The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Enhancing Depression Detection with Chain-of-Thought Prompting: From Emotion to Reasoning Using Large Language Models
Open accessAbstract
Depression is one of the leading causes of disability worldwide, posing a severe burden on individuals, healthcare systems, and society at large. Recent advancements in Large Language Models (LLMs) have shown promise in addressing mental health challenges, including the detection of depression through text-based analysis. However, current LLM-based methods often struggle with nuanced symptom identification and lack a transparent, step-by-step reasoning process, making it difficult to accurately classify and explain mental health conditions. To address these challenges, we propose a Chain-of-Thought Prompting approach that enhances both the performance and interpretability of LLM-based depression detection. Our method breaks down the detection process into four stages: (1) sentiment analysis, (2) binary depression classification, (3) identification of underlying causes, and (4) assessment of severity. By guiding the model through these structured reasoning steps, we improve interpretability and reduce the risk of overlooking subtle clinical indicators. We validate our method on the E-DAIC dataset, where we test multiple state-of-the-art large language models. Experimental results indicate that our Chain-of-Thought Prompting technique yields superior performance in both classification accuracy and the granularity of diagnostic insights, compared to baseline approaches.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“the majority of reviewed studies leverage the inherent text generation capabilities of LLMs to produce explanations as a natural by-product of inference [62,71,72,78,97,112].”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [78]
In the citing paper
“Chain-of-Thought prompting [62,64,78] and natural language explanation generation [72,74,75] produce outputs that align with clinical reasoning conventions, mimicking the differential diagnosis process familiar to practitioners.”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [78]
In the citing paper
“The verbose reasoning traces produced by agentic decomposition systems and reasoning models [74, 78] are valuable for retrospective audit but may overwhelm a clinician seeking a rapid decision aid during a time-pressured consultation.”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [78]
In the citing paper
“This is particularly consequential given the growing prominence of Chinese-language medical LLMs and knowledge graph approaches, as well as the identified importance of models such as Qwen, DeepSeek, and ChatGLM in our reviewed studies [78,87,99].”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [78]
In the citing paper
“A third, more recent group uses a clinical instrument to organize the reasoning process itself rather than the explanation surface [74,77-79].”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [78]
In the citing paper
“This is particularly consequential given the growing prominence of Chinese-language medical LLMs and knowledge graph approaches, as well as the identified importance of models such as Qwen, DeepSeek, and ChatGLM in our reviewed studies [78,87,99].”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [78]
Citations
Cites
The PHQ-9: Validity of a brief depression severity measure
Kroenke, K., Spitzer, R. L., & Williams, J. B. W. (2001) · Journal of General Internal Medicine · doi:10.1046/j.1525-1497.2001.016009606.x · Cited by 44,910
A concordance correlation coefficient to evaluate reproducibility.
Lin, L. I.-K. (1989) · Biometrics · doi:10.2307/2532051 · Cited by 8,785
Self-citationSantomauro, D. F., Mantilla Herrera, A. M., Shadid, J., Zheng, P., Ashbaugh, C., Pigott, D. M., Abbafati, C., Adolph, C., Amlag, J. O., Aravkin, A. Y., et al. (2021) · The Lancet · doi:10.1016/s0140-6736(21)02143-7 · Cited by 5,444
The PHQ-8 as a measure of current depression in the general population
Kroenke, K., Strine, T. W., Spitzer, R. L., Williams, J. B. W., Berry, J. T., & Mokdad, A. H. (2009) · Journal of Affective Disorders · doi:10.1016/j.jad.2008.06.026 · Cited by 5,121
Explainability for artificial intelligence in healthcare: a multidisciplinary perspective
the Precise4Q consortium, Amann, J., Blasimme, A., Vayena, E., Frey, D., & Madai, V. I. (2020) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-020-01332-6 · Cited by 2,203
Ringeval, F., Schuller, B., Valstar, M., Cummins, N., Cowie, R., Tavabi, L., Schmitt, M., Alisamir, S., Amiriparian, S., Messner, E.-M., et al. (2019) · Proceedings of the 9th International on Audio/Visual Emotion Challenge and Workshop · doi:10.1145/3347320.3357688 · Cited by 409
Al-Mosaiwi, M., & Johnstone, T. (2018) · Clinical Psychological Science · doi:10.1177/2167702617747074 · Cited by 304 · cited 1×
“Identifying such patterns requires structured evaluation, yet current LLMs struggle with this task [7].”
MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models
Yang, K., Zhang, T., Kuang, Z., Xie, Q., Huang, J., & Ananiadou, S. (2024) · International World Wide Web Conference (WWW) · doi:10.1145/3589334.3648137 · Cited by 275
CubeMLP: An MLP-based Model for Multimodal Sentiment Analysis and Depression Estimation
Sun, H., Wang, H., Liu, J., Chen, Y., & Lin, L. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548025 · Cited by 191
Self-citationMulti-Modal Adaptive Fusion Transformer Network for the Estimation of Depression Level
Sun, H., Liu, J., Chai, S., Qiu, Z., Lin, L., Huang, X., & Chen, Y. (2021) · Sensors · doi:10.3390/s21144764 · Cited by 104
Self-citationSun, H., Chen, Y., & Lin, L. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3233070 · Cited by 81
Self-citationMultimodal Sentiment Analysis With Mutual Information-Based Disentangled Representation Learning
Sun, H., Niu, Z., Wang, H., Yu, X., Liu, J., Chen, Y.-W., & Lin, L. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3529732 · Cited by 28
Self-citationMulti-Modal and Multi-Task Depression Detection with Sentiment Assistance
Teng, S., Chai, S., Liu, J., Tateyama, T., Lin, L., & Chen, Y. (2024) · International Conference on Consumer Electronics · doi:10.1109/icce59016.2024.10444213 · Cited by 25
Self-citationTeng, S., Chai, S., Liu, J., Tateyama, T., Lin, L., & Chen, Y. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782904 · Cited by 5
Self-citation
Cited by
Sorted by citations
Hussain, N., Qasim, A., Mehak, G., Zain, M., Sidorov, G., Gelbukh, A. F., & Kolesnikova, O. (2025) · AI · doi:10.3390/ai6070157 · Cited by 26
LLA MADRS: Evaluating Open-Source LLMs on Real Clinical Interviews—To Reason or Not to Reason?
Kebe, G. Y., Girard, J. M., Liebenthal, E., Baker, J., la Torre, F. D., & Morency, L. (2026) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl.a.741 · Cited by 14
Natural language processing for mental health assessment: a survey and comparative evaluation
Cao, Y., Xiao, G. G., Xi, P., Okuhara, S., Fan, Y., & Liu, Z. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01146-1 · Cited by 2
Shimgekar, S. R., Zhao, R., Goyal, A., Rodriguez, V. J., Bloom, P. A., Kumar, N., Sundaram, H., & Saha, K. (2026) · ACM Web Science Conference (WebSci) · doi:10.1145/3795766.3799758 · Cited by 4
Cantini, A., & Mauro, A. D. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10070224 · Cited by 1
Metadata
- Authors
- Teng, S., Liu, J., Kumar Jain, R., Chai, S., Hou, R., Tateyama, T., Lin, L., & Chen, Y.-W.
- Affiliations
- Ritsumeikan University (JP)
- Ritsumeikan University,College of Information Science and Engineering,Osaka,Japan
- Fujita Health University (JP)
- Zhejiang University (CN)
- Venue
- 2025 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Publisher
- IEEE
- Published
- 2025-07-14
- Volume
- 2025
- Pages
- 1-6
- ISSN
- 2375-7477 (ISSN-L)
- OpenAlex
- W4416960928
- Cited by
- 12
- References
- 14
- Citations by year
- 2026: 12
- FWCI
- 22.85
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Japan Society for the Promotion of Science (23K16909)
- Topics
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- depression detection, chain-of-thought prompting, large language models, interpretability, sentiment analysis, depression severity assessment
- MeSH terms
- Large Language Models, Algorithms, Depression, Emotions, Humans, Language, Natural Language Processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
