Usefulness of serum nucleotide pyrophosphatase and phosphodiesterase I activities in classifying liver disease.

1981 ◽  
Vol 27 (8) ◽  
pp. 1392-1396 ◽  
Author(s):  
H F Haugen ◽  
S Ritland ◽  
J P Blomhoff ◽  
H E Solberg ◽  
S Skrede
Keyword(s):  
Alkaline Phosphatase ◽  
Liver Disease ◽  
Discriminant Analysis ◽  
Clinical Routine ◽  
Extrahepatic Cholestasis ◽  
Nucleotide Pyrophosphatase ◽  
Different Types ◽  
Test Sets ◽  
Liver Tests

Abstract Nucleotide pyrophosphatase and phosphodiesterase I activities were determined in sera from 126 patients with different types of liver disease and in two additional groups of patients with intra- and extrahepatic cholestasis, respectively. Both activities probably represent the same enzyme, and were positively correlated with alkaline phosphatase, lipoprotein X, and several other tests reflecting cholestasis. Also, we found by discriminant analysis that tests for cholestasis frequently replaced the results of both enzymes. In some groups of liver disease, nucleotide pyrophosphatase and phosphodiesterase I were correlated with the concentrations of prealbumin and albumin. The sensitivity of phosphodiesterase I (and nucleotide phosphatase) is rather low when compared with alkaline phosphatase, and we do not recommend it for use in the clinical routine. Nevertheless, it appears to be of potential value for studies on classification of liver diseases, adding information to a panel of 20 commonly used "liver tests" by appearing in some of the best four test-sets for distinguishing between groups of liver disease by discriminant analysis.

Motor Oil Classification Using Color Histograms and Pattern Recognition Techniques

2018 ◽  
Vol 101 (6) ◽  
pp. 1967-1976 ◽  
Author(s):  
Shiva Ahmadi ◽  
Ahmad Mani-Varnosfaderani ◽  
Biuck Habibi
Keyword(s):  
Pattern Recognition ◽  
Discriminant Analysis ◽  
Classification Problem ◽  
Classification Model ◽  
Motor Oil ◽  
Pattern Recognition Techniques ◽  
Color Histograms ◽  
Different Types ◽  
Motor Oils

Abstract Motor oil classification is important for quality control and the identification of oil adulteration. In this work, we propose a simple, rapid, inexpensive and nondestructive approach based on image analysis and pattern recognition techniques for the classification of nine different types of motor oils according to their corresponding color histograms. For this, we applied color histogram in different color spaces such as red green blue (RGB), grayscale, and hue saturation intensity (HSI) in order to extract features that can help with the classification procedure. These color histograms and their combinations were used as input for model development and then were statistically evaluated by using linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM) techniques. Here, two common solutions for solving a multiclass classification problem were applied: (1) transformation to binary classification problem using a one-against-all (OAA) approach and (2) extension from binary classifiers to a single globally optimized multilabel classification model. In the OAA strategy, LDA, QDA, and SVM reached up to 97% in terms of accuracy, sensitivity, and specificity for both the training and test sets. In extension from binary case, despite good performances by the SVM classification model, QDA and LDA provided better results up to 92% for RGB-grayscale-HSI color histograms and up to 93% for the HSI color map, respectively. In order to reduce the numbers of independent variables for modeling, a principle component analysis algorithm was used. Our results suggest that the proposed method is promising for the identification and classification of different types of motor oils.

Application of Neural Networks for the Classification of Diffuse Liver Disease by Quantitative Echography

1993 ◽  
Vol 15 (3) ◽  
pp. 205-217 ◽  
Author(s):  
M.S. klein Gebbinck ◽  
J.T.M. Verhoeven ◽  
J.M. Thijssen ◽  
T.E. Schouten
Keyword(s):  
Neural Networks ◽  
Liver Disease ◽  
Image Texture ◽  
Attractive Alternative ◽  
Diffuse Liver Disease ◽  
Texture Parameters ◽  
Number Of Patients ◽  
Test Sets ◽  
Validation Set

Three different methods were investigated to determine their ability to detect and classify various categories of diffuse liver disease. A statistical method, i.e., discriminant analysis, a supervised neural network called backpropagation and a nonsupervised, self-organizing feature map were examined. The investigation was performed on the basis of a previously selected set of acoustic and image texture parameters. The limited number of patients was successfully extended by generating additional but independent data with identical statistical properties. The generated data were used for training and test sets. The final test was made with the original patient data as a validation set. It is concluded that neural networks are an attractive alternative to traditional statistical techniques when dealing with medical detection and classification tasks. Moreover, the use of generated data for training the networks and the discriminant classifier has been shown to be justified and profitable.

scholarly journals Titrable acidity of wines at different pH and its relation with the colour

OENO One ◽  
1998 ◽  
Vol 32 (3) ◽  
pp. 163
Author(s):  
Maria Dolores Huerta ◽  
Maria Rosario Salinas Fernandez ◽  
Taisir Masoud Musa
Keyword(s):  
Discriminant Analysis ◽  
Correct Classification ◽  
Red Wines ◽  
Colour Intensity ◽  
Titrable Acidity ◽  
Ph Values ◽  
First Approximation ◽  
Different Types ◽  
The Difference

<p style="text-align: justify;">This work constitute a first approximation to study the relation between the value of the titrable acidit y at different pH and the colour intensity of wines. The organic acids from wines treated with NaOH are weak acids, for this reason the neutralisation with a strong alkali solution, it should give pH values greater than 7. We have studied a new parameter based on the difference between pH 8.2 (stablised by the Association of Official Analytical Chemists) and pH 7.0 (stablised by the Office International de la Vigne et du Vin). the mentioned parameter (AT<sub>8,2</sub>-AT<sub>7,0</sub>) has been used to find a possible differentiation between wines according to colour. Eighty eighth wines (white, red and rose) belonging to the three district making up the « Vinos of Madrid» Origin were analysed. The values of this new parameter are similar for white and rose wines but considerably differences were observed for the red type. A linear correlation was obtained between the <span>AT</span><sub>8,2</sub><span>-AT</span><sub>7,0 </sub>parameter and the colour intensity from red wines. Discriminant analysis were applied to this parameter in order to classify the wines according to their colour. A correct classification of 71.43 p. cent was obtained for the three different types of red wines.</p>

scholarly journals CLASSIFICATION OF SWEET PEA CULTIVARS BY MEANS OF DISCRIMINANT ANALYSIS

HortScience ◽  
1994 ◽  
Vol 29 (4) ◽  
pp. 253a-253
Author(s):  
Nicolas Tremblay
Keyword(s):  
Cluster Analysis ◽  
Discriminant Analysis ◽  
Nutrient Composition ◽  
Diagnosis System ◽  
Leaf Analysis ◽  
Different Types ◽  
Processing Plants ◽  
Leaf Composition ◽  
Sweet Pea

Processing plants requires that cultivars be categorized as either small, medium, or large peas to meet the different markets. A reliable nutrient diagnosis system based on sweet pea leaf analysis should be robust to the type of cultivar. The objective of this study was to determine whether the type of cultivar should be taken into account in producing the nutrient diagnosis. Proportions of peas in categories 1 (small) to 5 (large) were determined for 18 cultivars produced under commercial conditions over 3 years. Cluster analysis was conducted with the constraint of revealing three groups, as homogeneous as possible with regard to their proportions in the different categories. Three cultivars were identified as belonging to the small, nine to the medium, and six to the large group. The archetype of each group was characterized. The function discriminated among the cultivars perfectly along the canonical axes. However, no classification was possible when the nutrient composition variables (N, P, K, Ca, Mg, B, Fe, Mn, Zn) were used for discriminating cultivars' types. Hence, sweet pea cultivars of different types do not differ substantially in leaf composition.

scholarly journals Mucin producing carcinomas of the breast. Cytological diagnostics

2020 ◽  
Vol 16 (1) ◽  
pp. 21-31
Author(s):  
O. G. Grigoruk ◽  
T. A. Moskvina ◽  
L. M. Bazulina ◽  
E. S. Sigitova ◽  
A. S. Stepanova ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Ethics Committee ◽  
Biomedical Ethics ◽  
Multiple Factor Analysis ◽  
Different Types ◽  
Cytological Characteristics ◽  
Cytological Method ◽  
Medical University ◽  
Cytological Diagnostics

The aim of the study is to estimate potentiality of the cytological diagnostics of different types of mucin producing carcinomas of the breast.Materials and methods. Cytological evidences of the investigation of 35 patients with mucinous mass in cytological specimens were studied. Different types of mucinous carcinomas which had been diagnosed by cytological method were identified retrospectively.Results. “Pure” mucous carcinomas were divided into two types: hypocellular (A) and hypercellular (B) (n = 9 (25.7 %) and 14 (40 %), respectively). Mixed carcinomas (mucous carcinoma with invasive no special type carcinoma) were noticed of 12 women (34.3 %). 24 cell characteristics of mucin producing carcinomas were identified. Some cytological characteristics were estimated due to multiple factor analysis and discriminant analysis.Conclusions. Investigation results indicated that cytological technique is a high-quality diagnostic method. The fraction of correct classification of mucous carcinoma types based on discriminant analysis was 92–99 %.The study protocol was approved by the biomedical ethics committee of The Altai State Medical University, Ministry of Health of Russia.

Dual stain kit for the microscopic gram classification of ocular infection bacteria

1993 ◽  
Vol 51 ◽  
pp. 248-249
Author(s):  
Jacob S. Hanker ◽  
Dale N. Holdren ◽  
Kenneth L. Cohen ◽  
Beverly L. Giammara
Keyword(s):  
Contact Lenses ◽  
Ocular Infection ◽  
Gram Negative Bacteria ◽  
Gram Negative ◽  
Gram Staining ◽  
Ocular Infections ◽  
Different Types ◽  
Culture Positive ◽  
Increased Susceptibility

Keratitis and conjunctivitis (infections of the cornea or conjunctiva) are ocular infections caused by various bacteria, fungi, viruses or parasites; bacteria, however, are usually prominent. Systemic conditions such as alcoholism, diabetes, debilitating disease, AIDS and immunosuppressive therapy can lead to increased susceptibility but trauma and contact lens use are very important factors. Gram-negative bacteria are most frequently cultured in these situations and Pseudomonas aeruginosa is most usually isolated from culture-positive ulcers of patients using contact lenses. Smears for staining can be obtained with a special swab or spatula and Gram staining frequently guides choice of a therapeutic rinse prior to the report of the culture results upon which specific antibiotic therapy is based. In some cases staining of the direct smear may be diagnostic in situations where the culture will not grow. In these cases different types of stains occasionally assist in guiding therapy.

Explanatory Power for Medical Expert Systems: Studies in the Representation of Causal Relationships for Clinical Consultations

1982 ◽  
Vol 21 (03) ◽  
pp. 127-136 ◽  
Author(s):  
J. W. Wallis ◽  
E. H. Shortliffe
Keyword(s):  
Explanatory Power ◽  
Prototype System ◽  
Inference Rules ◽  
Medical Expert ◽  
Comprehensive Knowledge ◽  
Different Types ◽  
Medical Expert Systems ◽  
Explanation System ◽  
Systems Studies

This paper reports on experiments designed to identify and implement mechanisms for enhancing the explanation capabilities of reasoning programs for medical consultation. The goals of an explanation system are discussed, as is the additional knowledge needed to meet these goals in a medical domain. We have focussed on the generation of explanations that are appropriate for different types of system users. This task requires a knowledge of what is complex and what is important; it is further strengthened by a classification of the associations or causal mechanisms inherent in the inference rules. A causal representation can also be used to aid in refining a comprehensive knowledge base so that the reasoning and explanations are more adequate. We describe a prototype system which reasons from causal inference rules and generates explanations that are appropriate for the user.

Sign in / Sign up

Export Citation Format

Share Document