Prediction of Social Participation Factors Affecting the Quality of Life of Mothers with Children with PKU Using a Random Forest Model: A Cross-sectional Study in Hamadan, Iran, in 2018

Document Type : Original Article

Authors

1 University Research and Development Center, Tehran University of Medical Sciences, Tehran, Iran

2 Department of Nursing, Faculty of Nursing and Midwifery, Hormozgan University of Medical Science, Bandar Abbas, Iran

3 Department of Public Health, School of Health, Abadan University of Medical Sciences, Abadan, Iran

4 Yazd Cardiovascular Research Center, Shahid Sadoughi University of Medical Sciences, Yazd, Iran

5 Department of Occupational Therapy, Faculty of Rehabilitation, Hamadan University of Medical Sciences, Hamadan, Iran

6 Endocrinology and Metabolism Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran

10.34172/JHAD.92376

Abstract

Abstract
Background: Parents of children with chronic medical conditions, including those with phenylketonuria (PKU), face emotional
stress. In this study, we will focus mainly on the social relationships, social participation, and quality of life of mothers of children
with PKU using the random forest (RF) method.
Method: In this cross-sectional study, data were collected from the Association for the Protection of PKU in Hamadan province.
We utilized the RF method for data analysis using the packages “Metrics” and “random forest SRC” in R software (version 3.2.2).
Results: In total, 201 mothers who had children with PKU were included in this study. More than half (52.2%) of the mothers
were aged between 18 and 35 years. Based on the random forest method, the most important predictors of the social interactions
and social participation of mothers who had children with PKU were, in order, environmental health, social relationships, mental
health, physical health, income, the number of family members, educational status, mothers’ job status, and age of mothers.
Conclusion: The first four variables (environmental health, social relationships, mental health, and physical health) were the most
effective predictors.

Keywords

Main Subjects