There are several patient- and verruca-specific factors that determine treatment response to cryotherapy. A comprehensive analysis of these factors necessitates the use of a systematic and rational approach. The present study uses machine learning algorithms to analyze the clinical patient- and verruca-specific factors that affect the success of cryotherapy treatment. Machine learning algorithms were applied to the cryotherapy dataset. The best results in the prediction of treatment response to cryotherapy were achieved through the C&R Tree classification method, with a 96% accuracy rate, followed by the C5.0 Tree, CHAID Tree and the adjusted J48 Decision Tree algorithms, respectively. The C&R Tree classification method revealed that the most significant factors that affected treatment response in verrucae, in the order of importance, were the time to the first session, the patient’s age, the type of verruca, the number of verrucae and the region of the verruca. We believe that by identifying factors that affect treatment success and investigating the relations between variables, machine learning approaches can guide clinical treatment decisions for the more effective management of verruca treatment, which represent an important social and economic burden in public health.
There are several patient- and verruca-specific factors
that determine treatment response to cryotherapy. A comprehensive analysis of
these factors necessitates the use of a systematic and rational approach. The
present study uses machine learning algorithms to analyze the clinical patient-
and verruca-specific factors that affect the success of cryotherapy treatment.
Machine learning algorithms were applied to the cryotherapy dataset. The best
results in the prediction of treatment response to cryotherapy were achieved
through the C&R Tree classification method, with a 96% accuracy rate,
followed by the C5.0 Tree, CHAID Tree and the adjusted J48 Decision Tree
algorithms, respectively. The C&R Tree classification method revealed that
the most significant factors that affected treatment response in verrucae, in the
order of importance, were the time to the first session, the patient’s age, the
type of verruca, the number of verrucae and the region of the verruca. We
believe that by identifying factors that affect treatment success and
investigating the relations between variables, machine learning approaches can
guide clinical treatment decisions for the more effective management of verruca
treatment, which represent an important social and economic burden in public
health.
Primary Language | English |
---|---|
Journal Section | Articles |
Authors | |
Publication Date | December 31, 2019 |
Acceptance Date | December 27, 2019 |
Published in Issue | Year 2019 Volume: 3 Issue: 2 |