Modelling the Results of the Phadiatop Test Using the Logistic and Ordinal Regression
This study was based on examination Phadiatop onerous test at the Clinic of Occupational and Preventive Medicine in order to save money and not make unnecessary testing. The aim of this study was to assess the outcome of the test Phadiatop only under close personal or family history of each patient. This estimation was used statistical methods specifically logistic and ordinal regression. The most important findings are that Phadiatop test result does not imply eczema; it is a different immune response and the disease is not relevant in personal or family anamnesis. The patient was based on a family and personal anamnesis, in assigning only two groups (healthy or sick) correctly classified with a probability of 75 %. The test sensitivity is about 77 % and the diseases influencing the results are asthma and allergic rhinitis. The success rate of classifying each patient into one of the five Phadiatop test groups according to the seriousness of diseases was about 68 %. Also a testing based on age groups of the patients was done using this database. The presence of the positive Phadiatop test was the most common for people born between 1972 and 1981, where the genetic predispositions for a positive Phadiatop test results are about 39 %.
KeywordsLogistic Regression Positive Predictive Value Negative Predictive Value Allergic Rhinitis Genetic Predisposition
This paper was done thanks to cooperation with The University Hospital of Ostrava, the Department of Clinic of Occupation and Preventive medicine. This work was supported by the International Visegrad Fund’s Standard Grant No. 21320401.
- 2.Hajduková, Z., Vantuchová, Y., Klimková, P., Makhoul, M., Hromádka, R.: Atopy in patiens with allergic contact dermatitis. J. Czech Phys. Occup. ther. 2, 69–73 (2009). In CzechGoogle Scholar
- 3.Hajduková, Z., Pólová, J., Kosek, V.: The importance of Atopy Investigation in the Department of Travel Medicine, Allergies: magazine for continuous education in allergy and clinical immunology, No. 2 (2005), pp. 106–109Google Scholar
- 4.Sigurs, N., et al.: Asthma and allergy patterns over 18 years after severe RSV bronchiolitis in the first year of life. Thorax 65.12 (2010), pp. 1045–1052Google Scholar
- 5.Wuthrich, B., et al.: Prevalence of atopy and pollinosis in the adult population of Switzerland (SAPALDIA study). Int. Arch. Allergy Immunol. 106(2), 149–156 (2009)Google Scholar
- 6.Wuthrich, B., et al.: IgE levels, atopy markers and hay fever in relation to age, sex and smoking status in a normal adult Swiss population. Int. Arch. Allergy Immunol. 111(4), 396–402 (2009)Google Scholar
- 9.Kuráňová, P.: The processing of the medical data with use of logistic regression, reliability & risk analysis: theory & applications (R&RATA). J. Int. Group Realiability 24(01), 65–72 (2012)Google Scholar
- 10.Kuráňová, P., Praks, P., Hajduková, Z.: Improving the probabilistic prediction model of the phadiatop test by data pre-processing. In: Mendel 2012: 18th International Conference on Soft Computing. Brno University of Technology, Brno, pp. 500–504 (2012) ISSN 1803–3814. ISBN 978-80-214-4540-6Google Scholar
- 11.Kuráňová, P., Hajduková, Z.: The use of logistic and ordinal regression for the prediction of the phadiatop test results. In: Sbornk konference the Ninth International Conference on Digital Technologies 2013, Ilina, pp. 111–115 (2013) ISBN: 978-1-4799-0923-0. doi: 10.1109/DT.2013.6566297
- 12.Menard, S.: LOGISTIC REGRESSION From Introductory to Advanced Concepts and Applications. SAGE Publications Inc., California (2009)Google Scholar
- 14.McCullagh, P., Nelder, J.A.: Generalized Linear Models, 2nd edn. Chap-man & Hall/CRC, Boca Raton (1989)Google Scholar
- 15.Powers, D.A., Xie, Y.: Statistical Methods for Categorical Data Analysis. Academic Press, San Diego (2000)Google Scholar
- 16.Vidal, C., et al.: Evaluation of the phadiatop test in the diagnosis of allergic sensitization in a general adult population. J. Investig. Allergol. Clin. Immunol. 15(2), 124–130 (2005)Google Scholar