Current issue
About the Journal
Scientific Council
Editorial Board
Regulatory and archival policy
Code of publishing ethics
Publisher
Information about the processing of personal data in relation to cookies and newsletter subscription
Archive
For Authors
For Reviewers
Contact
Reviewers
Annals reviewers in 2022
Annals reviewers in 2021
Annals reviewers in 2020
Annals reviewers in 2019
Annals reviewers in 2018
Annals reviewers in 2017
Annals reviewers in 2016
Annals reviewers in 2015
Annals reviewers in 2014
Annals reviewers in 2013
Annals reviewers in 2012
Links
Sklep Wydawnictwa SUM
Biblioteka Główna SUM
Śląski Uniwersytet Medyczny w Katowicach
Privacy policy
Accessibility statement
Logistic regression and classification tree methods as elements of diagnosis in cardiology
| 1 | Department of Environmental Health, School of Public Health in Bytom, Medical University of Silesia in Katowice, Poland |
CORRESPONDING AUTHOR
Anna Spychała
Department of Environmental Health, School of Public Health in Bytom, Medical University of Silesia in Katowice, Poland, ul. Piekarska 18, 41-902 Bytom, tel. 32 397 65 44
Department of Environmental Health, School of Public Health in Bytom, Medical University of Silesia in Katowice, Poland, ul. Piekarska 18, 41-902 Bytom, tel. 32 397 65 44
Ann. Acad. Med. Siles. 2016;70:154–162
KEYWORDS
TOPICS
ABSTRACT
Introduction:
The purpose of statistical analysis in research is to identify accurate and reliable conclusions where the researcher has a great deal of sources and information. Usually, one can point to a few different methods that allow the task to be fulfilled, but each time the question arises: which one to choose?
Material and methods:
The study was conducted using a database that included 3246 patients in the Second Department of Cardiology, Silesian Medical Centre in Katowice-Ochojec in 2003–2008. We were A model in which the STROKE dependent variable was considered was subjected to statistical analysis, and the results of the analysis suggested selecting the following variables: gender, transfusion, PTCA, IVA, IVM, SVA, aneurysm and hematocrit.
Results:
The essential factors affecting the occurrence of stroke, according to logistic regression are: aneurysm, transfusion of blood components, prior treatment with PTCA and according to the classification tree: aneurysm and level of hematocrit.
Conclusions:
The results achieved by both the two statistical models complemented each other, and by combining them one is able to obtain reliable information to use as a base for the decision-making process.
The purpose of statistical analysis in research is to identify accurate and reliable conclusions where the researcher has a great deal of sources and information. Usually, one can point to a few different methods that allow the task to be fulfilled, but each time the question arises: which one to choose?
Material and methods:
The study was conducted using a database that included 3246 patients in the Second Department of Cardiology, Silesian Medical Centre in Katowice-Ochojec in 2003–2008. We were A model in which the STROKE dependent variable was considered was subjected to statistical analysis, and the results of the analysis suggested selecting the following variables: gender, transfusion, PTCA, IVA, IVM, SVA, aneurysm and hematocrit.
Results:
The essential factors affecting the occurrence of stroke, according to logistic regression are: aneurysm, transfusion of blood components, prior treatment with PTCA and according to the classification tree: aneurysm and level of hematocrit.
Conclusions:
The results achieved by both the two statistical models complemented each other, and by combining them one is able to obtain reliable information to use as a base for the decision-making process.
REFERENCES (26)
1.
Koźmiński A.K., Piotrowski W. Zarządzanie. Teoria i praktyka. Wydawnictwo Naukowe PWN. Warszawa 2002.
2.
Szydło R. Komu jest potrzebny statystyk medyczny? Onkol. Prakt. Klin. 2005; 1(3): 129–131.
3.
Michalski T. Statystyka. Wydawnictwo Szkolne i Pedagogiczne. Warszawa 2004, s. 5–7.
4.
Sobczyk M. Statystyka. Wydawnictwo Uniwersytetu Marii Curie-Skłodowskiej. Lublin 2001, s. 7–9.
5.
Dobbson A.J. The role of the statistician. Int. J. Epidemiol. 1983; 12(3): 274–275.
6.
Lenz R., Reuchert M. IT suport for healthcare processes-premises, challenges, perspectives. Data & Knowlegde Engineering 2007; 61: 39–58.
7.
Stanisz A. Przystępny kurs statystyki z zastosowaniem STATISTICA PL na przykładach z medycny. Tom II. StatSoft Polska. Kraków 2006, s. 217–254.
8.
Stanisz A. Biostatystyka. Wydawnictwo Uniwersytetu Jagiellońskiego. Kraków 2005, s. 325–335.
9.
Stanisz A. Regresja logistyczna. Medycyna Praktyczna 200110, http:www.mp.plartykulyindex.php?aid=11813&_tc=32F4510F44D54B93654578ACE3F57E99 [dostęp z dnia: 02.01.2013].
10.
Łapczyński M. Drzewa klasyfikacyjne i regresyjne w badaniach marketingowych. Uniwersytet Ekonomiczny. Kraków 2011.
11.
Stanisz A. Przystępny kurs statystyki z zastosowaniem STATISTICA PL na przykładach z medycyny. Tom III. StatSoft Polska. Kraków 2006, s. 113–153.
12.
Łapczyński M. Drzewa klasyfikacyjne w badaniach satysfakcji i lojal-ności klientów. StatSoft Polska. Kraków 2003.
13.
Gatnar E., Walesiak M. Statystyczna analiza danych z wykorzystaniem programu R. Wydawnictwo Naukowe PWN. Warszawa 2009, s. 238–260.
14.
Stanisz A. Statistica w badaniach naukowych i nauczaniu statystyki. StatSoft Polska. Kraków 2010, s. 61–80.
15.
StatSoft Electronic Statistic Textbook. Drzewa klasyfikacyjne, http:www.statsoft.pltextbookstathome_stat.html?http%3A%2F%2Fwww.statsoft.pl%2Ftextbook%2Fstclatre.html [dostęp z dnia: 02.01.2013].
16.
Koronacki J., Ćwik J. Statystyczne systemy uczące się. 2 wyd. EXIT. Warszawa 2008, s. 129–164.
17.
Harańczyk G. Krzywa ROC, czyli ocena jakości klasyfikatora i poszukiwanie optymalnego punktu odcięcia. StatSoft Polska. Kraków 2010, s. 79–89.
18.
Swets J.A., Dawes S.M., Monahan J. Better decisions through science. Sci. Am. 2000; 283(4): 82–87.
19.
Stanisz A. Przystępny kurs statystyki z zastosowaniem STATISTICA PL na przykładach z medycyny. Tom I. StatSoft Polska. Kraków 2006, s. 340–370.
20.
Harańczyk G., Stępień M. Ilustrowana sztuka podejmowania decyzji. Matematyka Społeczeństwo Nauczanie 2008; 41: 12–15.
21.
Lemon S.C., Roy J., Clark M.A., Friedmann P.D., Rakowski W. Classification and regression tree analysis in public health: methodological review and comparison with logistic regression. Ann. Behav. Med. 2003; 26(3): 172–181.
22.
Long W.J., Griffith J.L., Selker H.P., D’Agostino R.B. A comparison of logistic regression to decision-tree induction in a medical domain. Comput. Biomed. Res. 1993; 26: 74–97.
23.
Owczarek A. Drzewa decyzyjne oraz analiza hazardu proporcjonalnego Coxa w przewidywaniu niekorzystnych zdarzeń sercowych u chorych z przewlekłą niewydolnością serca. Rozprawa habilitacyjna nr 12/2011. Śląski Uniwersytet Medyczny w Katowicach. Katowice 2011.
24.
Classification and Regression Trees. http:documents.software.dell.com StatisticsTextbookClassification-and-Regression-Trees [dostęp z dnia: 15.06.2015].
25.
Słapa R.Z. Zastosowanie ultrasonografii trójwymiarowej w diagnostyce zmian ogniskowych tarczycy. Akademia Medyczna w Warszawie. Warszawa 2007.
26.
Goel R., Misra A., Kondal D., Pandey R.M., Vikram N.K., Wasir J.S., Dhingra V., Luthra K. Identification of insulin resistance in Asian Indian adolescents: classification and regression tree (CART) andlogistic regre-ssion based classification rules. Clin. Endocrinol. (Oxf) 2009; 70(5): 717–724.
RELATED ARTICLE
The Medical University of Silesia in Katowice, as the Operator of the annales.sum.edu.pl website, processes personal data collected when visiting the website. The function of obtaining information about Users and their behavior is carried out by voluntarily entered information in forms, saving cookies in end devices, as well as by collecting web server logs, which are in the possession of the website Operator. Data, including cookies, are used to provide services in accordance with the Privacy policy.
You can consent to the processing of data for these purposes, refuse consent or access more detailed information.
You can consent to the processing of data for these purposes, refuse consent or access more detailed information.