compared to women below 40 years, more than 3 children and illiterate group. Similarly, the rates were higher in women with clinical diagnosis of cervical erosion which bled on touch, unhealthy cervix and suspicious looking cervix, malignancy rates were 17.1, 24.7, 263.2 (per 1000), respectively. An attempt was made to study the combined effect of all the six factors (sociodemographic and clinical) by employing the technique of linear discriminant analysis to find out the discrimination power between the normal and malignant women. Discriminant score thus obtained would help to classify the case for subjecting to cervical cytology. It was observed that the model containing sociodemographic and clinical variables was able to classify 69% of malignant cases correctly. When the clinical variables were dropped from the model, the sensitivity dropped to 65%. The above exercise indicated that based on the discriminant score even in the absence of facilities for clinical examination of women, it may be possible to identify women of high risk group for subjecting them to cervical cytology screening.

Adult↗
PubMed2006

Application of linear discriminant analysis in the virtual screening of antichagasic drugs through trypanothione reductase inhibition.

We have performed virtual screening to identify new lead trypanothione reductase inhibitor (TRI) compounds, enzyme present in Tripanozoma cruzi, the agent responsible of Chagas disease. From a training set of 58 compounds, linear discriminant analysis (LDA) was performed using 2D and 3D descriptors as discriminating variables in order to find out which function of descriptors characterizes the active TRI. The values of the statistical parameters F--Snedecor and Wilk's lambda for the discriminant function (DF) showed good statistical significance, as long as the rate of success in the prediction for both the training and the test set: 91.38% and 88.63%, in that order. Internal validation through the Leave--Group--Out methodology was performed with good results, assuring the stability of the DF. Afterwards, the DF was applied in virtual screening of 422,367 compounds. The optimum range of values of octanol--water partition coefficient for a compound to develop trypanothione reductase inhibition was applied as a second filtering criteria. 739 structurally heterogeneous drugs of the virtual library were selected as promissory TRI.

Animals↗
PubMed1994

[Cancer of the larynx and discriminant analysis].

In order to get the prognosis on the 5 years survival, free of disease, in a sample of 428 laryngectomies, for cancer of the larynx, the AA. have realized a discriminant analysis working out with several known factors. Only from 109 components of the group complete information could be available about the variables studied and with these a linear discriminant function was obtained. The rate of correct prediction was 78.8 percent for cancer recurrence and 77.6 percent for survival without recurrence after 5 years term. The discriminant variables were: positive lymph nodes, tumour staging using TNM classification, cord mobility and alcohol consumption.

Discriminant Analysis↗
PubMed1987

Prediction of cervical neoplasia diagnosis groups. Discriminant analysis on digitized cell images.

The purpose of this study was to develop discriminant analysis models for predicting cervical dysplasia/neoplasia case diagnoses using cytometric features derived from the digital image analysis of cell monolayers. The data base consisted of 925 cells from 27 cases diagnosed either as moderate dysplasia (n = 10), severe dysplasia (n = 5), carcinoma in situ (n = 8) or invasive carcinoma (n = 4) on both tissue biopsy and monolayer preparations. Cell features examined were cell diameter, nuclear diameter, nuclear mean optical density (OD), nuclear integrated OD (IOD), nuclear OD standard deviation, normalized IOD, nuclear texture and nuclear-cytoplasmic ratio. Features derived from cells visually classified as moderate dysplasia correctly predicted the case diagnosis of moderate dysplasia versus more severe disease for 85% of the cells. Prediction models using summary measures (mean and variance) derived from all visually classified abnormal cells within each case correctly separated all cases into their respective diagnostic categories. These findings suggest that dysplastic cells in a cytologic sample have features that collectively reflect the tissue diagnosis, regardless of the visual differences among the cells. Such information has potential use for diagnosis and possibly for prognosis.

Carcinoma in Situ↗