Research map / Large language models / Agents, code and math
Unveiling the Landscape of Clinical Depression Assessment: From Behavioral Signatures to Psychiatric Reasoning
Zhuang Chen, Guanqun Bi, Wen Zhang, Jiawei Hu, Aoyun Wang, Xiyao Xiao, Kun Feng, Minlie Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Psychiatric Reasoning prompt vs Direct (zero-shot) | GPT-4o · C-MIND | Macro-F1: +7.01% | Improved |
| add Psychiatric Reasoning prompt vs Direct (zero-shot) | Qwen3-235B-A22B (non-thinking) · C-MIND | Macro-F1: +3.67% | Improved |
| add Vanilla Reasoning vs Direct (few-shot) | GPT-4o · C-MIND | Macro-F1: +7.31% | Improved |
| add Psychiatric Reasoning vs Direct (few-shot) | GPT-4o · C-MIND | Macro-F1: +8.34% | Improved |
| add Vanilla Reasoning vs Direct (few-shot) | DeepSeek-R1 · C-MIND | Macro-F1: -22.5% | Hurt |
| add Psychiatric Reasoning vs Direct (few-shot) | DeepSeek-R1 · C-MIND | Macro-F1: -11.96% | Hurt |
| add reasoning prompts under few-shot | DeepSeek-V3 · C-MIND | Macro-F1 | Hurt |
| use multimodal input (audio, video, transcript) instead of transcript only | Qwen2.5-Omni · C-MIND | Macro-F1: 46.36%, below transcript-only LLMs | Hurt |
| add VFT to INT transcript input (ablation) | GPT-4o · C-MIND | Macro-F1: 50.48% -> 55.68% | Improved |
| add Psychiatric Reasoning to INT+VFT (ablation) | GPT-4o · C-MIND | Macro-F1: 55.68% -> 60.53% | Improved |
| fuse modalities (e.g. audio and video) (ablation) | classical models · C-MIND | Macro-F1 | Improved |
| fuse tasks (e.g. INT and PDT) (ablation) | classical models · C-MIND | Macro-F1 | Improved |
Closest papers by meaning
- MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis (NeurIPS 2025 · similarity 0.85)
- Mental-Perceiver: Audio-Textual Multi-Modal Learning for Estimating Mental Disorders (AAAI 2025 · similarity 0.85)
- Neural Signals Generate Clinical Notes in the Wild (NeurIPS 2026 · similarity 0.83)
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces (NeurIPS 2026 · similarity 0.82)
- Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks (ICLR 2026 · similarity 0.82)
- From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity (ICLR 2026 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
