🤖 AI Summary
This study addresses the challenge of early, contactless screening for depression and anxiety in perinatal women. We propose a zero-shot visual-language model (VLM)-based facial representation analysis method leveraging routine self-captured facial images. Unlike conventional paradigms reliant on clinical questionnaires or specialized hardware, our approach is the first to apply VLMs to zero-shot facial affect recognition for mental health risk assessment—requiring no labeled data or fine-tuning, thereby substantially enhancing generalizability to real-world settings. Evaluated on a real-world clinical dataset, the VLM achieves 77.6% accuracy, significantly outperforming a fine-tuned CNN baseline. Our results demonstrate the feasibility of using everyday selfies for preliminary perinatal psychological assessment and establish a novel, scalable pathway toward AI-driven, equitable mental health interventions.
📝 Abstract
Major Depressive Disorder and anxiety disorders affect millions globally, contributing significantly to the burden of mental health issues. Early screening is crucial for effective intervention, as timely identification of mental health issues can significantly improve treatment outcomes. Artificial intelligence (AI) can be valuable for improving the screening of mental disorders, enabling early intervention and better treatment outcomes. AI-driven screening can leverage the analysis of multiple data sources, including facial features in digital images. However, existing methods often rely on controlled environments or specialized equipment, limiting their broad applicability. This study explores the potential of AI models for ubiquitous depression-anxiety screening given face-centric selfies. The investigation focuses on high-risk pregnant patients, a population that is particularly vulnerable to mental health issues. To cope with limited training data resulting from our clinical setup, pre-trained models were utilized in two different approaches: fine-tuning convolutional neural networks (CNNs) originally designed for facial expression recognition and employing vision-language models (VLMs) for zero-shot analysis of facial expressions. Experimental results indicate that the proposed VLM-based method significantly outperforms CNNs, achieving an accuracy of 77.6%. Although there is significant room for improvement, the results suggest that VLMs can be a promising approach for mental health screening.