A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study

Jinling Wang; Michaela Black; Debbie Rankin; J. G. Wallace; Catherine Hughes; L. Hoey; AJ Moore; Joshua Tobin; Mimi Zhang; James Ng; G, et al Horigan; Paul Carlin; Kevin McCarroll; Conal Cunningham; H McNulty; Anne Molloy

doi:10.36922/AIH025070009

A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study

Jinling Wang
, Michaela Black
, Debbie Rankin
, J. G. Wallace
, Catherine Hughes
, L. Hoey
, AJ Moore
, Joshua Tobin
, Mimi Zhang
, James Ng
, G, et al Horigan
, Paul Carlin
, Kevin McCarroll
, Conal Cunningham
, H McNulty
, Anne Molloy

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

14 Downloads (Pure)

Abstract

Anxiety disorders (ADs) rank among the most prevalent mental health problems, especially in older people. The high risk and prevalence of ADs underscore the need for effective mental health care. Artificial intelligence has gained popularity in the diagnosis and prediction of medical conditions and diseases, including mental health problems. In this study, we developed an adapted bagging ensemble machine learning system that can be used for the diagnosis and prediction of ADs and can address the challenges posed by extremely imbalanced data from the Trinity-Ulster-Department of Agriculture study. Statistical techniques were used to identify the risk factors for ADs. Feature selection and feature engineering were conducted based on the analysis of biomarker risk factors. Five machine learning methods have been used in the developed system to build weak learner submodels, yielding promising prediction results. Some risk factors were identified. These findings will benefit the early prediction of ADs in our future studies.

Original language	English
Pages (from-to)	1-22
Number of pages	22
Journal	Artificial Intelligence in Health
Early online date	8 Sept 2025
DOIs	https://doi.org/10.36922/AIH025070009
Publication status	Published online - 8 Sept 2025

Bibliographical note

Data Access Statement

The data will not be shared due to some concerns. For more data information, please refer to the relevant research works.7,26-28

Funding

The TUDA study was supported by government funding from the Irish Department of Agriculture, Food and the Marine, and Health Research Board (under the Food Institutional Research Measure), as well as from the Northern Ireland Department for Employment and Learning (under its Strengthening the All-Island Research Base Initiative). The AIM4HEALTH project gratefully acknowledges the support of the higher education authority, Department of Further and Higher Education, Research, Innovation and Science, and the Shared Island Fund, and the SFI grant 21/RC/10295_P2.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

anxiety disorder
bagging ensemble machine learning
risk factor analysis
diagnosis
imbalanced data
ageing

Access to Document

10.36922/AIH025070009

manuscript_aih05561.cleanedFinal published version, 4.8 MBLicence: CC BY

Cite this

Wang, J., Black, M., Rankin, D., Wallace, J. G., Hughes, C., Hoey, L., Moore, AJ., Tobin, J., Zhang, M., Ng, J., Horigan, G. E. A., Carlin, P., McCarroll, K., Cunningham, C., McNulty, H., & Molloy, A. (2025). A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study. Artificial Intelligence in Health, 1-22. Advance online publication. https://doi.org/10.36922/AIH025070009

@article{f1556cbac63c48b68cf1c5d7b95962b1,

title = "A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study",

abstract = "Anxiety disorders (ADs) rank among the most prevalent mental health problems, especially in older people. The high risk and prevalence of ADs underscore the need for effective mental health care. Artificial intelligence has gained popularity in the diagnosis and prediction of medical conditions and diseases, including mental health problems. In this study, we developed an adapted bagging ensemble machine learning system that can be used for the diagnosis and prediction of ADs and can address the challenges posed by extremely imbalanced data from the Trinity-Ulster-Department of Agriculture study. Statistical techniques were used to identify the risk factors for ADs. Feature selection and feature engineering were conducted based on the analysis of biomarker risk factors. Five machine learning methods have been used in the developed system to build weak learner submodels, yielding promising prediction results. Some risk factors were identified. These findings will benefit the early prediction of ADs in our future studies.",

keywords = "anxiety disorder, bagging ensemble machine learning, risk factor analysis, diagnosis, imbalanced data, ageing",

author = "Jinling Wang and Michaela Black and Debbie Rankin and Wallace, \{J. G.\} and Catherine Hughes and L. Hoey and AJ Moore and Joshua Tobin and Mimi Zhang and James Ng and Horigan, \{G, et al\} and Paul Carlin and Kevin McCarroll and Conal Cunningham and H McNulty and Anne Molloy",

note = "{\textcopyright} 2025 Author(s). ",

year = "2025",

month = sep,

day = "8",

doi = "10.36922/AIH025070009",

language = "English",

pages = "1--22",

journal = "Artificial Intelligence in Health",

issn = "3029-2387",

publisher = "AccScience Publishing",

}

Wang, J , Black, M , Rankin, D , Wallace, JG , Hughes, C , Hoey, L , Moore, AJ, Tobin, J, Zhang, M, Ng, J, Horigan, GEA, Carlin, P, McCarroll, K, Cunningham, C, McNulty, H & Molloy, A 2025, 'A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study', Artificial Intelligence in Health, pp. 1-22. https://doi.org/10.36922/AIH025070009

TY - JOUR

T1 - A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study

AU - Wang, Jinling

AU - Black, Michaela

AU - Rankin, Debbie

AU - Wallace, J. G.

AU - Hughes, Catherine

AU - Hoey, L.

AU - Moore, AJ

AU - Tobin, Joshua

AU - Zhang, Mimi

AU - Ng, James

AU - Horigan, G, et al

AU - Carlin, Paul

AU - McCarroll, Kevin

AU - Cunningham, Conal

AU - McNulty, H

AU - Molloy, Anne

PY - 2025/9/8

Y1 - 2025/9/8

N2 - Anxiety disorders (ADs) rank among the most prevalent mental health problems, especially in older people. The high risk and prevalence of ADs underscore the need for effective mental health care. Artificial intelligence has gained popularity in the diagnosis and prediction of medical conditions and diseases, including mental health problems. In this study, we developed an adapted bagging ensemble machine learning system that can be used for the diagnosis and prediction of ADs and can address the challenges posed by extremely imbalanced data from the Trinity-Ulster-Department of Agriculture study. Statistical techniques were used to identify the risk factors for ADs. Feature selection and feature engineering were conducted based on the analysis of biomarker risk factors. Five machine learning methods have been used in the developed system to build weak learner submodels, yielding promising prediction results. Some risk factors were identified. These findings will benefit the early prediction of ADs in our future studies.

AB - Anxiety disorders (ADs) rank among the most prevalent mental health problems, especially in older people. The high risk and prevalence of ADs underscore the need for effective mental health care. Artificial intelligence has gained popularity in the diagnosis and prediction of medical conditions and diseases, including mental health problems. In this study, we developed an adapted bagging ensemble machine learning system that can be used for the diagnosis and prediction of ADs and can address the challenges posed by extremely imbalanced data from the Trinity-Ulster-Department of Agriculture study. Statistical techniques were used to identify the risk factors for ADs. Feature selection and feature engineering were conducted based on the analysis of biomarker risk factors. Five machine learning methods have been used in the developed system to build weak learner submodels, yielding promising prediction results. Some risk factors were identified. These findings will benefit the early prediction of ADs in our future studies.

KW - anxiety disorder

KW - bagging ensemble machine learning

KW - risk factor analysis

KW - diagnosis

KW - imbalanced data

KW - ageing

UR - https://pure.ulster.ac.uk/en/publications/f1556cba-c63c-48b6-8cf1-c5d7b95962b1

U2 - 10.36922/AIH025070009

DO - 10.36922/AIH025070009

M3 - Article

SN - 3029-2387

SP - 1

EP - 22

JO - Artificial Intelligence in Health

JF - Artificial Intelligence in Health

ER -

A Bagging Ensemble Machine Learning Method for Imbalanced Data to Predict Anxiety Disorders and Analysis of Risk Factors in Older People: Observational Study

Abstract

Bibliographical note

Data Access Statement

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this