Stručni rad
Cluster Analysis as a Prediction Tool for Pregnancy Outcomes
Ines Banjari
orcid.org/0000-0002-8680-5007
; »J. J. Strossmayer« University Osijek, Department of Food and Nutrition Research, Faculty of Food Technology, Osijek, Croatia
Daniela Kenjerić
; »J. J. Strossmayer« University Osijek, Department of Food and Nutrition Research, Faculty of Food Technology, Osijek, Croatia
Krešimir Šolić
; »J. J. Strossmayer« University Osijek, School of Medicine, Department of Biophysics, Medical Statistics and Medical Informatics, Osijek, Croatia
Milena L. Mandić
; »J. J. Strossmayer« University Osijek, Department of Food and Nutrition Research, Faculty of Food Technology, Osijek, Croatia
Sažetak
Considering specifi c physiology changes during gestation and thinking of pregnancy as a »critical window«, classifi cation
of pregnant women at early pregnancy can be considered as crucial. The paper demonstrates the use of a method
based on an approach from intelligent data mining, cluster analysis. Cluster analysis method is a statistical method
which makes possible to group individuals based on sets of identifying variables. The method was chosen in order to
determine possibility for classifi cation of pregnant women at early pregnancy to analyze unknown correlations between
different variables so that the certain outcomes could be predicted. 222 pregnant women from two general obstetric offi
ces’ were recruited. The main orient was set on characteristics of these pregnant women: their age, pre-pregnancy body
mass index (BMI) and haemoglobin value. Cluster analysis gained a 94.1% classifi cation accuracy rate with three branches
or groups of pregnant women showing statistically signifi cant correlations with pregnancy outcomes. The results are
showing that pregnant women both of older age and higher pre-pregnancy BMI have a signifi cantly higher incidence of
delivering baby of higher birth weight but they gain signifi cantly less weight during pregnancy. Their babies are also
longer, and these women have signifi cantly higher probability for complications during pregnancy (gestosis) and higher
probability of induced or caesarean delivery. We can conclude that the cluster analysis method can appropriately classify
pregnant women at early pregnancy to predict certain outcomes.
Ključne riječi
pregnant women; cluster analysis; pre-pregnancy BMI; maternal age; pregnancy outcomes; caesarean delivery; gestosis; weight gain; birth weight; classifi cation
Hrčak ID:
147803
URI
Datum izdavanja:
30.3.2015.
Posjeta: 914 *