AI Research

PsyBridge: A Hybrid Intelligent Framework for Multi... | AI Research

Key Takeaways

PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support Mental health assessments often rely on isolate...
Mental health assessment commonly relies on isolated screening instruments or data-driven models that often lack interpretability and multi-dimensional integration.
Existing approaches frequently focus on individual indicators such as depression or anxiety while providing limited support for comprehensive and explainable decision-making.
To evaluate the framework, a semi-synthetic dataset consisting of 500 patient profiles representing varying severity levels was constructed based on clinically grounded score distributions.
Experimental results demonstrate that PsyBridge achieves an overall accuracy of 0.84, outperforming standalone PHQ-9 and GAD-7 assessments while improving precision, recall, and F1-score.

Paper AbstractExpand

Mental health assessment commonly relies on isolated screening instruments or data-driven models that often lack interpretability and multi-dimensional integration. Existing approaches frequently focus on individual indicators such as depression or anxiety while providing limited support for comprehensive and explainable decision-making. To address this limitation, this study proposes PsyBridge, a hybrid intelligent decision-support framework designed for multi-dimensional mental health assessment through the integration of clinically validated screening tools, cognitive evaluation, and personality profiling within a unified architecture. The proposed framework incorporates PHQ-9 and GAD-7 assessments alongside cognitive and behavioural indicators using a modular design and a weighted aggregation mechanism to generate interpretable mental health risk classifications and recommendations. To evaluate the framework, a semi-synthetic dataset consisting of 500 patient profiles representing varying severity levels was constructed based on clinically grounded score distributions. Experimental results demonstrate that PsyBridge achieves an overall accuracy of 0.84, outperforming standalone PHQ-9 and GAD-7 assessments while improving precision, recall, and F1-score. Sensitivity analysis and ablation studies further indicate that integrating cognitive and personality components contributes to more stable classification performance and reduces inconsistencies in moderate-risk prediction. The findings suggest that PsyBridge provides a scalable and interpretable approach for AI-assisted mental health decision support, particularly within digital healthcare and telehealth environments.

PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support
Mental health assessments often rely on isolated tools—such as questionnaires for depression or anxiety—that fail to capture the full picture of a patient’s well-being. This paper introduces PsyBridge, a framework designed to bridge this gap by combining traditional clinical screening with cognitive and personality assessments. By integrating these diverse data points into a single, unified system, the researchers aim to provide a more comprehensive and explainable way to evaluate mental health risks in digital and clinical settings.

A Multi-Dimensional Approach

Existing mental health tools often focus on a single condition, which can lead to fragmented or incomplete evaluations. PsyBridge addresses this by using a modular architecture that gathers data from four key areas: clinical screening (using the PHQ-9 for depression and GAD-7 for anxiety), cognitive testing (measuring memory and attention), and personality profiling (using MBTI-based mapping). By bringing these different sources together, the framework creates a more holistic view of an individual's mental state than any single test could provide on its own.

How the System Makes Decisions

To ensure that different types of data—which use different scoring scales—can be compared, PsyBridge first normalizes all inputs to a standard range. It then uses a "weighted aggregation" mechanism to calculate a final risk score. In this model, clinical screening tools are given the most weight because of their established reliability, while cognitive and personality data serve as important supporting context. This process results in a clear risk classification—Low, Moderate, or High—which provides actionable insights for clinicians while maintaining transparency about how the final score was reached.

Performance and Reliability

To test the framework, the researchers used a semi-synthetic dataset of 500 patient profiles. The results showed that PsyBridge achieved an overall accuracy of 0.84, outperforming the use of standalone PHQ-9 or GAD-7 assessments. Furthermore, the study found that including cognitive and personality data helped stabilize the system’s performance, particularly in cases where the risk level was moderate. This suggests that the multi-dimensional approach reduces the inconsistencies often found in traditional, single-domain screening.

Future Directions

While the initial results are promising, the researchers note that the current framework is a foundational step. Future work will focus on validating the system using real-world clinical datasets rather than synthetic ones. Additionally, the team plans to develop data-driven weighting strategies that could allow the system to learn and adapt its decision-making process over time, further improving its accuracy and utility for healthcare professionals.

Comments (0)

No comments yet

Be the first to share your thoughts!