This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Faculty of Technical Sciences, University of Kragujevac , Kragujevac , Serbia
Tarbiat Modares University , Tehran , Iran
University of Tehran , Tehran , Iran
Faculty of Technical Sciences, University of Kragujevac , Kragujevac , Serbia
Breast cancer is one of the most common malignancies, and one of the leading causes of cancer-related death among women. This research aimed to explain emotional distress based on self-empowerment skills and interpersonal interactions in breast cancer patients using the explainable multilayer perceptron classification model. The participants in this research were a sample of 735 patients age ranged from 19-80 with breast cancer from Tajrish Hospital in Tehran in 2022 who were selected by convenience sampling through online platforms. The survey assessments included demographic characteristics (age and job, marital status and educational level), emotional distress, self-empowerment skills, interpersonal interactions, and family care. The data were analyzed using the Multilayer Perceptron Classification Model. The input layer includes age and job, marital status and educational level, self-empowerment skills, interpersonal interactions, family care and gender) and the output layer (target feature) includes emotional distress divided into low and high groups using a mean split. The results indicated that the accuracy of the classification in the training and test samples was 75.6% and 73.5% respectively. The AUC of 0.812 in the models was near to 1 indicating an excellent fit. Interpersonal interactions, self-empowerment, family care, age, having job, educational level and marital status were the most important effects in explaining the classification of emotional distress.
breast cancer, emotional distress, multilayer perceptron, self-empowerment skills, interpersonal interactions
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.
