# Passive Assessment of Depression Severity from AI Mental Health Conversations: A Large Model Fine-Tuning Approach

> This article introduces a passive assessment method for depression severity based on large language models, which enables continuous symptom monitoring without additional questionnaires by analyzing conversation content between users and AI mental health applications.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-06-16T14:28:47.000Z
- 最近活动: 2026-06-17T02:34:24.956Z
- 热度: 138.9
- 关键词: 心理健康, 抑郁症, PHQ-9, 被动监测, 大语言模型, AI对话, 症状评估, arXiv
- 页面链接: https://www.zingnex.cn/en/forum/thread/ai-6c411cdf
- Canonical: https://www.zingnex.cn/forum/thread/ai-6c411cdf
- Markdown 来源: floors_fallback

---

## [Introduction] Passive Assessment of Depression via AI Conversations: Core Exploration of Large Model Fine-Tuning Methods

This article introduces a passive assessment method for depression severity based on large language models (LLMs), aiming to address issues such as low completion rates and selection bias in traditional self-report scales (e.g., PHQ-9). By analyzing daily conversations between users and AI mental health applications, this method enables continuous symptom monitoring without additional questionnaires. The study uses real user data, combined with a pseudo-label data augmentation strategy, to fine-tune the open-source model Qwen3.5-27B, achieving good predictive performance and opening up new directions for mental health monitoring.

## Dilemmas of Traditional Mental Health Monitoring and the Need for Passive Monitoring

Depression is the leading cause of disability globally, and early identification is crucial. However, traditional scales like PHQ-9 have limitations: low completion rates, selection bias, low temporal resolution, and additional burden. An ideal monitoring approach should be passive—automatically collecting data while users use services normally, enabling continuous monitoring, reducing burden, and minimizing bias.

## Research Method Design: Data, Model, and Training Strategy

1. Data foundation: Conversation data from 3111 users + PHQ-9 labels; 2. Data augmentation: Using Claude Opus to generate pseudo-labels, expanding to 6283 users; 3. Model architecture: Qwen3.5-27B base model + regression head to predict PHQ-9 total score; 4. Training strategy: Supervised learning fine-tuning to optimize prediction accuracy.

## Experimental Results: Model Performance and Clinical Value

On the test set of 842 users, the model performance is as follows: MAE=2.6 points (small average deviation), RMSE=4.0 points, Pearson correlation coefficient r=0.80 (strong correlation), AUC=0.91 at the PHQ-9≥10 threshold (good classification ability). The AUC exceeds 0.87 across all severity thresholds, covering the entire clinical spectrum.

## Technical Contributions and Application Prospects

Contributions: The first large-scale real-user validation study, pseudo-label data augmentation strategy, and open-source model achieving commercial model performance. Application prospects: Continuous symptom monitoring, early warning, personalized intervention, and auxiliary research data collection.

## Ethical Considerations and Research Limitations

Ethical issues: Informed consent, data privacy, clinical boundaries (cannot replace professional diagnosis), and intervention responsibility. Limitations: Sample representativeness (users of specific applications), dependence on conversation quality, lack of longitudinal validation, and unclear causal relationships. Future directions: Validation in diverse populations, interpretability research, expansion to other mental conditions, and long-term longitudinal studies.

## Industry Insights and Conclusion

Insights: Reassessing the value of conversation data, shifting product design to unobtrusive monitoring, and integrating auxiliary tools into clinical practice. Conclusion: This method represents progress in mental health monitoring technology; it is necessary to balance technological innovation and ethical responsibility, providing valuable experience for the industry.