Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.08591 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913985771601920 |
|---|---|
| author | Moon, Sehwan Lee, Aram Kim, Jeong Eun Kang, Hee-Ju Shin, Il-Seon Kim, Sung-Wan Kim, Jae-Min Jhon, Min Kim, Ju-Wan |
| author_facet | Moon, Sehwan Lee, Aram Kim, Jeong Eun Kang, Hee-Ju Shin, Il-Seon Kim, Sung-Wan Kim, Jae-Min Jhon, Min Kim, Ju-Wan |
| contents | Advances in large language models (LLMs) have enabled a wide range of applications. However, depression prediction is hindered by the lack of large-scale, high-quality, and rigorously annotated datasets. This study introduces DepressLLM, trained and evaluated on a novel corpus of 3,699 autobiographical narratives reflecting both happiness and distress. DepressLLM provides interpretable depression predictions and, via its Score-guided Token Probability Summation (SToPS) module, delivers both improved classification performance and reliable confidence estimates, achieving an AUC of 0.789, which rises to 0.904 on samples with confidence $\geq$ 0.95. To validate its robustness to heterogeneous data, we evaluated DepressLLM on in-house datasets, including an Ecological Momentary Assessment (EMA) corpus of daily stress and mood recordings, and on public clinical interview data. Finally, a psychiatric review of high-confidence misclassifications highlighted key model and data limitations that suggest directions for future refinements. These findings demonstrate that interpretable AI can enable earlier diagnosis of depression and underscore the promise of medical AI in psychiatry. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08591 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives Moon, Sehwan Lee, Aram Kim, Jeong Eun Kang, Hee-Ju Shin, Il-Seon Kim, Sung-Wan Kim, Jae-Min Jhon, Min Kim, Ju-Wan Computation and Language Artificial Intelligence Advances in large language models (LLMs) have enabled a wide range of applications. However, depression prediction is hindered by the lack of large-scale, high-quality, and rigorously annotated datasets. This study introduces DepressLLM, trained and evaluated on a novel corpus of 3,699 autobiographical narratives reflecting both happiness and distress. DepressLLM provides interpretable depression predictions and, via its Score-guided Token Probability Summation (SToPS) module, delivers both improved classification performance and reliable confidence estimates, achieving an AUC of 0.789, which rises to 0.904 on samples with confidence $\geq$ 0.95. To validate its robustness to heterogeneous data, we evaluated DepressLLM on in-house datasets, including an Ecological Momentary Assessment (EMA) corpus of daily stress and mood recordings, and on public clinical interview data. Finally, a psychiatric review of high-confidence misclassifications highlighted key model and data limitations that suggest directions for future refinements. These findings demonstrate that interpretable AI can enable earlier diagnosis of depression and underscore the promise of medical AI in psychiatry. |
| title | DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.08591 |