Adverse Childhood Experiences and Social Determinants of Mental Health as Predictors of Adult Depression: A Machine Learning Approach.
Saved in:
| Title: | Adverse Childhood Experiences and Social Determinants of Mental Health as Predictors of Adult Depression: A Machine Learning Approach. |
|---|---|
| Authors: | Han, Eunae, Shin, Jihoon |
| Source: | Journal of Counseling & Development (John Wiley & Sons, Inc.). Apr2026, Vol. 104 Issue 2, p268-279. 12p. |
| Subjects: | Mental illness risk factors, Competency assessment (Law), Mental depression risk factors, Risk assessment, Boosting algorithms, Health services accessibility, Sexual orientation, Cultural awareness, Random forest algorithms, Medical care use, Social determinants of health, Income, Receiver operating characteristic curves, Sex distribution, Unemployment, Food security, Logistic regression analysis, Probability theory, Interviewing, Loneliness, Family history (Medicine), Descriptive statistics, Race, Surveys, Emotional trauma, Need (Psychology), Machine learning, Counseling, Housing, Discrimination (Sociology), Sociodemographic factors, Decision trees, Accuracy, Social support, Data analysis software, Adverse childhood experiences, Educational attainment, Neighborhood characteristics, Algorithms, Predictive validity, Sensitivity & specificity (Statistics), Evaluation, Adults |
| Abstract: | This study applied machine learning (ML) models to the 2023 Behavioral Risk Factor Surveillance System (BRFSS) dataset, a nationally representative and state‐based survey conducted annually by the Centers for Disease Control and Prevention (CDC), to examine how adverse childhood experiences (ACEs) and social determinants of mental health (SDMH) predict adult depressive disorders. Among ML models, eXtreme Gradient Boosting (XGBoost) achieved the strongest performance, and we identified key predictors, including family history of mental illness, sex, total ACE score, loneliness, unemployment, and healthcare barriers. Subgroup analyses revealed variation across racial groups, showing the need for culturally responsive approaches. We discuss the utility of ML for advancing early identification, trauma‐informed counseling practice, and equity‐focused prevention strategies. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Counseling & Development (John Wiley & Sons, Inc.) is the property of John Wiley & Sons, Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | This study applied machine learning (ML) models to the 2023 Behavioral Risk Factor Surveillance System (BRFSS) dataset, a nationally representative and state‐based survey conducted annually by the Centers for Disease Control and Prevention (CDC), to examine how adverse childhood experiences (ACEs) and social determinants of mental health (SDMH) predict adult depressive disorders. Among ML models, eXtreme Gradient Boosting (XGBoost) achieved the strongest performance, and we identified key predictors, including family history of mental illness, sex, total ACE score, loneliness, unemployment, and healthcare barriers. Subgroup analyses revealed variation across racial groups, showing the need for culturally responsive approaches. We discuss the utility of ML for advancing early identification, trauma‐informed counseling practice, and equity‐focused prevention strategies. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 15566676 |
| DOI: | 10.1002/jcad.70029 |
