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

Md Mamun Ali; Hussein Ali A. Algashamy; Enas Alzidi; Kawsar Ahmed; Francis M. Bui; Shobhit K. Patel; Sami Azam; Lway Faisal Abdulrazak; Mohammad Ali Moni

doi:10.1016/j.health.2023.100202

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

Md Mamun Ali, Hussein Ali A. Algashamy, Enas Alzidi, Kawsar Ahmed, Francis M. Bui, Shobhit K. Patel, Sami Azam, Lway Faisal Abdulrazak, Mohammad Ali Moni

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

55 Downloads (Pure)

Abstract

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.

Original language	English
Article number	100202
Pages (from-to)	1-13
Number of pages	13
Journal	Healthcare Analytics
Volume	3
DOIs	https://doi.org/10.1016/j.health.2023.100202
Publication status	Published - Nov 2023

Bibliographical note

Funding Information:
Md. Mamun Ali: Analyzed the data, Wrote the manuscript. Hussein Ali A. Algashamy: Helped perform the experimental analysis with constructive discussion. Enas Alzidi: Helped perform the experimental analysis with constructive discussion. Kawsar Ahmed: Provided the idea, Designed the experiments, Analyzed the data, Wrote the manuscript. Francis M. Bui: Provided the idea, Designed the experiments, Helped perform the experimental analysis with constructive discussion, Supported by funding. Shobhit K. Patel: Helped perform the experimental analysis with constructive discussion. Sami Azam: Helped perform the experimental analysis with constructive discussion. Lway Faisal Abdulrazak: Helped perform the experimental analysis with constructive discussion. Mohammad Ali Moni: Provided the idea, Designed the experiments.

Publisher Copyright:
© 2023 The Author(s)

Access to Document

10.1016/j.health.2023.100202

80964527-oaFinal published version, 2.68 MBLicence: CC BY-NC-ND

Cite this

@article{761c8b07f0944b4cb362b73f46f3ecb8,

title = "Development and performance analysis of machine learning methods for predicting depression among menopausal women",

abstract = "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.",

keywords = "Artificial intelligence, Depression, Machine learning, Menopause, Quality of life, Random Forest",

author = "Ali, {Md Mamun} and Algashamy, {Hussein Ali A.} and Enas Alzidi and Kawsar Ahmed and Bui, {Francis M.} and Patel, {Shobhit K.} and Sami Azam and Abdulrazak, {Lway Faisal} and Moni, {Mohammad Ali}",

note = "Funding Information: Md. Mamun Ali: Analyzed the data, Wrote the manuscript. Hussein Ali A. Algashamy: Helped perform the experimental analysis with constructive discussion. Enas Alzidi: Helped perform the experimental analysis with constructive discussion. Kawsar Ahmed: Provided the idea, Designed the experiments, Analyzed the data, Wrote the manuscript. Francis M. Bui: Provided the idea, Designed the experiments, Helped perform the experimental analysis with constructive discussion, Supported by funding. Shobhit K. Patel: Helped perform the experimental analysis with constructive discussion. Sami Azam: Helped perform the experimental analysis with constructive discussion. Lway Faisal Abdulrazak: Helped perform the experimental analysis with constructive discussion. Mohammad Ali Moni: Provided the idea, Designed the experiments. Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2023",

month = nov,

doi = "10.1016/j.health.2023.100202",

language = "English",

volume = "3",

pages = "1--13",

journal = "Healthcare Analytics",

issn = "2772-4425",

publisher = "Elsevier",

}

TY - JOUR

T1 - Development and performance analysis of machine learning methods for predicting depression among menopausal women

AU - Ali, Md Mamun

AU - Algashamy, Hussein Ali A.

AU - Alzidi, Enas

AU - Ahmed, Kawsar

AU - Bui, Francis M.

AU - Patel, Shobhit K.

AU - Azam, Sami

AU - Abdulrazak, Lway Faisal

AU - Moni, Mohammad Ali

N1 - Funding Information: Md. Mamun Ali: Analyzed the data, Wrote the manuscript. Hussein Ali A. Algashamy: Helped perform the experimental analysis with constructive discussion. Enas Alzidi: Helped perform the experimental analysis with constructive discussion. Kawsar Ahmed: Provided the idea, Designed the experiments, Analyzed the data, Wrote the manuscript. Francis M. Bui: Provided the idea, Designed the experiments, Helped perform the experimental analysis with constructive discussion, Supported by funding. Shobhit K. Patel: Helped perform the experimental analysis with constructive discussion. Sami Azam: Helped perform the experimental analysis with constructive discussion. Lway Faisal Abdulrazak: Helped perform the experimental analysis with constructive discussion. Mohammad Ali Moni: Provided the idea, Designed the experiments. Publisher Copyright: © 2023 The Author(s)

PY - 2023/11

Y1 - 2023/11

N2 - 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.

AB - 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.

KW - Artificial intelligence

KW - Depression

KW - Machine learning

KW - Menopause

KW - Quality of life

KW - Random Forest

UR - http://www.scopus.com/inward/record.url?scp=85161885685&partnerID=8YFLogxK

U2 - 10.1016/j.health.2023.100202

DO - 10.1016/j.health.2023.100202

M3 - Article

AN - SCOPUS:85161885685

SN - 2772-4425

VL - 3

SP - 1

EP - 13

JO - Healthcare Analytics

JF - Healthcare Analytics

M1 - 100202

ER -

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

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this