4 / 34
Advance Nursing Practice 2018
J u n e 2 1 - 2 2 , 2 0 1 8
P a r i s , F r a n c e
Page 60
Journal of Nursing and Health Studies
ISSN 2574-2825
6
t h
I n t e r n a t i o n a l C o n f e r e n c e o n
Advance Nursing Practice
D
ecision-makers, and even patients, want to know in advance what will
happen to their health. There are various developed statistical models
in this regard. The nomogram is one of these models, and it generates a
graphical solution in order to calculate disease outcome probabilities on an
individual basis. Prognostic factors of individual patients can be addressed
and the results can be easily calculated by using the nomogram. The aim
of this study is to develop a nomogram for predicting urinary incontinence.
This nomogram developing study was conducted on 95 patients with urinary
incontinence and 126 patients without urinary incontinence. Demographic
and clinical characteristics were collected; also patients filled Urogenital
Distress Inventory-6 (UDI-6). The effect of probably prognostic factors on
urinary incontinence were investigated by using the univariate statistical tests
and multivariate logistic regression analysis and then based on these data,
a nomogram model was developed for predict urinary incontinence. Model
validation and calibration work was done. Among the independent prognostic
factors that were entered to the multivariate logistic regression model, 4
variables (age, body mass index, waist circumference, and smoking) were
found significantly. These variables entered to the nomogram model, however,
body mass index was deleted from the model in the validation process (Chi-
square=0.36, df=1, p=0.546). As a result of the 1000 bootstrap replication that
were made for the validity of the model, three variables "age (p<0.001), waist
circumference (p<0.001), and smoking (p=0.001)" were included in the final
model. The c-index value for the validated model was found to be 0.989. The
mean absolute error for the model calibration was 0.007. A novel nomogram
that was developed in this study can be use in clinical practices for predicting
of urinary incontinence.
A novel statistical tool for predicting urinary incontinence in
clinical practice
Necdet Sut, Hatice Kahyaoglu-Sut and Burcu Kucukkaya
Trakya University, Turkey
Necdet Sut et al., J Nurs Health Stud 2018, Volume: 3
DOI: 10.21767/2574-2825-C3-009
Biography
Necdet Sut has completed his PhD from Istanbul University.
He is Chief of the Department of Biostatistics and Medical
Informatics, Trakya University, Medical Faculty. He has
published more than 200 papers in reputed journals and has
been serving as Biostatistics Editor of repute
necdetsut@yahoo.com