Deep learning with ensemble-based hybrid AI model for bipolar and unipolar depression detection using demographic and behavioral based on time-series data

Deep learning with ensemble-based hybrid AI model for bipolar and unipolar depression detection using demographic and behavioral based on time-series data

Background Depression, including Bipolar and Unipolar types, is a widespread mental health issue. Conventional diagnostic methods rely on subjective assessments, leading to possible underreporting and bias. Machine learning (ML) and deep learning (DL) offer automated approaches to detect depression...

Full description

Saved in:
Bibliographic Details
Main Authors: Naga Raju Kanchapogu, Sachi Nandan Mohanty
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Dialogues in Clinical Neuroscience
Subjects:
Depression prediction
bipolar disorder
unipolar depression
actigraph time-series analysis
machine learning
hybrid deep learning model
Online Access:https://www.tandfonline.com/doi/10.1080/19585969.2025.2524337
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Depression, including Bipolar and Unipolar types, is a widespread mental health issue. Conventional diagnostic methods rely on subjective assessments, leading to possible underreporting and bias. Machine learning (ML) and deep learning (DL) offer automated approaches to detect depression using behavioral and demographic data.Methods This study proposes a hybrid AI framework combining structured demographic features with synthetic actigraph time-series data. Demographic data is modeled using an XGBoost ensemble, while temporal data is analyzed through a deep convolutional neural network (CNN). The training pipeline includes stratified k-fold cross-validation, hyperparameter tuning, and statistical testing. Model explainability is enhanced using SHAP (XGBoost) and Grad-CAM (CNN).Results The hybrid model demonstrated strong classification performance across metrics like accuracy, sensitivity, and specificity. Integrating temporal and static features improved prediction of Bipolar and Unipolar Depression. Interpretability tools revealed key features and time patterns influencing predictions.Conclusions This work introduces a robust and interpretable framework for depression classification using synthetic multimodal data. While not clinically validated, the model serves as a methodological foundation for future research with real-world datasets.
ISSN:1958-5969

Similar Items