This research demonstrates how large language models can transform mental health screening by providing objective, accessible depression detection and severity assessment.

• Evaluated four LLMs on clinical interview data for depression detection
• Selected the best-performing model for severity evaluation
• Developed a multilingual approach making mental health screening more accessible
• Created a cost-effective solution for early depression detection

This breakthrough has significant implications for clinical practice, enabling more objective assessment of subjective symptoms and potentially increasing access to mental health screening in resource-limited settings.

Leveraging Large Language Models for Cost-Effective, Multilingual Depression Detection and Severity Assessment