LOGIC REGRESSION FOR DIAGNOSTIC CLASSIFICATION BY MEANS OF BIOMARKER PANELS
Journal Title: Colloquium Biometricum; Colloquium Biometricum (Online) - Year 2016, Vol 46, Issue
Abstract
Biomarkers can indicate a variety of health or disease characteristics, including the level or type of exposure to an environmental factor, genetic susceptibility, genetic responses to exposures, markers of subclinical or clinical disease, or indicators of response to therapy. In this paper we presented using the logic regression for diagnostic classification by means of biomarker panels. The sample collective comprised 389 highly characterized rheumatoid artritis patients and 390 controls, composed of 200 healthy and 190 osteoarthritis samples. The predictive panel consisted of the most promising 11 biomarkers for the early diagnosis of rheumatoid artritis, collected in serum. Obtained results show that the Logic II is the simplest model and performs well, resulting in the lowest misclassification error rate on the test set.
Authors and Affiliations
Jan Bocianowski, Kamila Nowosad
Keywords
Related Articles
- EP ID EP190145
- DOI -
- Views 114
- Downloads 0
A METHOD FOR ANALYSIS AND INTERPRETATION OF DATA FROM FIELD AND BREWERY TRIALS
In the paper a method for statistical analysis of data with brewing barley is proposed which allows to use information from designing a field experiment. The experiment was conducted during the growing seasons 2008–2010...
On the efficiency of orthogonal treatment contrasts in multistratum incomplete split-split-plot designs constructed by square lattice designs
We construct an incomplete split-split-plot design for three factor experiments. The method is based on a semi-Kronecker (Khatri-Rao) product of three matrices. We use two square lattice designs for whole plot treatments...
CHANGES OF CHOSEN PROPERTIES OF SANDY SOIL IN RESULT OF COMPOST APPLICATION
In this paper, the analysis of variance of the results of experiment conducted in laboratory conditions is described. The objective of this study was to evaluate changes in soil reaction, hydrolytic acidity, sum of bases...
RELATIONS BETWEEN TERNARY DESIGNS AND D-OPTIMAL WEIGHING DESIGNS WITH NON-NEGATIVE CORRELATED ERRORS
This work was intended as an attempt at motivating to increase the list of possible classes in that we are able to construct optimal plans of experiments. Here, we consider the criterion of D-optimality. We introduce the...
NEW CONSTRUCTION OF D-OPTIMAL WEIGHING DESIGNS WITH NON-NEGATIVE CORRELATIONS OF ERRORS
In this paper, the regular D-optimal chemical balance weighing designs with equally non-negative correlated errors are considered. Here we study the issues regard to the existence conditions of optimal designs. Presented...