Development and performance analysis of machine learning methods for predicting depression among menopausal women

Menopause is an obligatory phenomenon in a woman’s life. Some women face mental and physical issues during their menopausal period. Depression is one of the issues some women struggle with during their menopausal period. The scarcity of specialists, lack of knowledge, and awareness is the motivating...

Full description

Saved in:
Bibliographic Details
Published in:Healthcare analytics (New York, N.Y.) N.Y.), 2023-11, Vol.3, p.100202, Article 100202
Main Authors: Ali, Md. Mamun, Algashamy, Hussein Ali A., Alzidi, Enas, Ahmed, Kawsar, Bui, Francis M., Patel, Shobhit K., Azam, Sami, Abdulrazak, Lway Faisal, Moni, Mohammad Ali
Format: Article
Language:English
Subjects:
Artificial intelligence
Depression
Machine learning
Menopause
Quality of life
Random Forest
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Menopause is an obligatory phenomenon in a woman’s life. Some women face mental and physical issues during their menopausal period. Depression is one of the issues some women struggle with during their menopausal period. The scarcity of specialists, lack of knowledge, and awareness is the motivating factor in this research to predict depression among menopausal women and enhance their quality of life. The prediction of depression symptoms among menopausal women with machine learning techniques is promising and challenging in artificial intelligence. This study develops a system with significant accuracy using a supervised machine-learning approach. Various classification algorithms are used to determine the best-performing classifier by evaluating multiple parameters, including accuracy, sensitivity, specificity, precision, recall, F-Measure, Receiver Operating Characteristic (ROC), Precision–Recall​ Curve (PRC), and Area Under the Curve (AUC). We found that Random Forest and XGBoost classifiers are the performers with 99.04% accuracy employing the 14 most significant features. •A prediction system is developed in this study to predict depression among menopausal women.•Numerous machine learning classification algorithms are employed on a raw dataset.•A superior performer algorithm is chosen for the proposed method based on accuracy, sensitivity, specificity, precision, recall, and F-Measure.•It is observed that Random forest and XGBoost show significantly better outcomes than other classifiers.•This study aims to provide a simple and user-friendly prediction system, which is easy to use.
ISSN:2772-4425
2772-4425
DOI:10.1016/j.health.2023.100202